Random Is Almost Enough? Stable and Low-Cost Benchmark Compression via BestRand
In shortBestRand improves random benchmark compression by cutting high-error risk and estimation error while using about half the cost.
Published 30 Oct 2026
8 Nov 2026
200 papers that day.
Picks that day
VFlash: Fast, Accurate Visual Planning via Flash Primitive Decoding
In shortVFlash jointly decodes visual primitives for fast, accurate planning, achieving ~25× speedup and higher task success.
Published 5 Nov 2026
Everything else
198 more papers from this day- Nov 2 Harness-S: Learning from Sibling Harnesses for Generalizable Agent Training
-
Nov 3
From Autonomous Agents to Cognitive Symbionts: Toward AI-Augmented Human Intelligence
TrendingReasoning & Agents
- Oct 31 Decoupled Predictive Decision Making: A Shared Conditional Predictor for Agents
-
Nov 5
SLA: Scaling Spatial-Language-Action Model via Continual Pre-training
TrendingLLMs & Language Models
- Nov 2 VisSearch-Bench: Evaluating Long Horizon Visual Search in Multimodal Agents
- Nov 3 D3D: Decoupled Diffusion Drafting for Asynchronous Speculative Decoding
- Nov 5 Towards Foundation Decision Models: Drex
- Nov 1 EvoMemState: Evolving Memory State for Personal Agents
- Nov 5 WeLM-Image: A Unified Image Generation Model towards Visual Intelligence
- Nov 5 EDGAR: Efficient Diffusion-Driven Gaussian Avatar Refinement via Synthetic Failure
- Nov 4 On the Opportunities and Challenges of Prefill-to-Autoregressive Cross-Model Transfer
- Nov 5 Terminal-style Mathematical Modeling Bench: The First Agentic and Verifiable Benchmark for Mathematical Modeling
- Nov 3 Open-HumanScale: An Open Recipe for Scaling Human and Robot Experience for Embodied Foundation Models
- Nov 3 Halley: A Predictive Control Plane for Optical AI Data Center Networks
- Nov 5 SAE Interprets MoE: Sparse AutoEncoders Reveal That MoE Experts Exhibit Human-Interpretable Fine-Grained Specialization
- Nov 1 TAC-CoT: Tool-Empowered Implicit Chain-of-Thought via Interleaving Explicit Tokens
- Nov 4 SwarmEvolve: Latent Agent Swarms for Evolutionary Discovery and Optimization
- Nov 2 HeLM: Hierarchical Explicit Language Memory for Non-Markovian Manipulation
- Nov 3 NitroFusion2: Bringing Adversarial Loss to the Text Stream of Multimodal Diffusion Transformers
- Nov 2 StepX-OPD: Rethinking Multi-Teacher On-Policy Distillation in Diffusion Models
- Nov 3 Future Representation Distillation for Imagination-free World Action Models
- Nov 1 The SIMPLE Law for Energy Cost of LLM Inference
- Nov 3 Tools Need Not Speak in Text: Latent Context Compression for Agents
- Nov 1 Multi-layer Indexer: Overlapping Selection and Attention in DeepSeek Sparse Attention
- Nov 1 Why Pay for Long Reasoning When Rewrite Do Trick? Causal Effects of Reasoning History Compaction on Future Generation and Agent Cost
- Nov 5 Muir: Linear Attention with Sensitivity-Allocated Gating and Matched-Filter Readout
- Nov 4 PyRUA-REAL: Robot Exploration and Adaptive Learning through RSI in the Real World
- Nov 5 Towards Real-Time Full-Waveform LiDAR Transformers via Intensity-Guided Token Reduction and Physics-Aware Augmentation
- Nov 4 Signed but Steerable: Measuring and Closing the Text-Vector Integrity Gap in Offline Retrieval-Augmented Generation
- Nov 1 TaoMate-HD: Progressive-Resolution Autoregressive Audio-Video Generation
- Nov 4 LiveFoley: Dynamic Real-Time Video-to-Audio Generation for Immersive Interactive Worlds
- Nov 3 Koopman Generative Operators for Efficient Probabilistic Time-Series Forecasting
- Nov 3 Decode Before You Hear: Speculative Listening for Chunk-Interleaved Full-Duplex Speech Language Models
- Nov 3 GaussianRenderFormer: Transformer-based Rendering of 3D Gaussian Splats
- Nov 4 Reducing Representational Interference in Retrieval Embeddings with Trainable Prefix Tokens
