All papers By lab By lab
The companies, universities and labs behind the papers, with the most papers first. A lab shows here when Hugging Face, the paper's code or its authors' listed institutions name it, so it grows every day.
10 7
AeroZoo: A Benchmark of Well-Posed Flow Problems for Foundation Models of Aerodynamics Nov 12 Lara Mini Base: Language Diversity as a Resource, Not a Trade-off Nov 12 Kezek: Splitting Mono Two-Person Conversations into Per-Speaker Tracks for Full-Duplex Dialogue Data Nov 12 See all 29 papers →
7 4
HyPLM Technical Report Nov 9 HyInv Technical Report Nov 9 Do Recommenders Need to Think in Words? Latent Reasoning for Efficient LLM-Based Recommendation Nov 5 See all 21 papers →
7 6
Few-Step Streaming Video Generation via Condition Shifting Nov 10 Tools Need Not Speak in Text: Latent Context Compression for Agents Nov 3 MKD2World: A Typed Spatial MarkDown World Model For Web Agents Nov 4 See all 20 papers →
4 3
Experience-Handoff Reinforcement Learning for Recursive Self-Improvement Nov 12 Don't Just Trust Your Memory: Evidence-Linked Memory Reduces Memory-Induced Degradation in LLM Agents Nov 10 EDGAR: Efficient Diffusion-Driven Gaussian Avatar Refinement via Synthetic Failure Nov 5 See all 19 papers →
7 5
Actor, Judge, or Teacher? Understanding Decision Models in Long-Horizon Agents Nov 12 AutoVend: Benchmarking LLM Agents on Long-Horizon Autonomous Vending Operations Oct 27 SplatAnything: Gaussian Spacing Normalization for Feed-forward 3DGS across Arbitrary Scenes Nov 5 See all 19 papers →
10 3
Is Your Robot's Memory Just a Clock? Temporal Shortcuts in Memory-Augmented VLA Policies Nov 10 Predictive Surprise as Self-Grounding Concept Bottleneck for Interpretable Time Series Nov 6 HiVe-Mem: Interleaving Horizontal Memory Expansion and Vertical Evidence Composition for Multimodal Agents Nov 8 See all 19 papers →
6 3
SWAM: Scaling World Action Models with Cross-Modal Alignment Nov 8 Harness-S: Learning from Sibling Harnesses for Generalizable Agent Training Nov 2 3DGS-VBench+ and 3DGSV-Assessor: A Multi-Dimensional Subjective Benchmark and a Reference-Flexible Objective Model for 3D Gaussian Splatting Video Quality Assessment Nov 3 See all 18 papers →
5 3
RF3DGS: Reflection-Free 3D Gaussian Splatting with Self-Priors Nov 10 ProQuant: Progressive Quantization-aware Training for Edge MLLMs Nov 5 AttnSR: Attention Step Reward for Long-Horizon Agentic RL Nov 5 See all 16 papers →
5 4
EgoX: Egocentric Cross-Embodiment Manipulation with Embodiment Dreaming Nov 12 "PRISM" Is Not All You Need: Cross-Topic Name Collisions and Scientific Paper Retrieval Oct 31 Random Is Almost Enough? Stable and Low-Cost Benchmark Compression via BestRand Oct 30 See all 15 papers →
7 3
MCPHallu: Benchmarking Reasoning, Execution, and Memory Hallucinations in MCP Agents Nov 5 Guidance Is a Field, Not a Scalar: Interval-Integrated Classifier-Free Guidance for One-Step Video Generation Nov 5 Softmax Attention with Any Temperature in Fixed Dimension: Matching the Best Known Maximum-Inner-Product Bounds Nov 4 See all 15 papers →
3 2
Beneath the Surface: What We Overlook When We Talk About Agent Evolution Nov 4 ElecLoad: Adaptive Electricity Load Forecasting Guided by Multiple Events Nov 4 Sekai: Incremental Event Memory for Generalized Reasoning Video Segmentation Nov 4 See all 14 papers →
5 4
SIRIS: Can LLMs Tell When Simulation Errors Matter in AI-Driven Systems Research Nov 5 HarnessFlow: MCTS-Guided Harness Optimization for LLM Agents Nov 4 WebHarbor: Docking Real Websites for Evolving GUI Agent Environments Nov 2 See all 14 papers →
5 3
SO-Arena: Benchmarking the Capability Spectrum and Reliability of System One Models Nov 11 Learning to Act with World Models by Valuing What Comes Next Nov 9 Conformal Prediction for Distribution-to-Distribution Regression Nov 4 See all 13 papers →
3 2
UniSpark: Exploring Hybrid Attention for Multimodal Understanding and Generation Nov 12 Duo: A Reciprocal World Model for Full-Duplex Interaction Nov 11 ZoomGain: Mining Global-to-Zoom Perception Gaps for Fine-Grained Visual Supervision Nov 10 See all 12 papers →
3 3
Do Multi-Turn Conversational Capabilities Carry Over from Text to Speech? A Parallel Multilingual Benchmark Nov 3 Prism: Bidirectional Self-Teaching for Unified Multimodal Models Nov 4 Diagnosis by Composition: Detecting and Localizing Unseen Diseases by Composing Learned Radiological Findings Nov 3 See all 12 papers →
3 3
Using Experience Twice: Dynamic Process Rubrics for Privileged Token-Level Credit Assignment Nov 4 EvoOPD: Evolving Privileged Information Strategies for Black-Box On-Policy Distillation Nov 4 Learning When to Think Aloud in Latent Reasoning Nov 4 See all 12 papers →
4 2
TTB: Test-time Baking for Efficient Rendering of Decoder-only View Synthesis Models Nov 12 BirdDreams: Joint Perspective and BEV Video Generation for a Plausible, Reactive Driving World Model Nov 10 CPU-ARC: Agentic Reasoning Caching for on-CPU Reasoning Reuse Nov 5 See all 11 papers →
2 2
GTAGym: Real AAA Game Tasks Environment for Evaluation and Reinforcement Learning Nov 9 CANDO: Conservative Action-Noise Directional Optimization for Residual Reinforcement Learning Nov 3 DecoupAttn: Decoupled Sparse Attention for Training-Free Acceleration of Video Diffusion Nov 4 See all 9 papers →
4
MMDM: Measuring Massive Multitask Decision Making Nov 10 LibriSpeech-Real-QA: A Benchmark for Streaming Question Answering Nov 4 CUA-Master: Scaling Computer-use Agents through Open-World Recursive Improvements Nov 2 See all 8 papers →
6
Sage-Taiyi: A Metacognitive Architecture for Scientific Discovery Nov 9 UPSHIFT: User Preference Steering from Human-AI Interaction Feedback Traces Nov 2 How Much Can Tool Calls Reveal About You? Privacy Leakage from Tool-Call Traces Oct 30 See all 8 papers →
3
Reframe: Observation-Aligned Multi-Teacher On-Policy Distillation for Agentic Visual Reasoning Nov 9 ConvPE: Convolutional Position Embedding Improves Transformers Nov 5 Understanding the Out-of-Distribution Generalization of Chain-of-Thought Reasoning in LLMs Nov 4 See all 8 papers →
4
Blind Variation, Selective Retention: Improving Creative Idea Generation in AI Scientists Nov 9 Benchmarks as Software: Terminal-Bench and the Case for Continuous Benchmarks Nov 5 Agnostic Learning by Imitating Nov 3 See all 8 papers →
4 2
TandemBench: Benchmarking Decision Models for Multi-Agent Collaboration Nov 4 HARP: Training-Free Dual-Profile Agentic Communication for LLM-Based Recommendation Nov 3 As Expected? Efficient LLM Planning via Expectation-Observation Consistency Verification Nov 2 See all 8 papers →
3 2
Evolving Infra: Agent-Adaptive LLM Serving at Scale Nov 8 AlgoPilot: Cross-Paradigm Reasoning in Language Models via Strategy Selection and Guidance Nov 2 End-to-End Guarantees for Masked Diffusion Models under Conditional Mixing Oct 29 See all 7 papers →
4
Where Does Alignment Emerge and What Does It Mean? A Closer Look at the Platonic Representation Hypothesis Nov 9 A Bayesian Framework for Safe Optimal Control of Unknown Systems from Input-Output Data Nov 2 Certifying Graph Neural Networks Against Label and Structure Poisoning Nov 2 See all 7 papers →
3
EmoHarness: Boosting Multimodal Emotion Understanding with Meta-Harness Evolving Nov 8 OpenFrontiers: A Collection of Open Research Problems and a Benchmark for Scientific Rediscovery Oct 26 Autonomous agents for electricity-system planning Nov 4 See all 7 papers →
3 3
Do Multimodal Models Decide Consistently on Equivalent Optical Spectra? Oct 29 Humanized but Still True? Auditing Facts and Detection in AI-Text Humanizers Oct 29 Mechanistic Interpretability Needs a Logic of Inference Nov 10 See all 7 papers →
2
The Narrative Gap: Can LLMs Help Us Navigate Diverse Narratives Across Languages? Nov 8 Subliminal Learning in Vision-Language Models Nov 3 Multimodal Hierarchical Mixture-of-Experts for 3D Medical Vision-Language Modeling Nov 5 See all 7 papers →
4
Horizon-Scalable Q-Learning Nov 6 MOMASPLAT: Dynamic Novel-View Demonstration Augmentation for Mobile Manipulation Nov 5 TSFM Meets LLM: Context as Covariates Nov 3 See all 6 papers →
2
LegalEvolver: Agentic Legal Judgment Prediction via Rubric-Guided Self-Evolution Nov 4 ToolSpace: Scaling Tool-Centric Environment Synthesis for Long-Horizon Agents Nov 3 CoworkOS:Scaling Agent Coworkers for Real-world Automation Nov 2 See all 6 papers →
2
SphereFlow: Missing Modality Imputation via Geometric Transport on Hypersphere Nov 3 Self-Privileged Fine-Tuning Nov 3 Lab2Sim: Turning Real-World Experiment Videos into Interactive Virtual Experiments Nov 2 See all 6 papers →
2
TAQ-MOTR: Tracking-Aware Detection Query Formation for End-to-End Multiple Object Tracking Nov 3 VagueBench: Benchmarking the Robustness of Embodied Agents on Ambient Context Illusions Nov 2 BLPO: Beyond-Local Policy Optimization for Long-Horizon LLM Agents Nov 2 See all 6 papers →
2
Beyond Token Representations: Explicit Visual Object Grounding for Video Reasoning Segmentation Nov 3 DSRS: Teaching MLLMs to Perceive, Reason, and Segment in Complex Driving Scenes Nov 4 TactiNavi: Serving and Revising an LLM Game Coach with Explicit Strategy Conditions Nov 3 See all 6 papers →
2 2
Neural Image Compression with Internal-External Prior Fusion and Alignment Nov 5 Modulating Merging Strengths via Joint Loss Estimation for LoRA-based Continual Learning Nov 3 Behavioral Affinity Transduction for Zero-Shot Vision-Language Classification Nov 2 See all 6 papers →
3
Zero-Shot Coordination among LLM Agents Nov 4 Replicability, Reproducibility, and Robustness in Political and Social Science Research with Large Language Models Nov 4 From Autonomous Agents to Cognitive Symbionts: Toward AI-Augmented Human Intelligence Nov 3 See all 5 papers →
3
VABAR: A Variational Automation Benchmark for Agentic Robotics Nov 4 SpecPilot: Autonomous Algorithm Discovery and Systems Optimization for Speculative Decoding Nov 2 GeoGuesser Bench: Benchmarking Vision-Language Agents on Interactive Geolocation Nov 2 See all 5 papers →
3
ReproBridge: Building Reproducibility into ML Research Artifacts Nov 5 Muir: Linear Attention with Sensitivity-Allocated Gating and Matched-Filter Readout Nov 5 A prospective randomized study of patient-centered AI for clinical visit preparation Oct 30 See all 5 papers →
2
OneTrans-GSR: A Generative Slate Ranking Paradigm Unifying Reranking and Mix-Ranking with One Autoregressive Transformer Nov 2 Hierarchical Residuals: A Minimalist Decoupling of Residual Width from Compute Width Oct 30 SAE Interprets MoE: Sparse AutoEncoders Reveal That MoE Experts Exhibit Human-Interpretable Fine-Grained Specialization Nov 5 See all 5 papers →
3
Unbundling Multimodal Vision Encoding Nov 12 Large Language Models as Digital Twins: a Distribution-Aware Questionnaire-Based Evaluation Nov 12 e-means: outperforming k-means (in one-tenth the epochs) Nov 5 See all 5 papers →
3
Computational Explanations of Semantic Universals Nov 11 Cultural Adaptation within Repeated Social Interactions Nov 5 Frozen in Time: How a Physics Foundation Model Forgets Under Sim-to-Real Adaptation Oct 29 See all 5 papers →
2
Axis-LoRA: Probing and Adapting Embedding Models for Personal-Memory Retrieval Nov 5 HeLM: Hierarchical Explicit Language Memory for Non-Markovian Manipulation Nov 2 LoopVQ: Sub 1-bit KV Cache Quantization for Looped Transformers Nov 3 See all 5 papers →
3 2
Beyond Instruction Override: Benchmarking Indirect Prompt Injection with Task-Tampering Attacks Nov 5 $D^2$-OPD: Separating Direction and Distance in Extrapolative On-Policy Distillation Nov 4 Chronos-2: A foundation model for multivariate time series forecasting Oct 30 See all 5 papers →
2
Evidence-Guided Recovery for AI Agents with Ambiguous Tool Outcomes and Partial Execution Oct 29 A Novel Conditional Adversarial Diffusion Model for High-Fidelity OCT-to-OCT Image Translation and Precise Anti-VEGF Therapy Response Prediction in Diabetic Macular Edema Nov 2 Axion 1.0: Open Agent Foundation Models, Simplified Nov 2 See all 5 papers →
Consensus Capture in Reference-Based UAV Video Stabilization: A Benchmark on Dynamic Urban Scenes Nov 12 Mixed Signals: Weight-Space Programming for EEG and ECG Nov 10 Library of Layers (LoL): Adaptively Ordering Transformer Layers at Runtime Nov 2 See all 5 papers →
2
FinForesight: A Diagnostic Backtesting Benchmark for Deep Research Systems in Financial Forecasting Oct 31 Why Tabular Foundation Models Excel on Relational Data They Have Never Seen Nov 2 A Novel Federated Learning Framework for Defending Against Gradient Inversion Attacks Nov 2 See all 5 papers →
CMDiff: Left Atrial Scar Segmentation from 3D LGE MRI Using Conditional Mask Diffusion Model: A Feasibility Study Nov 5 Dynamic Optimistic Constrained OCO with Memory via Delay Equivalence Nov 5 TouchéWorld tech report : Towards Online Unified Camera--Hand Exploration in Generative Worlds Nov 4 See all 5 papers →
2
Self-Supervised Learning of Universal Latent Spaces for Operator Learning Nov 3 Multi-Objective Generative Optimization via Expected Hypervolume Fine-Tuning Nov 3 ART of PIV: Agentic Real-Time Particle Image Velocimetry for Active Flow Control Oct 30 See all 5 papers →
2
Where and Why is Grounded Reasoning Useful? Nov 5 XStack: A Benchmark for ML Repo Migration Nov 5 Procedural Adversarial Learning Nov 4 See all 5 papers →
2
Meta$^2$: Precomputing Reusable Knowledge for Online Harness Evolution in Long-Horizon Agents Nov 3 MotorSense: A Video-EMG Dataset of Motoric Representations for Action Understanding Oct 30 Grounding Multimodal Reasoning with Evidence-Ablated Negatives Oct 29 See all 5 papers →
Scaling Neural Motor Decoding via Decoupled Behavioral Pretraining Nov 5 Statistical Foundations of Reinforcement Learning: A Non-Asymptotic Perspective Oct 30 PathCowork: Learning from real-world pathology practice to build AI copilots Oct 29 See all 5 papers →
2
PhysLoop: Harnessing LLMs' Physics Awareness for Self-Improving Video Generation Models Nov 12 Learning the Task or Learning the Verifier? Rethinking Criteria Exposure in Embodied Self-Improvement Nov 4 PyRUA-DataFarm: LLM Agent as a Cost-Efficient Teleoperator for Real-Ready Robot Data Nov 3 See all 4 papers →
2
G-STAR: Group-Scaled Token Capacity for Deeply Compressed Autoregressive Generation Nov 7 dNaViT: Discrete Codes are General-Purpose Visual Representations Nov 9 Efficient Hybrid Distillation: Synergizing Score and Adversarial Objectives for One-Step Diffusion Nov 2 See all 4 papers →
Infrathon: Benchmarking Language Agents for Real-World, Long-Horizon AI Infra Optimization Nov 8 D&A: Decoupling Description and Assessment Enables VLMs as Zero-Shot Robotic Reward Models Nov 2 Beyond Region Memory: Local Point Tracking for Vocal Cord Localization in Video Laryngoscopy Oct 28 See all 4 papers →
2
Analyzing Condensation on Patterned Surfaces via Deep Learning Oct 29 Training language models in simulation for psychiatric intake Oct 29 Factorized Representations of Concurrent Temporal Variables in Pretrained Language Models Oct 29 See all 4 papers →
2
Uncertainty-Aware Hybrid Offline Reinforcement Learning with Online Action Selection Enabled by Sparse Gaussian-Process Critics Nov 10 RM-VLM: From Natural-Language Task Descriptions to Vision-Grounded Reward Machines Nov 5 Do sEMG Foundation Models Improve Cross-Subject Generalisation? Nov 5 See all 4 papers →
2
ChanSFormer: A Channel Agnostic Vision Transformer for Multi-Channel Cell Painting Images Nov 4 COSMIO: A Benchmark for Cross-Survey Modality Imputation Nov 3 AtomTree: A Hierarchical Framework for State-Aware Embodied Instruction Following with LLMs Oct 28 See all 4 papers →
2 2
Stochastic Deep Supervision for Gallery-Consistent Early-Exit Face Recognition Nov 1 IDPrior: Decoupling Identity Generation from Facial Image Synthesis Nov 5 Hard Sample-Conditioned Decorrelated Attention for Robust Face Recognition Oct 30 See all 4 papers →
2
Length Is Cheap, Competition Is Not: Attention Predicts Context Rot in Retrieval Nov 2 TAPE: Learning General Audio Effect Representations Oct 29 Optimal Neural Estimation for High-Dimensional Nonparametric Regression under Multisource Covariate Shift Oct 29 See all 4 papers →
2
SafeStart: Mitigating the Overlooked Safety Cost of Active Expert Reduction in MoE LLM Serving Nov 4 Say the Same, Act Differently: Diagnosing and Steering Text-Action Divergence in Reasoning VLAs Nov 3 C-GRPO: Conformal Group Relative Policy Optimization Nov 3 See all 4 papers →
3
La-JEPA: Compact Robot Policies with Latent World Modeling Nov 5 Q-CamTuning: A Multimodal Large Language Model for Fine-Grained Quality Reasoning in Livestreaming Camera Tuning Nov 2 Trainable Vector Quantization for Large Language Models Oct 30 See all 4 papers →
2
PRIME: Predictive Routing of Interventions by Modeling Effects for Scientific Ideation Nov 2 Discovering Jailbreaks via Curriculum of Models Oct 28 Elucidating the Design Space of LM Data Attribution Oct 29 See all 4 papers →
Turns Matter: Advancing Streaming Video RL via Turn-Level Credit Nov 4 PDRVLA: A Vision-Language-Action Model with Physical Dynamics Representations Oct 27 Editing Images into Reusable Layers via Compositional Edit-Prior Distillation Oct 16 Show as cards →
2
LowRAM: Low-Rank Keys and Amortised Values for Composable KV Cache Compression at Test-Time Nov 4 iMED: A Multi-Endoscope Dataset for Surgical 3D Perception Nov 3 Can Large Language Model Agents Learn by Watching Tutorial Videos? Oct 31 Show as cards →
3
What Does Multi-Turn Reinforcement Learning Really Improve in LLM Agents? Nov 4 AskStream: When and What to Ask Proactively under Uncertainty in Streaming Video Understanding Oct 28 CoSTA: Compressed Speech Token Adaptation for Efficient Spoken Dialogue Models Oct 14 Show as cards →
2
Entropogram-guided Visual Realignment Decoding: Capturing the Rhythm of Multimodal Reasoning Nov 4 TRIO: Task Refinement with Individual Optimization for Retrieval-Augmented Generation Nov 1 VideoMemBench: How Well Do MLLMs Remember in Video Conversations? Nov 2 Show as cards →
2
MoviEdit: Long-form Multi-Shot Video Editing Made Easy Nov 2 EditAgent: Rethinking Agentic Image Editing Oct 29 SliderEdit++: Improved Slider Trajectories in Instruction-Based Image Editing Oct 13 Show as cards →
3
Are Dense Rewards Worth Their Tokens in GRPO? Nov 10 LEANGUARD: Lean-Verified Guardrails for Tool-Using Agents Nov 1 Cord: Confidence-Anchored Order Residual Decoding for Masked Diffusion Language Models Oct 29 Show as cards →