- Oct 24 Identically Trained Language Models Break on Different Jailbreaks
- Oct 30 Hard Sample-Conditioned Decorrelated Attention for Robust Face Recognition
- Nov 2 HERIT: Enabling Global Access to Hanja-to-English Historical Translation by Mitigating Temporal Bias
- Nov 1 Ask, Don't Equip: Question-Driven Coding Agents for Deep Kernel Optimization
- Nov 4 UniRestorer++: Scalable Universal Image Restoration with Multi-Granularity Degradation Modeling
- Oct 26 OpenFrontiers: A Collection of Open Research Problems and a Benchmark for Scientific Rediscovery
- Nov 4 Information Games: Strategic Crowding and Firm Repositioning in Language-Model Space
- Oct 26 Monitor Accuracy Isn't the Answer: A Decision-Value Framework for Evaluating AI Agent Restart Monitors
- Nov 5 NPCBench: A Clinical Apprenticeship Benchmark for Multimodal Care-Pathway Reasoning in Nasopharyngeal Carcinoma
- Oct 28 SynthFaces: Balanced Large Scale Human Dataset
- Nov 3 DRAP: Dynamics-Risk Adaptive Plasticity for Continual Learning in Physical AI
- Nov 4 Interactive World Simulation with Cosmos for Physical AI
- Nov 4 Confucius4-R2T2: A Stable-Prefix Streaming ASR Model for Real Real-Time Transcription
- Nov 5 Beyond Instruction Override: Benchmarking Indirect Prompt Injection with Task-Tampering Attacks
- Nov 5 ProQuant: Progressive Quantization-aware Training for Edge MLLMs
- Nov 5 MUSS: A Multi-scale and Sequence-based Model for Single-cell Gene Regulation
- Nov 5 How Far Can Lightweight LLMs Go in Intent-to-SLO Translation?
- Nov 5 AttnSR: Attention Step Reward for Long-Horizon Agentic RL
- Nov 5 Enhanced MRI brain tumor detection using deep learning in conjunction with explainable AI SHAP based diverse and multi feature analysis
- Nov 5 Axis-LoRA: Probing and Adapting Embedding Models for Personal-Memory Retrieval
- Nov 5 Reinforcing What the Student Has Learned: Teacher-Guided On-Policy Distillation
- Nov 5 MCPHallu: Benchmarking Reasoning, Execution, and Memory Hallucinations in MCP Agents
- Nov 5 Simple Meta-Learning for HPO and CASH Using Performance Representations
- Nov 5 Binding Paraphrased Instructions to Encountered Objects in sLLM Agents under Partial Observability
- Nov 5 FlashOffloading: Low-Latency KV Cache Offloading for Long-Context LLM Serving
- Nov 5 Concertina: Embodying Manipulation and Cognition in One Diffusion Vision-Language Model
- Nov 5 RLGPA: A Reinforcement Learning-Guided Granularity Planning Attack for Decision-Based Sparse Adversarial Examples
- Nov 5 Enhancing Repository-Level Code Completion with Reinforcement Learning in Real-World Scenarios
- Nov 5 Where Do Reported Long-Video QA Gains Come From? A Controlled Audit of Frame Selection, Evidence Injection, and Expert Routing
- Nov 5 TriAttention: Unified Sparse Mixed-Precision Attention for Long-Context LLM Inference
- Nov 4 TileQuant: Tile as the Precision-Allocation Unit for LLM Mixed-Precision Post-Training Quantization
- Nov 4 τ-bench-LILT: Evaluating Conversational Agents on Realistic Multilingual Tool-Use Tasks
- Nov 4 SD-LoRA: Training-Time Structural Distillation into LoRA for Few-Shot Vision-Language Adaptation
- Nov 3 Where to Connect? Boosting MLLMs via Dynamic Gated Pathways across ALL ViT and LLM Layers
- Nov 4 Context-Aware Autoregressive Image Generation for Emerging Reasoning Properties
- Nov 4 Energy-Guided Transport for Projection-Free Physics-Informed Flow Matching
- Nov 4 Agent-Driven Generative Priors for Pathology Image Synthesis and Segmentation
- Nov 4 When Do Summaries Become Instructions? Unsupported Policy in LLM Agents' Self-Written Handoff Summaries
- Nov 4 MKD2World: A Typed Spatial MarkDown World Model For Web Agents
- Nov 4 Using Experience Twice: Dynamic Process Rubrics for Privileged Token-Level Credit Assignment