NightIQA: A Comprehensive Dataset and Benchmark for MLLM-Based Nighttime Image Quality Assessment Nov 3 Learned Smartphone ISP on Mobile GPUs: Mobile AI 2026 Challenge Report Nov 3 When Requirements Interact: Scaling Long-Horizon Coding via Interdependent Specifications Oct 28 Show as cards →
On-Policy Self-Distillation with Teacher Evolution Oct 27 COGS: A Diagnostic Benchmark for Attribute-Aware Object-Level 3D Gaussian Splatting Perception Oct 29 PIVOT: Progressive Intervention via Online Teacher Correction Oct 29 Show as cards →
EvoGuard: Mitigating Degradation in Online Skill Evolution Nov 4 VeriSpoof: Beyond Real or Fake with One Audio LLM Nov 2 Towards Multi-Value Alignment via Value Localization in LLMs Nov 2 Show as cards →
Learning to evolve by matching velocities Oct 30 DenseTwins: Dense Modality Decoupling for Multimodal Self-Supervision Nov 3 Reinforcement learning for control of partial differential equations Oct 29 Show as cards →
SynthFaces: Balanced Large Scale Human Dataset Oct 28 Beyond Foundation Models: PFN Priors Improve Tabular Hyperparameter Optimization Nov 3 Numerical Integration on Bounded Domains via Learned Reflected Diffusions Oct 29 Show as cards →
Energy-Tweedie: Score meets Score, Energy meets Energy Nov 6 MedGraph: Maintaining Patient State with Graph Memory for Long-Term Medical Dialogue Nov 5 DistDebug-Bench: Can LLM Agents Diagnose Bugs in Distributed Systems? Nov 2 Show as cards →
2
StrataFlux: Memory-Hierarchy-Native Low-Bit LLM Inference Nov 5 Stop Handcrafting Your Engine! GenDB-V: Towards AI-Generated and Formally Verified Database Systems Nov 2 Micro-Edits: Computational Support for Fine-Scale Edits in Film Oct 29 Show as cards →
Simple Meta-Learning for HPO and CASH Using Performance Representations Nov 5 DeepWeave: Weaving Neural and Symbolic Evidence for ML-Based Network Intrusion Detection System Oct 30 Uncertainty-aware Feedback Loop Diagnosis: integrating reinforcement learning and conformal prediction for reliable wafer defect classification Oct 29 Show as cards →
3
The Cost of Mismatch: Noise Amplification in Zeroth-Order Reinforcement Learning Nov 2 MoETok: Sparse Expert Routing for 1D Visual Tokenizers Oct 30 Cross-Encoder Anchor Refinement for Zero-Shot Anomaly Detection Oct 29 Show as cards →
3
MotoVerse: A Benchmark for Predictive Perception of Motorized Two-Wheelers in Dense Unstructured Traffic Nov 4 What do MLLMs know about 'Waldo'? Evaluating Visual Reasoning under Multi-Instance Multi-Object Challenges Oct 28 CrossWeave: Cross-Modal Scene and Instance Retrieval from Sparse 2D-3D Alignment Oct 29 Show as cards →
Spectral and Subspace Dynamics of LoRA in Supervised Fine-Tuning and Reinforcement Learning Nov 5 PolicyIK: High-Precision Inverse Kinematics for Robot Arms with Reinforcement Learning Nov 3 Framework-Conditional Open Materials Generation Oct 29 Show as cards →
Tilted Convexity and an Exact Offline-Online Separation Nov 2 Mechanistic Interpretability for End-to-End Self-Driving Oct 30 GraphNIAH: A Benchmark for Long-Context Reasoning over Real-World Graphs Oct 30 Show as cards →
AVID: A 5T fMRI Dataset for Benchmarking Auditory-induced Visual Mental Imagery Decoding Nov 2 Harvesting SWE Benchmarks from Wild Vibe Coding Sessions Nov 2 CryoAtlas: A Large Curated Dataset and Unified Benchmark for Cryo-EM Atomic Model Building Oct 30 Show as cards →
LIRA: A More Interpretable Dynamic Loss-Informed Rank Allocation for Low-Rank Adaptation Nov 3 MambaHand: Local Identity and Behavioral Sequence Learning with Mamba for Dynamic Hand Gesture Authentication Nov 3 Uncertainty-Aware Prototype Learning for Open-Set Test-Time Adaptation Nov 3 Show as cards →
Reinforcing End-to-End Autonomous Driving Safety via Negative-Aware Planning in a Unified World-Action Model Nov 5 Variance Reduction for Decentralized Stochastic Optimization with Multiple Local Updates Oct 30 Beyond Trial-and-Error: A Geospatial-Guided Active Reasoning Framework for Robust Aerial Vision-and-Language Navigation Oct 30 Show as cards →
2
The Geometry of Ignorance: Detecting Suppressed Knowledge in LLMs through Activation Fragmentation Nov 3 Continual Classification Beyond the Kernel Regime: Harnessing the Sparsity Bias of L2 Regularization in Diagonal Linear Networks Nov 4 Ramanujan Challenge Results: AI-Assisted Evaluation Pipeline for Multi-Format Proofs Oct 29 Show as cards →
Concertina: Embodying Manipulation and Cognition in One Diffusion Vision-Language Model Nov 5 TraceRouter++: Causal Semantic Routing Realignment via Optimal Transport Nov 3 MetaRefine: Score Refinement with Multi-Level Features for Image Assessment Oct 29 Show as cards →
ReTailor: A Residual Feature Tailoring Framework for Real-Time Cross-Sensor Pansharpening Adaptation Nov 4 TOP: Transmission-Oriented Remote Sensing Pansharpening Nov 4 UniRA: Unified Representation Alignment and Auto-Encoding for Efficient Diffusion Generation Oct 29 Show as cards →
2
A Systematic Benchmark for Evaluating Multimodal Personalized Reasoning of Vision-Language Models Nov 4 Attention Maps Know When to Think: Training-Free Difficulty-Aware Chain-of-Thought for Reasoning Segmentation Oct 30 GRIT: Gradient Masking for Visually Misgrounded Tokens in Text-Rich Reasoning Oct 30 Show as cards →
Semantic Residual Vector Quantization for Sign Language Generation Nov 4 Classical training of conditional instantaneous quantum polynomial-time Born machines Nov 3 Hierarchical Step Decomposition for Training-free Online Video Step Grounding Oct 29 Show as cards →
2
FedIA: Instance-Aware Cross-Modal Representations for Federated Prompt Learning Nov 4 Dexterous Robotic Hands in the Foundation-Model Era: A Full-Stack Survey of Hardware, Data, Cross-Embodiment Transfer, Learning, and Evaluation Nov 4 On the Fundamental Limits of Prefill-Based Decoding Length Prediction Oct 29 Show as cards →
Decode Before You Hear: Speculative Listening for Chunk-Interleaved Full-Duplex Speech Language Models Nov 3 R^2Orch: Recursive Self-Improvement for Agent Orchestration via Self-Play within a Skill-Internalization Loop Oct 21 Show as cards →
One Table, Many Queries: Benchmarking Generalist Tabular Models Across Generation, Imputation, and Prediction Nov 7 Decoupled Predictive Decision Making: A Shared Conditional Predictor for Agents Oct 31 Show as cards →
From Pixels to Actions - Towards Native Vision-Language-Action Policies Nov 4 Probing Spatial State Representations in Visual Foundation Models Oct 29 Show as cards →
P^2-MOPD: Accelerating Multi-Teacher On-Policy Distillation via Parameter Priors Nov 2 StepX-OPD: Rethinking Multi-Teacher On-Policy Distillation in Diffusion Models Nov 2 Show as cards →
PCBRouteAgent: How Close Are LLM Agents to Becoming PCB Routing Engineers? Nov 5 DeFT-RAG: Decomposing Multi-Hop Questions into Self-Contained Sub-Questions with Reusable Answers Oct 29 Show as cards →
2
WorkFactory: Turning Professional Intents into Executable Work for Scalable Agent Training Oct 26 RealCLI: Toward a Unified Evaluation of Human-Agent Collaboration for CLI Agents Oct 14 Show as cards →
GameVerse: A Minute-Scale Gameplay Dataset for Long-Horizon Interactive World Modeling Oct 30 StreamDuo: A Live Commentator and a Research Agent for Unseen Games Oct 30 Show as cards →
LongBanana: An Expert-Verified Benchmark for Long-Context Multi-Reference Image Synthesis Nov 4 Utility-Aware Generative Recommendation: Utility-Enriched Semantic Codes and Utility-Guided Decoding Nov 2 Show as cards →
2
On the Design of Hyper-Connections: Simplification, Stability, and Scalability Nov 3 DepthGraft: Structural Regularization through Hierarchical Cross-Layer KV Reconstruction Nov 1 Show as cards →
Ropedia Xperience 2: A Gold Standard for Scaling Physical AI Environments and Behaviors Nov 12 Ropedia W0: Scaling Loco-Manipulation World Models across Embodiments with Human Experience Oct 18 Show as cards →
FINCOSMOS: An Open-World Evaluation Paradigm for Agents in Finance Nov 4 LLMs Don't Know What They Know: Benchmarking Temporal Self-Knowledge for Financial Backtesting Nov 3 Show as cards →
Factored One-sided Adam-Moment for Practical and Scalable SOAP Nov 12 No Channels Left Behind: Understanding Diffusion Acceleration through Residual Gates Oct 29 Show as cards →
On the Opportunities and Challenges of Prefill-to-Autoregressive Cross-Model Transfer Nov 4 Macrocanonical Generator Networks: Data-Efficient Neural Surrogates for Amortized Physics Simulation Nov 3 Show as cards →
MIMIC-Note-Extract: A Large-Scale Structured Dataset Extracted from MIMIC-IV-Note Discharge Summaries Nov 3 AnchorComplete: Recovering Complete Scene Meshes from Partial Point Clouds Nov 2 Show as cards →
LiveFoley: Dynamic Real-Time Video-to-Audio Generation for Immersive Interactive Worlds Nov 4 Reasoning-Aware Cross-Modal Association Unlearning in Multimodal Large Reasoning Models Nov 4 Show as cards →
FAME-QP: A GPU-Accelerated Quadratic-Programming Solver for Real-Time Model Predictive Control Nov 10 From FAIR to AI-FAIR Metadata-First Infrastructure for AI-Enabled Science Nov 2 Show as cards →
Towards Real-Time Full-Waveform LiDAR Transformers via Intensity-Guided Token Reduction and Physics-Aware Augmentation Nov 5 STARE: Scene Text-Aware multimodal Retrieval for Everyday objects Nov 4 Show as cards →
LEASH: Stay Safe in Agentic Robotics Nov 10 Auditable Belief Updates as a Missing Safety Layer for LLM-Powered Multi-Agent Systems Oct 28 Show as cards →
2
CogBattery: Human-Referenced Evaluation of Cognitive Task Behavior and Structure in Language Models Oct 29 WMIP: A Working-Memory-Inspired Programmable Probe of Cumulative State Tracking in Large Language Models Oct 29 Show as cards →
GaussianRenderFormer: Transformer-based Rendering of 3D Gaussian Splats Nov 3 Difficulty Calibration Across Time for Membership Inference in Diffusion Models Oct 29 Show as cards →
TaoMate-FVSR:Audio-Guided Facial Video Restoration Nov 2 TaoMate-HD: Progressive-Resolution Autoregressive Audio-Video Generation Nov 1 Show as cards →
CARTBench: Rubric-Based Evaluation of Shopping Advice for Complex and Ambiguous Requests with Timelines Nov 3 DeCoRL: Decomposed Consistency Reinforcement Learning for Multi-Image Composition Oct 29 Show as cards →
2
Prompt2Echo (P2Echo): Text-Prompted Multi-View Echocardiography Segmentation with One Model Nov 10 Every Pixel Is an Option: A System One Model for Medical Ultrasound Biometry Nov 1 Show as cards →
Anomaly-ranked confirmation slows new-class learning Nov 2 rTaste: Do Research Agents Have Taste? Evaluating Early Stage Research Judgment Oct 29 Show as cards →
Knowledge Graph-based Retrieval-Augmented Generation for Schema Matching Nov 5 CoDecide: Content-Adaptive Video Decoding for High-Throughput Video Analytics Nov 4 Show as cards →
Prune Gradually, Adapt Sparsely: Efficient Pruning of Large Language Models at Extreme Sparsity Oct 30 Uncertainty-aware Coarse-to-Fine Main Pancreatic Duct Segmentation for Width Measurement in 3D MRCP Oct 29 Show as cards →
PaddleMaterials: An End-to-End Deep Learning Toolkit for Materials Science Nov 2 SCARL: Sequence Confidence-Aligned Reinforcement Learning Oct 29 Show as cards →
2
Discovering hierarchical governing equations for community-structured complex network dynamics with LLM agents Nov 2 When Safety Checks Become Privacy Risks: A Privacy-Preserving Paradigm for LLM Agent Safety Auditing Oct 30 Show as cards →
ImplicitHop: Evaluating knowledge integration across context and memory Oct 30 Explore Where It Matters: Targeted Exploration for Efficient Rover Adaptation Oct 28 Show as cards →
From Transcription to Reformulation: Defining and Benchmarking Grounded Generative Speech Recognition Oct 30 Ask on Demand: Targeted Peer Communication for Parallel Agentic Systems Oct 30 Show as cards →
Binding Paraphrased Instructions to Encountered Objects in sLLM Agents under Partial Observability Nov 5 RI-Prune: Relation and Information Aware Visual Token Pruning for Multi-Image Vision-Language Models Nov 4 Show as cards →
Feeling of Knowing in Large Language Models Nov 3 Think Globally, Generate Personally: Multi-View Thinking with Adaptive Generation for Generative Recommendation Nov 2 Show as cards →
Hybrid Particle-Voxel Dynamics for Multimodal 3D World Simulation Nov 3 Can LLM Agents Improve Imperfect Earth System Model Parameterizations? Nov 2 Show as cards →
Unlocking the Potential of Vision Foundation Models for Multi-Task Dense Prediction via Mixture of Task Adapters Nov 2 Spectral Invariant Fusion and Refinement for Domain Generalized Semantic Segmentation Oct 29 Show as cards →
LoRe-MIM: Lost-or-Replaced Masked Image Modeling for Self-Supervised Representation Learning in Whole-Body PET/CT Oct 29 A Low-Rank Space Captures Linear Alignment Between LLM and Human Neural Activity During Naturalistic Language Listening Oct 29 Show as cards →
2
RECAST: REconstruction of Chain-of-Thought via Auditable Structured Traces Oct 30 Compile Away Uncertainty: Self-Evolving Agent Skills via Programmatic Compilation Oct 29 Show as cards →
SD-LoRA: Training-Time Structural Distillation into LoRA for Few-Shot Vision-Language Adaptation Nov 4 Batch-Conditioned Semantic Anchors for Robust Transductive Adaptation of Vision--Language Models Nov 4 Show as cards →
2
Do Language Models Know What Compelling Scientific Evidence Looks Like? Oct 29 Learning to Reason from Reference Samples Alone: Reinforced Adversarial Learning for Modern LLM Post-Training Oct 28 Show as cards →
Dr. No: Feature Steering for Abstention in Vision-Language Models Nov 2 RADIOlogy: A Single-Pass Approach to Training-Free Zero-Shot Anomaly Detection Oct 29 Show as cards →
Specification-Guided Generation for Large Language Models Oct 30 Communication-Efficient Clustered Federated Learning in Non-IID Wireless Networks Oct 28 Show as cards →
BudgetSplat: Budget-Controllable Generalizable Gaussian Splatting Nov 4 On-device Detection of Wearer-induced NLOS on Chest-worn UWB Tags: Machine Learning, Link Indicators, or Both? Oct 30 Show as cards →
OcTreeMamba: Topology-Aware Mamba for 3D Medical Segmentation via Octree Sparsification Nov 5 Retrieving from Your Own Mistakes: On-Policy Training of Embedding Models for Multi-Hop Retrieval-Augmented Generation Oct 29 Show as cards →
Twists and Turns: A Graph-Based Benchmark and Framework for Long-Term Memory in Exploration Tasks Nov 4 Revisiting Over-refusal in Safety-aligned Large Language Models: A Representation and Optimization Perspective Oct 29 Show as cards →
Enhancing Medical Lesion Segmentation via Several Simple Modules Oct 30 Aligning Medical Vision Language Models at the Capability Boundary with Entropy Adaptive Rubric Grounding Oct 29 Show as cards →
Robustness Verification against Patch Attacks via Group-Lasso Semidefinite Relaxation Nov 3 Collaborative AI agents for autonomous experimental research with solid-state quantum spins Oct 29 Show as cards →
Parse Before You Execute: Efficient Spatial Reasoning with Executable Primitives Oct 30 Do Transaction Prices Reflect Visual Preference? A Diagnostic Study with Multimodal Language Models Oct 30 Show as cards →
ReVA-HPE: Relative 6DoF Head Pose Estimation with Synthetic Pose Supervision and Personalized Virtual Anchors Nov 2 Leveraging Recourse and Size Bounds for OnlineKnapsack with Removable Items Oct 29 Show as cards →
SimXAI: A Simple Drop-in Layer Increases Interaction Quality and Understanding in Conversational XAI Oct 30 Decision and System One models in rheumatology: accuracy and calibration on specialty-training examination questions and diagnostic case vignettes Oct 29 Show as cards →
2
How Far Can Lightweight LLMs Go in Intent-to-SLO Translation? Nov 5 Retrieval Supersedes Scale: Efficient Log Level Prediction via Multiplex Socio-Technical Context Nov 4 Show as cards →
Multimodal Prompt Learning with Dual-Granularity Contrastive Alignment for Preoperative Prediction of Lung Adenocarcinoma Invasiveness Using 3D CT Nov 2 Distributional Reward Calibration and Budget-Neutral Credit Assignment for Multimodal RLVR Oct 29 Show as cards →
ManimCode: Learning Visual Self-Correction for Educational Animation Nov 5 DEG: Diffusion-Enhanced GFlowNet for Solving Vehicle Routing Problems Oct 29 Show as cards →
2
Timing is Everything: Inferring Temporal Membership in Continually Updated Models Nov 4 Testimony from Timelines: Evidence-Grounded Significance Testing of Temporal Clinical Hypotheses Oct 29 Show as cards →
FlexReader: Towards Adaptive Decoding Paths for Efficient Arbitrary-Length Scene Text Recognition Oct 30 Rimuru: Unified Memory Management for Modern LLM Serving via Elastic Expert Offloading Oct 29 Show as cards →
Drone-PUR: From Visual Clue Discovery to Understanding and Reasoning in UAV Scenes Oct 29 Regional Anchor Routing for Multi-Object Motion Transfer Oct 29 Show as cards →
2
RASP: Read-All, Sparse-Plasticity Continual Learning in a Stationary-Size LoRA Nov 2 BISECT: Bilevel Spectral Decomposition for Low-Rank Continual Learning Nov 2 Show as cards →
2
Training Specialist LLMs on Your Phone: Forward-Only Optimization via Block-Spectral Coordinates Nov 3 Can Test-Time Memory Evolution Outperform Test-Time Training for Scientific Discovery? Oct 22 Show as cards →
Generative AI for urban planning: synthesizing land-use maps with satellite imagery via DualControlNet Nov 4 FedFiOT: Fisher-Weighted Optimal Transport for Model Merging in One-Shot and Few-Round Federated Learning Nov 4 Show as cards →
FOCUS: First-Order Control Using Optimal Transport Supervision for Imitation from Observations Oct 30 Gaussian Distillation of Flow Policies Oct 29 Show as cards →
Transformer-Based Trajectory Prescription for sEMG-Optimizing Robot-Mediated Rehabilitation Nov 5 Grounded but Not Immune: Confirmation Bias in Agent-as-a-judge Nov 3 Show as cards →
AI evaluators favor job applications written by certain AI models, independent of candidate quality Oct 30 Bridging Semantics and Structure: A Theoretically Grounded Framework for Link Prediction on TAGs Oct 29 Show as cards →
MonoLaDN: Language-Guided DeNoising for Monocular 3D Object Detection Nov 4 Quo Vadis, Driving Scene Reconstruction? Occlusion-Aware Gaussian Densification Nov 4 Show as cards →
NextGAN: Towards Simple and Scalable GAN Training for Image and Video Generation Nov 4 ENGINE: Endogenous Variational MultiScale Optimization for Zeroth-Order LLM Fine-Tuning Nov 2 Show as cards →
2
Deogen: Automatic Benchmark Generation for Reasoning over Policies Oct 28 Statistical Analysis of Synthetic Data with Verification: A Linear Regression Framework Oct 29 Show as cards →
SMILE: A Structured Multi-Agent Clinical Reasoning for Liver Ultrasound Understanding Nov 2 Accurate MRI-free PET Quantification and Reliability Assessment via CT-to-MRI Synthesis and Conformal Prediction Oct 29 Show as cards →
Investigating the effects of the patch size in Time Series Foundation Models Nov 2 An ODE-based Sampler for Discrete Diffusion Models Oct 29 Show as cards →
A-RSI: Adaptive Task Refresh for Zero-Data Multimodal Self-Improvement Oct 27 Show as cards →
FrameForge: Harnessing Priors of Video Foundation Models for Unified Image Generation Oct 26 Show as cards →
Wave Forcing: Towards Speed-of-Light Streaming Video Generation Oct 30 Show as cards →
SLA: Scaling Spatial-Language-Action Model via Continual Pre-training Nov 5 Show as cards →
Learning Heterogeneous Tactile Representation for General Dexterous Manipulation Nov 9 Show as cards →
Video Generation Meets Agent Harness: Agentic Video Generation, Agentic World Modeling and Recursive Self-Improvement Oct 29 Show as cards →
World In-Context Learning for Agentic Robot Manipulation Nov 9 Show as cards →
Proving and Improving the Platonic Representation Hypothesis with JEPAs Oct 29 Show as cards →
WorldFoundry: Towards Unified Infrastructure for World Intelligence Nov 7 Show as cards →
Toward the Era of Agentic Embodied Intelligence Nov 5 Show as cards →
FrontierPhysics: Evaluating Agents for End-to-End Physics Research Nov 4 Show as cards →
TailSteer: Trajectory-Tail Steering for Drift-Resistant Multi-turn Image Editing Nov 4 Show as cards →
Apriel Voice 27B Preview: An Open Model for Speech, Reasoning, and Tool Use Oct 28 Show as cards →
Halley: A Predictive Control Plane for Optical AI Data Center Networks Nov 3 Show as cards →
NorthCUA Technical Report: Turbocharging Computer-Use Agents through Experience at Scale Oct 31 Show as cards →
MACaQ: Fast, Model Agnostic Calibrated Quantization for Low-Precision Weights and Activations Nov 6 Show as cards →
Open Vision Banana: A Fully Open Recipe for Generative Visual Perception Nov 11 Show as cards →
PhotoGuider: Composition-Aware Cropping and 360$^{\circ}$ View Framing with Explainable Photographic Assessments Nov 2 Show as cards →
Embodied First Exam Nov 9 Show as cards →
Confucius4-R2T2: A Stable-Prefix Streaming ASR Model for Real Real-Time Transcription Nov 4 Show as cards →
Follow the Gradient: Tracing Safety Degradation Back to Training Data Oct 26 Show as cards →
Order-Only On-Policy Distillation Oct 31 Show as cards →
IdeaTaste: Do LLMs Share the Research Taste of Human Researchers? Nov 2 Show as cards →
EvoTeam: Multi-Agent Collaboration via Evolving Teams Oct 29 Show as cards →
HiFOR: Hierarchical Foresight with Action-Guided World Grounding for Vision-Language-Action Model Oct 28 Show as cards →
DexForesight: Grounding Dexterous Policies with Implicit Spatial Foresight Nov 9 Show as cards →
From Fragmentation to Fusion: A Survey and Roadmap for Omnimodal Embeddings Oct 29 Show as cards →
Fast and Exact Relative-Position Attention via Structure-Aware Kernels Oct 30 Show as cards →
Towards Foundation Decision Models: Drex Nov 5 Show as cards →
ReLift: Dense 3D Tracking as Lifted Trajectory Repair Oct 30 Show as cards →
Read Less, Solve More: Token-Efficient Sparse Reading of External Content for AI Agents Nov 6 Show as cards →
The Surprising Effectiveness of Deleting Weights in LLM Post-Training Nov 6 Show as cards →
Longtail-SWE: High-Quality SWE Tasks for Underrepresented Languages Nov 6 Show as cards →
WaveGen: Truly End-to-End Waveform Generation via Internal Spectral Trajectory Learning Nov 9 Show as cards →
TAC-CoT: Tool-Empowered Implicit Chain-of-Thought via Interleaving Explicit Tokens Nov 1 Show as cards →
FLAMIA: FLAsh MIcroscaling Attention for Fast and Causally Safe Training on Blackwell Nov 2 Show as cards →
Video-Coder: Reinforcing Agentic Coding for Video Generation Nov 5 Show as cards →
InfraRSI: Harnessing Recursive Self-Improvement for Training Infrastructure Nov 8 Show as cards →
MUON-RT Reusing the Teacher's Trajectory for Momentum-Free Muon for LLM Self-Distillation Oct 29 Show as cards →
Interactive Visual Gym: Evaluating Visual Interaction Models with Simulated Users in Interactive Worlds Nov 4 Show as cards →
Glance: The Generator Is Its Own Reranker Oct 29 Show as cards →
MotionGraphicsBench: Evaluating Motion Graphics Generation with Programmatic Verification Nov 6 Show as cards →
Terminal-style Mathematical Modeling Bench: The First Agentic and Verifiable Benchmark for Mathematical Modeling Nov 5 Show as cards →
SwarmEvolve: Latent Agent Swarms for Evolutionary Discovery and Optimization Nov 4 Show as cards →
The SIMPLE Law for Energy Cost of LLM Inference Nov 1 Show as cards →
From Tool State to Scientific Action: Auditing Decision Provenance in Biomedical Research Agents Oct 31 Show as cards →
TauIndianBankBench: Procedure-Aware, Action-Oriented Evaluation of Tool-Using Conversational Agents Sep 29 Show as cards →
Online Dense Reinforcement Learning with Planning-Grounding Agent for UI Navigation on Live IOS Apps Oct 28 Show as cards →
GLOW-FM: Efficient Generative Low-Light Image Enhancement with One-Step Latent Flow Matching Oct 22 Show as cards →
How I Aligned Your Model: Scaling Up Multilingual Safety Training with Templates Oct 28 Show as cards →
On the Origin and Evolution of Training-Inference Mismatch in LLM Reinforcement Learning Oct 28 Show as cards →
Adversarial Speculative Reasoning Improves Long Horizon Agents Nov 3 Show as cards →
Evaluating DeepSeek V4.1 Flash-1017 for loss of control and harmful manipulation risks Oct 25 Show as cards →
SOMA: A Benchmark for Fine-Grained Egocentric Behavior and Body-Motion Understanding Oct 25 Show as cards →
NitroFusion2: Bringing Adversarial Loss to the Text Stream of Multimodal Diffusion Transformers Nov 3 Show as cards →
PhysOPSD: Code as Privilege for Physically Plausible Video Generation Nov 8 Show as cards →
Test-Time Scaling for Diffusion Language Models with Frequency-Aware Remasking Nov 6 Show as cards →
BYOD: Build Your Own DLM - Efficient Autoregressive-to-Diffusion Language Model Conversion Oct 29 Show as cards →
Micius-Flash: Lightweight Agentic Intelligence for Engineering Nov 3 Show as cards →
HALO: Human-Grounded Granular Evaluation of Proactive Agents Oct 28 Show as cards →
OpenFlyV2: An onboard vision-language-action model for aerial perception and navigation Oct 28 Show as cards →
Reducing Representational Interference in Retrieval Embeddings with Trainable Prefix Tokens Nov 4 Show as cards →
Matched Capabilities, Different Behaviors: A Controlled Study of MCP and CLI Interfaces for Language Agents Oct 24 Show as cards →
Shortcuts and Boundaries: Verifiable RL Misalignment and Contextual Safety Learning Nov 9 Show as cards →
IWIBench: Evaluating Gradient-Free Model Driven Intra-weight Injection Nov 4 Show as cards →
Supervising the Visible State: Separating Representation from View Selection in Streaming Video Oct 25 Show as cards →
Coding or Cheating? An Investigation of Frontier Coding LLMs Nov 6 Show as cards →
Market-Conditioned JEPA: Learning from Unpredictable Market Shocks Nov 10 Show as cards →
LCM-Promo: An LLM-Based Uplift Model for Promotion Allocation Oct 27 Show as cards →
Signed but Steerable: Measuring and Closing the Text-Vector Integrity Gap in Offline Retrieval-Augmented Generation Nov 4 Show as cards →
SIMIT: Self-Improving Vision-Language Models via Imagination at Test-Time Oct 10 Show as cards →
Multi-layer Indexer: Overlapping Selection and Attention in DeepSeek Sparse Attention Nov 1 Show as cards →
EarthRecord: From Pixels to Land Change with Multimodal Agents over Four Decades of Satellite Imagery Nov 5 Show as cards →
CausGround: Causal Interaction Grounding for Adaptive Embodied Planning Oct 20 Show as cards →
LOB-Impact Benchmark: Emergent Market Impact in Generative Limit Order Book Models Oct 18 Show as cards →
Monitor Accuracy Isn't the Answer: A Decision-Value Framework for Evaluating AI Agent Restart Monitors Oct 26 Show as cards →
Think Twice: The Metis-1.6 Technical Report Oct 26 Show as cards →
DeepStress: Stress-Testing Deep Search Agents Nov 11 Show as cards →
PREEN: Exemplar-Based Color Style Transfer with Smartphone Editor Presets Oct 26 Show as cards →
Ask, Don't Equip: Question-Driven Coding Agents for Deep Kernel Optimization Nov 1 Show as cards →
TurtLES: A Large-Scale Benchmark for Turbulent 3D Neural PDE Surrogates Nov 5 Show as cards →
DAMI: Dual-Axis Memory Initialization for Enhanced Long-Context Retrieval in Gated Linear Attention Oct 29 Show as cards →
How Many Exposures Does a World Model Need? Learning Unseen Game Mechanics at Test Time Nov 9 Show as cards →
A Tutorial on Generative Models for Music Audio Oct 27 Show as cards →
Module-Aware Optimization for Graph Neural Networks Nov 4 Show as cards →
CausalWAM: Learning the Causes of Actions in World Action Models Oct 29 Show as cards →
Identically Trained Language Models Break on Different Jailbreaks Oct 24 Show as cards →
NPCBench: A Clinical Apprenticeship Benchmark for Multimodal Care-Pathway Reasoning in Nasopharyngeal Carcinoma Nov 5 Show as cards →
Weaken to Strengthen: Weakening-Induced On-Policy Self-Distillation for Large Reasoning Models Oct 27 Show as cards →
JoVox: Joint Hierarchical Flow Matching for Lightweight Voxel Generation Nov 7 Show as cards →
Sketchpad: certified exact arithmetic with a small vision-language model Nov 3 Show as cards →
Koopman Generative Operators for Efficient Probabilistic Time-Series Forecasting Nov 3 Show as cards →
Information Games: Strategic Crowding and Firm Repositioning in Language-Model Space Nov 4 Show as cards →
RidgeFill: Training-Free Late-Layer Cache Fill for Faster Prefill Nov 5 Show as cards →
After One-Click Video: The Inflow of Service-Type Content, the Failure of the Recommendation Pool Mechanism, and the BoLe System Oct 23 Show as cards →
Cross-Prompt Reuse of Entity-Replacement Responses Oct 29 Show as cards →
HERIT: Enabling Global Access to Hanja-to-English Historical Translation by Mitigating Temporal Bias Nov 2 Show as cards →
Creative Priming: Decoupling Process from Product to Escape the Creative Paradox Nov 8 Show as cards →
ODE Policy: Robot Learning via Action Dynamics, Not Actions Nov 1 Show as cards →
InstantHMR : Real-Time Human Mesh Recovery on Your Phone Nov 6 Show as cards →
Static Recovery Is Not Dynamic Stability: Dynamics-Aware Benchmarking of Protein Motif Scaffolding Nov 5 Show as cards →
Back to Pixels: Lifting Latent Video Diffusion into Pixel Space Nov 12 Show as cards →
Spatial Harness: Grounding Spatial Reasoning in Executable World States with Physics Engines Nov 7 Show as cards →
Muon Makes the First Mixture-of-Experts Layer Harder to Balance Oct 26 Show as cards →
BEND 2.0: Benchmarking the Capabilities Needed to Design DNA Nov 2 Show as cards →
Lipschitz-Controlled Flow Matching for Robust Image Restoration Nov 10 Show as cards →
FDSML: Formula-Driven Supervised Metric Learning with Parameter-Aware Triplet Loss Oct 28 Show as cards →
Structured Confidence Perturbation via Fisher Geometry for Adversarial Training Nov 10 Show as cards →
TSFLab: A Self-Improving Agent-Agnostic Workbench for Time Series Forecasting Research Oct 28 Show as cards →
QFabric: Guarded Cross-Domain Task Recovery and Its Limits on a Linux-RTOS Board Oct 31 Show as cards →
SketchDirector: Complex Scene Sketching via Agentic Layout Reasoning and Detail Refinement Oct 30 Show as cards →
A frontier machine intelligence for human neuroimaging Nov 11 Show as cards →
Modality-Aware Expert Pruning for MoE-Based Multimodal Large Language Models Nov 3 Show as cards →
GigaSpeech 3: Scaling Multi-Dialect Arabic Speech Recognition with Weakly Labeled Data Nov 2 Show as cards →
Going Deeper With Memories Nov 3 Show as cards →
Click3R: Interactive Stereo 3D Reconstruction with Sparse Correspondence Clicks Nov 8 Show as cards →
Enhanced MRI brain tumor detection using deep learning in conjunction with explainable AI SHAP based diverse and multi feature analysis Nov 5 Show as cards →
Greenscapes: Optimized Vegetation Configurations in Cities Oct 29 Show as cards →
Scheduling Data to Compute: Hierarchical Data Pipelining for LLM Training on AMD GPUs Nov 3 Show as cards →
Red-Teaming Large Language Models in Low-Resource African Languages: A Case Study of Yoruba and Nigerian Pidgin Oct 29 Show as cards →
Text-Only Domain Adaptation for Low-Resource Medical ASR: Shallow Fusion and Density Ratio Rescoring for Hausa Nov 3 Show as cards →
What Standard Evaluations Hide About Detectors of Hijacked LLM Agents: Rare Attacks, Unseen Tools and Benchmark Transfer Oct 30 Show as cards →
Beyond fabrication: Misattributed numbers in papers written by AI research agents Oct 28 Show as cards →
They Know Where It Is, But Not What It Says: A Bilingual Hallucination Benchmark of Hadith Recall in Open LLMs Nov 2 Show as cards →
Coupled or Independent? Fault Coupling in Agentic Medical Vision Systems Oct 29 Show as cards →
Adaptive search with path-constrained mobile sensors using multi-arm bandits Oct 29 Show as cards →
Feature Puzzles: Single-Image Supervision for Multi-View 3D-Aware Segmentation Nov 4 Show as cards →
Matched but Not Better: An Equivalence-Tested Benchmark of Quantum Machine Learning on Six Clinical Datasets and the QML-Health-READY Reporting Framework Nov 3 Show as cards →
When to Assist and What to Suggest: Joint Gating and Memory-Grounded Hint Generation in One Compact Decoder Oct 29 Show as cards →
Propose-Filter-Release: Scaling Noise to Typical Sensitivity via Private Filtering Oct 29 Show as cards →
Agentic LLM reasoning in pediatric diabetes outcome prediction from multimodal medical records Oct 29 Show as cards →
Differential rank preservation manifold learning Oct 30 Show as cards →
TradeWar: A Benchmark for Execution-Grounded Trade Negotiation with Adaptive LLM Agents Oct 30 Show as cards →
Subspace Learning with Outlier Exposure for Out-of-Distribution Detection Nov 5 Show as cards →
BiHashFormer: Hash-Driven Dual-Branch Transformer for Efficient Object Detection in HRW Shots Oct 29 Show as cards →
RetryRoute: Retry-Aware Model Routing for Agentic Image Editing Services Oct 30 Show as cards →
LooM: Loop-Invariant Memory for Causal Encoder-Decoder Language Models Nov 4 Show as cards →
DR Pixel: Page-Native Deep Research with Vision-Language Models Nov 2 Show as cards →
DYNAS: A Dynamic Network Penetration Testing Framework Using Deep Hierarchical Reinforcement Learning Oct 29 Show as cards →
MoLRSI: A Recursive Self-Improving AI agent for Molecular Discovery Oct 29 Show as cards →
EEFA: A Framework for the Ethical Evaluation of AI Agents Nov 2 Show as cards →
ReSI-Math: Exploring Recoverable Capability Frontiers for Efficient Reasoning Improvement Nov 3 Show as cards →
SAGE (Subjectivity-Aware Generation Estimator): A Linguistic Framework for AI-Generated Review Detection * Nov 2 Show as cards →
Learned Terminal Costs for Short-Horizon Model Predictive Control of Autonomous Trucks in Interactive Highway Traffic Oct 29 Show as cards →
Variable names provide priors: semantic grounding enables data-efficient numerical prediction by large language models Nov 2 Show as cards →
Towards interpreting any residual stream direction by scaling activation inversion Nov 5 Show as cards →
Beyond Risk Cues: A Mechanism-Level Benchmark and Verifiable Debate for Scam Video Detection on the Web Nov 4 Show as cards →
Efficient Detailed Scheduling of Multiproduct Pipelines using Action-Decoupled Deep Reinforcement Learning Nov 2 Show as cards →
EffComp: Efficient Prompt Compression via Hybrid Reinforcement & Supervised Learning Nov 2 Show as cards →
FedCSGA: Evolutionary Client Selection with Joint Statistical and System Heterogeneity in Federated Learning Nov 3 Show as cards →
GeoFlip: Benchmarking Geometry-Sensitive Physics in Video Generation Oct 30 Show as cards →
Mitigating Spurious Invariance in Contrastive Learning: A Probabilistic Self-Supervised Learning Framework for Medical Image Analysis Nov 3 Show as cards →
Luggage re-identification: A study of strategies towards a real-world application Oct 29 Show as cards →
Directional Statistics in Signal Processing: A Geometry Driven Overview of Models, Learning, and Applications Nov 3 Show as cards →
Kolmogorov-Arnold Networks vs. Multi-Layer Perceptrons: A Rigorous Statistical Benchmark on Clinical Tabular Data Nov 2 Show as cards →
DEQ-Stereo: Deep Euilibrium Video Stereo Matching via Adaptive Convergence Oct 29 Show as cards →
Self-training for cross-centre coronary vessel segmentation in X-ray angiography using pre-contrast frame subtraction Oct 29 Show as cards →
AI in the EGI e-infrastructure -- Past experiences and future strategies Oct 29 Show as cards →
Can Personal Requirements Become Supervision for Planning? Oct 29 Show as cards →
Adaptive Low-Light Enhancement for Road Anomaly Detection: A Multi-Architecture Benchmark and Edge Deployment Study Nov 5 Show as cards →
Communication-Efficient Private Federated Reinforcement Learning with Post-Quantum Authentication for Vehicular Networks Oct 29 Show as cards →
Trustworthy Distributed Machine Learning in Cloud-Edge-IoT Systems: A Heterogeneity-Aware Survey of Security, Privacy, and Robustness Oct 28 Show as cards →
NEOPIC: A Neural Operator Framework for Particle-based Kinetic Plasma Simulations Oct 29 Show as cards →
Only Accepted Tokens Count: An Energy Accounting of Speculative Decoding Under Latency Targets Oct 29 Show as cards →
Preserving Utility in Continual LLM Unlearning via Orthogonal Projections Oct 29 Show as cards →
TalkFlow: Structured Latent Flow Matching for Speech Driven Holistic Motion Generation Oct 29 Show as cards →
Where is Physical RSI capability from? An Observational Scaling Law of LLM-as-policy Oct 18 Show as cards →
Comparing Human Role-Players and LLM-Simulated Clients in Online Counselling Training: An Analysis of Counselling Patterns Oct 29 Show as cards →
SO(3)-Equivariant Learning on CAD Boundary Representations Nov 3 Show as cards →
USI-Brain: Enhancing Underwater Spatial Intelligence via Spatial Data-Driven Vision-Language Modeling Nov 4 Show as cards →
world2vec: Mechanistic world models through latent dynamics learning Oct 29 Show as cards →
Alleviating Limited Effectiveness and Multi-Class Collapse in Deep Graph-level Clustering Nov 4 Show as cards →
GTAFL: Addressing Test-Agnostic Long-Tailed Federated Learning in Medical Image Nov 5 Show as cards →
TSB-SEG: A Systematic Time-Series Segmentation Benchmark Nov 2 Show as cards →
RLGPA: A Reinforcement Learning-Guided Granularity Planning Attack for Decision-Based Sparse Adversarial Examples Nov 5 Show as cards →
Modular Bayesian Foundation Models: Bayesian time series encoders for OOD detection, routing and forecasting Oct 28 Show as cards →
Reading Why: Born-Measured Attention with Exact Word Evidence on Light and Qubits Nov 3 Show as cards →
Dynamic Powergrid Optimization with FPGA-based Neuromorphic Higher-order Ising Machines Oct 29 Show as cards →
Optimal Path Planning with Localization constraints Oct 29 Show as cards →
TRIDENT and SHAKTI: A Framework and Benchmark for Hindi AI-Text Detection Oct 30 Show as cards →
Dhārā Bench: An Evidence-Oriented Retrieval Benchmark for Indian Knowledge Systems Nov 2 Show as cards →
Intra-Architecture Source Attribution for Stable Diffusion: A New Task with Benchmark Dataset and Baseline Nov 4 Show as cards →
OCCAMS: A Multi-Task Learning-Based Investigation of the CMB Power Spectra Oct 29 Show as cards →
LiDAR-SHIELD: A Fully Dockerized Adversarial Robustness Assessment Framework for LiDAR-Based 3D Perception Models Oct 29 Show as cards →
With foundation-model features, aggregator complexity does not improve cross-hospital discrimination in gastric whole-slide image classification Oct 30 Show as cards →
LungMend: A Healthy-Only Latent Diffusion Shape Prior for Lung Mask Correction in Severe Tuberculosis CT Nov 4 Show as cards →
AdMuse: Skill-Guided Creative Advertising Image Generation Oct 29 Show as cards →
VioTech: Frame-Level Violin Playing Technique Detection with Multi-Scale Mixture-of-Experts Nov 2 Show as cards →
Homebrewed SLMs: Autoregressive and Masked Diffusion Language Models Built at Home for Portuguese Oct 29 Show as cards →
Inter-Frame Predictive Contour Coding for Semantic Map Compression Oct 29 Show as cards →
Spatio-Temporal Multi-Order Interaction for Video Recognition Nov 3 Show as cards →
Novel or Not? PatEx-Gym: Agentic Prior-Art Search for Novelty Assessment in Patent Examination Oct 23 Show as cards →
Bridging Neural Representations and Symbolic Semantics in Audio Classification Oct 29 Show as cards →
A Unified Benchmark for Aerial-Enhanced Autonomous Driving: The KITScenes Aerial Dataset Oct 29 Show as cards →
Training-Time Domain Transfer for Generator-Free Diagnostics on Novel Modalities in Computational Pathology Nov 2 Show as cards →
D2ML: Models for Direct-to-Biology Small Molecule Screening Oct 29 Show as cards →
DINOFAS: Bonafide-Centric Representation Learning for Face Anti-Spoofing Nov 2 Show as cards →
ArabGeoText: Tool-Augmented Vision-Language Models for Arabic Geospatial Text Spotting Nov 2 Show as cards →
Calibrating Attention-Based Token Pruning for Efficient Multi-Image Synthesis in UMMs Oct 29 Show as cards →
PathoS2VD: From 2D Histopathology to Pseudo Z-Stack Representations Nov 4 Show as cards →
Multi-Resident Data Association in Smart Homes via MDP Modeling and Behavior Cloning Nov 4 Show as cards →
Can We Stop the Backtest Yet? Anytime-Valid Promotion Tests for Adaptive Financial Research Agents Nov 2 Show as cards →
EviCast: Forecasting Retrieval Gains Through Shared Response Calibration Nov 2 Show as cards →
Route First, See Later: Enabling Vision Agents to Reason Scientifically by Separating Routing Policy from Action Spaces Nov 4 Show as cards →
QUAL: Quantile Alignment Improves Zero-Shot Time-Series Foundation Models Oct 30 Show as cards →
BEAKER: An Expert-Curated Benchmark for Embodied Brains in Self-Driving Chemical Laboratories Nov 4 Show as cards →
Bayes-Consistent Losses for Adaptive Inference in Classification Oct 29 Show as cards →
Basin2Vec: Learning Basin-Centric Embeddings for Scalable Hydrological Modeling Nov 3 Show as cards →
BiGrounder: Bidirectional Training Unlocks the Potential of GUI Grounding Nov 5 Show as cards →
PlantVLM-Edge: Quantized Vision-Language Models for On-Device Crop Health Diagnosis Nov 2 Show as cards →
Sable: A Small-Field Sumcheck Argument for Bit-Exact Inference of Large Language Models Nov 10 Show as cards →
TCSExam: Evaluating Frontier LLMs on the Full Range of TCS Research Nov 5 Show as cards →
Painting Change Map as guidance for generating painting processes Oct 17 Show as cards →
A Two-Wheeled Quadrotor with All-Clockwise Tilted Rotors for Level-Attitude Surface Locomotnion Oct 29 Show as cards →
Heterogeneous Co-Evolution Learning for Tool-Efficient Search Agents with Zero Labels Oct 29 Show as cards →
Efficient Covariance-Aware Vicinal Latent Diffusion for Continuous Conditional Image Generation Oct 29 Show as cards →
PriCBMs: Multi-granular Concept Bottleneck Vision-Language Models for Visual Privacy Recognition Nov 2 Show as cards →
FARR: Forecast-Aware Residual Refinement with Matched Endpoint Evidence for Long-Horizon Time-Series Forecasting Nov 5 Show as cards →
Progressive Multi-Scale Super-Resolution via Cascaded Bicubic Anchors and Inter-Scale Mutual Refinement Nov 2 Show as cards →
Overview of the NTCIR-19 SciClaimEval Task: Cross-modal Claim Verification in Scientific Papers Nov 4 Show as cards →
IMPACT: Inverter-Informed Multimodal Learning for Photovoltaic Generation Forecasting Oct 29 Show as cards →
Selective Event Evidence and Persistent Temporal Priors for Event-Based Point Tracking Nov 5 Show as cards →
JEDI: Joint-Embedding Demonstration Compression for In-Context Imitation Learning Oct 29 Show as cards →
An Agentic Framework for Quality-Aware and Scenario-Adaptive Image Compression Nov 3 Show as cards →
Socratic Skill Learning: Interleaving Teaching and Practice for Transferable Agent Skills Oct 12 Show as cards →
StepBack: Step-Level Error-Localized Resampling for Efficient Test-Time Reasoning Nov 5 Show as cards →
Integrating Machine Learning and Uncertainty Quantification for Real-Time Decision-Making in Digital Twins: A System-Centric Review and Perspective Nov 3 Show as cards →
TEXMET: A Deep Learning Benchmark for Archaeological Textile Reconstruction Nov 3 Show as cards →
CR-Bench-v2: Evaluating the Real-World Utility of AI Code Review Agents Nov 2 Show as cards →
Latent Prediction Yields Cross-Subject Alignable Representations in Sensory-Evoked fMRI Oct 29 Show as cards →
LipLingo: CNN Model for Lip Reading Nov 2 Show as cards →
Beyond Selected Breakthroughs: Evaluating Language Models on Randomly Sampled Mathematical Conjectures Oct 29 Show as cards →
Kernel-based Interpolatory Methods for Context Compression of Attention Mechanisms Oct 29 Show as cards →
FPTR: Feasibility-Preserving Transactional Refinement for Deadline-Constrained Joint Beam and Resource Allocation Nov 4 Show as cards →
When Fine-Grained Credit Assignment Helps and Hurts: Multimodal Agentic Reinforcement Learning through Video Editing Oct 25 Show as cards →
Comparative study of global pooling for pre-departure ship fuel consumption prediction: Advantages over per-ship and adaptation-based approaches Nov 2 Show as cards →
Accelerating Safe Reinforcement Learning with Massive Parallelism Nov 5 Show as cards →
FindLink: Learning to Assess Scientific Connections from Source-Grounded Premises Nov 2 Show as cards →
A Unified Hessian-Guided Framework for Post-Training Quantization Oct 29 Show as cards →
Decoding Geometry, Not Tokens: Efficient VLMs for Robot Affordance and Trajectory Prediction Oct 29 Show as cards →
How Finely Can Vision-Language Models See Biology? Bio-VQA: A Benchmark for Taxonomic, Morphological, Spatial and Individual Reasoning Nov 3 Show as cards →
Practical Assessment of Agentic Systems in Acoustics Oct 29 Show as cards →
ARLoop: Fully-Open Pre-trained Looped Transformers with Attention Residuals Nov 3 Show as cards →
P-ContextBench: From Personal Fact Recall to Personalized Agent Behavior Oct 29 Show as cards →
Efficient Closure Learning in Dynamical Systems: A Comparison of Data-Assimilated and Embedded Approaches Nov 2 Show as cards →
Energy-Guided Transport for Projection-Free Physics-Informed Flow Matching Nov 4 Show as cards →
Evidence-First Agentic Verification Oct 12 Show as cards →
IGDA-ICMH: an Importance Guided Feature and Network Dual Adaptation Framework towards Image Compression for Machine and Human Vision Oct 30 Show as cards →
MRC-MMAgent: Reinforcement Learning for Multi-Role Collaboration in Multimodal Tool-Using Agents Oct 29 Show as cards →
InfMasking: A Unified Variational Framework for Synergistic Multimodal Learning Nov 5 Show as cards →
Benchmarking color judgment in multimodal LLMs with CIE-computable ground truth Oct 29 Show as cards →
ScienceJudge: Pattern Perturbation Augmentation for Sentence-Level Scientific Claim Verification Oct 29 Show as cards →
HistoTx: Early fusion of H&E images and spatial transcriptomics at varying spatial transcriptomics resolution with self-supervised learning Nov 2 Show as cards →
PathoJev: Efficient Pathology Decisions from Shared Visual Context Oct 29 Show as cards →
Last-Iterate Convergence for Constrained MDPs: From Dual Descent to Primal-Dual Oct 29 Show as cards →
Sonar-MoE: In-Backward Expert Updates for Memory-Efficient Mixture-of-Experts Training Nov 2 Show as cards →
SPA-Q: Structure-Preserving Adaptive Post-Training Quantization for Monocular Depth Estimation Nov 3 Show as cards →
Disen-Forcing: Disentangling Semantic Anchoring from Motion for Autoregressive Video Diffusion Nov 2 Show as cards →
Latent Diffusion-GAN: Adversarial Learning in the Autoencoded Latent Space Nov 2 Show as cards →
Pixel-space video generation with U-JiT Nov 3 Show as cards →
IndicIPR-QA: A Benchmark for Extractive Question Answering on Indian IPR Laws Oct 29 Show as cards →
Catastrophic Overfitting is Weight Drift the Training Loss Cannot See Nov 4 Show as cards →
Multimodal Information Interactions Bottleneck for Multimodal Self-Supervised Learning Nov 5 Show as cards →
A New AFIB Detection Method with Deep Neural Networks Oct 29 Show as cards →
Automatic keyphrase extraction and annotation: modern theoretical approaches and practical solutions for text and speech Nov 5 Show as cards →
MUSBRIC: LEGO-Compatible Pneumatic Muscle Bricks for Reconfigurable Musculoskeletal Robots Oct 29 Show as cards →
When Do Summaries Become Instructions? Unsupported Policy in LLM Agents' Self-Written Handoff Summaries Nov 4 Show as cards →
Which One Is Sounding? Binaural Sounding Instance Disambiguation for Audio-Visual Segmentation Nov 4 Show as cards →
AVPS-360: A Spatial Audio-Visual Benchmark for Instance Segmentation and Tracking of Sound-Producing Persons Oct 29 Show as cards →
WorkIng: A Real-World and Synthetic Highway Work-Zone Benchmark Dataset for Autonomous Navigation Oct 30 Show as cards →
τ-bench-LILT: Evaluating Conversational Agents on Realistic Multilingual Tool-Use Tasks Nov 4 Show as cards →
Confidence-Aware Speed-over-Ground Estimation from Doppler Spectra via Reconstruction-Based Representation Learning Oct 29 Show as cards →
Composing and Steering Diffusion Models with Generalized Feynman-Kac Correctors Oct 29 Show as cards →
Benchmark of THReD: Evaluating an LLM Agent and Its Preprocessing Tools for Turning Electronic Health Records into AI-Ready Datasets Nov 2 Show as cards →
Item Representations Matter: Bridging Hard Semantic IDs and Soft Prototype Mixtures for Generative Retrieval Nov 4 Show as cards →
When Does Closed-Loop Curriculum Adaptation Help GRPO? An Analysis on Countdown Oct 28 Show as cards →
Language-Grounded Force/Torque Pretraining for Extrinsic Contact Perception Oct 29 Show as cards →
PBSR: Pseudo-Burst Super-Resolution via Zero-Shot Novel View Synthesis Oct 30 Show as cards →
A Fine-Grained Hierarchy and Benchmark for State Tracking in Language Models Nov 2 Show as cards →
STAR-FER: Adaptive Selective Restoration for Edge-Based Low-Resolution Facial Expression Recognition Oct 30 Show as cards →
Hammering with Vampire in Lean Oct 29 Show as cards →
A Tutorial on Shape Servoing of Deformable Objects-Part I: Fundamentals Oct 29 Show as cards →
Beyond Quadratic Attention: Separable Gaussian Operators for ODE Vision Transformers Nov 5 Show as cards →
Machine Learning-Based Detection of Mobile Money Scan Messages in Ghana: A Comparative Evaluation of Naive Bayes, Support Vector Machine, and Randon Forest Classifiers Oct 29 Show as cards →
Securing the Robotics Supply Chain Oct 29 Show as cards →
Parameter-Efficient Fine-Tuning of Transformer Encoders for Audio-Image-Symbolic Music Retrieval Oct 30 Show as cards →
Balancing Representations by Identifying and Generating Under-represented Data Nov 2 Show as cards →
TRUST-Stereo: Teacher-Assisted Robust Uncertainty-Guided Search and Transfer for Fast Stereo Matching Nov 3 Show as cards →
Validation-Gated ML Pipeline Synthesis with Expert-Grounded Self-Evolving Skills Nov 3 Show as cards →
From Natural Images to Medical Scans: Transferability of Diffusion Models for Medical Image Generation Nov 3 Show as cards →
Towards a Trustworthy and Governable Internet of Agentics: An Architectural Perspective on Protocols, Systems, and Services Nov 2 Show as cards →
An Axiomatic Framework for Reinforcement Learning in Open Multi-Agent Systems Nov 2 Show as cards →
FedReason: Large Language Models as Weight-Space Meta-Aggregators for Heterogeneous Federated Learning Nov 5 Show as cards →
TRACER, a time-to-event EHR foundation model for disease detection across health systems Oct 29 Show as cards →
From the Zoo to the BULLPEN: Sample-Efficient LLM Profiling via Multi-Channel Model Embeddings Oct 30 Show as cards →
CrowdForge: Effects of Audio and Visual Audience Participation Modalities on Agency, Collaboration, and Engagement in AI-Mediated MR Performances Nov 2 Show as cards →
Multistep and Multivariate Time Series Explainability with GradientSHAP: A Wind Power Case Study Oct 29 Show as cards →
GeoBiaset: A Counterfactual Benchmark for Demographic Bias in World-Level Geolocalization Nov 4 Show as cards →
WayPOP: A Panoramic Open-Set Panoptic Tracking Benchmark Nov 4 Show as cards →
The Power of Meta Access in the Software of the Future --- Demonstrated on LLM Chat UIs and Chat AI Nov 5 Show as cards →
Achieving Minimax-Optimal First-Order and Best-of-Both-Worlds Regret Simultaneously in Multi-Armed Bandits Oct 29 Show as cards →
BrainBind: Bridging Synchronized EEG and fMRI through Long-Form Naturalistic Video Representations Nov 3 Show as cards →
Can Large Language Models Review the Scientific Literature? A Test Against a 102-Article Benchmark Nov 3 Show as cards →
SMART: State-based Multi Agent Reasoning Traces for Verification-oriented Problem-Solving Nov 5 Show as cards →
COMPREHEND: Ultra-Fine-Grained Benchmark Understanding by Entailment Hierarchy Nov 3 Show as cards →
LeanContext: Disentangling Mathematical Resources from Local Formal Context in Lean Whole-Proof Generation Nov 5 Show as cards →
M-PFT: Angular Margin for Calibrated Prompt-Tuning of Fine-Tuned Vision-Language Models Oct 29 Show as cards →
Big Models, Small Gains: Frozen Forecasters as Classifiers on MONSTER Nov 4 Show as cards →
CRoS: Causality Reward on Scrambled CoTs Improves Accuracy and Reasoning Faithfulness Oct 30 Show as cards →
TileQuant: Tile as the Precision-Allocation Unit for LLM Mixed-Precision Post-Training Quantization Nov 4 Show as cards →
Benchmarking Large Language Models on Heterogeneous Cognitive and Biomedical Knowledge Graphs: The Role of Graph Grounding in Multi-Hop Reasoning and Hallucination Mitigation Nov 5 Show as cards →
Upcycling Language Models for Multiple Specialized Domains Oct 29 Show as cards →
AquaProbe: Efficient Adaptation of Frozen Vision Models for Underwater Images Oct 29 Show as cards →
Unsupervised Feature Selection Using Local Intrinsic Dimensionality -- Extended Version Oct 29 Show as cards →
Finite-Sample LTI System Identification from a Misspecified Finite Model Set Oct 29 Show as cards →
From PID to Reinforcement Learning in Building HVAC Control: A Control-Architecture Review of Tuning Strategies, Formulations, and Deployment Trade-offs Nov 2 Show as cards →
Human--AI Interactions as First-Class Data: A Formal Interaction Model and Runtime for Explainable AI Collaboration Oct 29 Show as cards →
KeyWise: Efficient Video-Only Piano Transcription with a Lightweight Per-Key Architecture Nov 3 Show as cards →
A Conveyor Belt Mechanism for Repositionable Magnetic Coupling Between Continuum Robots Oct 29 Show as cards →
Rain Beyond Streaks: Cascaded Realistic Rain and Wet Surface Synthesis via Scene Priors Nov 5 Show as cards →
DART: Domain-Agnostic Residual Transfer for Generalist Anomaly Detection Nov 5 Show as cards →
Contrastive Adapter Training and Consensus Knowledge Distillation for Multi-Source-Free Domain Adaptation in Skin Cancer Diagnosis Nov 2 Show as cards →
When Latent Dynamics Meet Data Assimilation: A Benchmark of Koopman-Type Representations Nov 2 Show as cards →
Blueprint2CAD: Benchmarking Foundation Models on Engineering Drawing-to-CAD Render Correspondence Nov 2 Show as cards →
Self-Supervised Pretraining for Label-Efficient Facial Expression Recognition using Smart Glasses Nov 3 Show as cards →
Rohbau3D-Semantics: Dense Semantic and Instance Labels for Point Clouds of Indoor Shell Construction Scenes Nov 4 Show as cards →
Evaluating Token Probabilities as Confidence Estimators in Human Behavior Simulations: A Case Study in Luxembourgish Next Like Prediction Nov 5 Show as cards →
GEKey: Learning Geodesic Eccentric 3D Keypoints via Self-Supervision Nov 5 Show as cards →
STRATA: Reinforcement-driven Active Sampling with Tri-paradigm Adaptation for Efficient 3D Spatial Transcriptomics Oct 29 Show as cards →
FIRME: Registry-Anchored Memory Graphs for Evolving, Heterogeneous Investor Knowledge Oct 29 Show as cards →
NitiBench+: A Temporal Thai Legal Question Answering Benchmark Across 17 Domains Nov 2 Show as cards →
DINOv2 for PET: A Pre-Training Domain Benchmark Across Classification, Segmentation, and Prognosis Oct 29 Show as cards →
MUSS: A Multi-scale and Sequence-based Model for Single-cell Gene Regulation Nov 5 Show as cards →
Latent Path Exploration via Potential-Guided Subtrajectory Balance Oct 29 Show as cards →
Navigational Safety of Marine Surface Vehicles in Restricted Visibility: From Intelligent Vision to Vision-Centered Multi-Sensor Fusion Nov 4 Show as cards →
How a Model's Architecture and Performance Influences Explainability: A Study of Grad-CAM and CRAFT in CNN-Based Image Classification Nov 9 Show as cards →
Beyond Local Refinement: Wide-Area Precise Cross-View Localization Nov 3 Show as cards →
The Geometry of Simulated Perspectives: Dissociating Representation and Behaviour in a Multimodal Language Model Nov 5 Show as cards →
LanG 2.0: Energy-Efficient Agentic AI for Semi-Automated Security Operations at Scale Oct 29 Show as cards →
Anomaly Detection on Resource-Constrained Devices with Reservoir Computing Nov 3 Show as cards →