- Nov 4 ElecLoad: Adaptive Electricity Load Forecasting Guided by Multiple Events
- Nov 4 Understanding the Out-of-Distribution Generalization of Chain-of-Thought Reasoning in LLMs
- Nov 4 Entropogram-guided Visual Realignment Decoding: Capturing the Rhythm of Multimodal Reasoning
- Nov 4 Zero-Shot Coordination among LLM Agents
- Nov 4 A Systematic Benchmark for Evaluating Multimodal Personalized Reasoning of Vision-Language Models
- Nov 4 Rohbau3D-Semantics: Dense Semantic and Instance Labels for Point Clouds of Indoor Shell Construction Scenes
- Nov 4 Beyond Risk Cues: A Mechanism-Level Benchmark and Verifiable Debate for Scam Video Detection on the Web
- Nov 4 Catastrophic Overfitting is Weight Drift the Training Loss Cannot See
- Nov 4 SVGFaith: A Two-Layer Meta-Evaluation of Faithfulness Metrics for Text-to-SVG Generation
- Nov 4 USI-Brain: Enhancing Underwater Spatial Intelligence via Spatial Data-Driven Vision-Language Modeling
- Nov 4 MotoVerse: A Benchmark for Predictive Perception of Motorized Two-Wheelers in Dense Unstructured Traffic
- Nov 4 Intra-Architecture Source Attribution for Stable Diffusion: A New Task with Benchmark Dataset and Baseline
- Nov 3 Modality-Aware Expert Pruning for MoE-Based Multimodal Large Language Models
- Nov 4 RECAP: Context-Aware Prediction Recycling with Request-Local and Persistent Memories for Multimodal Speculative Decoding
- Nov 4 TandemBench: Benchmarking Decision Models for Multi-Agent Collaboration
- Nov 4 ReTailor: A Residual Feature Tailoring Framework for Real-Time Cross-Sensor Pansharpening Adaptation
- Nov 4 Module-Aware Optimization for Graph Neural Networks
- Nov 5 SpecCTMC: Exact Speculative Simulation of Diffusion Language Model Continuous-Time Markov Chains
- Nov 5 LeanContext: Disentangling Mathematical Resources from Local Formal Context in Lean Whole-Proof Generation
- Nov 5 DART: Domain-Agnostic Residual Transfer for Generalist Anomaly Detection
- Nov 5 Scaling Neural Motor Decoding via Decoupled Behavioral Pretraining
- Nov 5 Reinforcing End-to-End Autonomous Driving Safety via Negative-Aware Planning in a Unified World-Action Model
- Nov 5 GTAFL: Addressing Test-Agnostic Long-Tailed Federated Learning in Medical Image
- Nov 5 TCSExam: Evaluating Frontier LLMs on the Full Range of TCS Research
- Nov 5 IDPrior: Decoupling Identity Generation from Facial Image Synthesis
- Nov 5 FARR: Forecast-Aware Residual Refinement with Matched Endpoint Evidence for Long-Horizon Time-Series Forecasting
- Nov 5 OcTreeMamba: Topology-Aware Mamba for 3D Medical Segmentation via Octree Sparsification
- Nov 5 Learning Robotic World Models with Semantic and Visual Feedback
- Nov 5 CMDiff: Left Atrial Scar Segmentation from 3D LGE MRI Using Conditional Mask Diffusion Model: A Feasibility Study
- Nov 5 Rain Beyond Streaks: Cascaded Realistic Rain and Wet Surface Synthesis via Scene Priors
- Nov 5 BiGrounder: Bidirectional Training Unlocks the Potential of GUI Grounding
- Nov 5 ConvPE: Convolutional Position Embedding Improves Transformers
- Nov 5 Multimodal Information Interactions Bottleneck for Multimodal Self-Supervised Learning
- Nov 5 Selective Event Evidence and Persistent Temporal Priors for Event-Based Point Tracking
- Nov 5 Fast and Accurate Hand Estimation in Pixels, Interaction and World Space
- Nov 5 InfMasking: A Unified Variational Framework for Synergistic Multimodal Learning
- Nov 5 GEKey: Learning Geodesic Eccentric 3D Keypoints via Self-Supervision
- Nov 5 Neural Image Compression with Internal-External Prior Fusion and Alignment
- Nov 5 Subspace Learning with Outlier Exposure for Out-of-Distribution Detection
- Nov 5 Guidance Is a Field, Not a Scalar: Interval-Integrated Classifier-Free Guidance for One-Step Video Generation
- Nov 5 ZYFA: Speed and Accuracy of FP8 FlashAttention on AMD CDNA4
- Nov 5 Echoes of Error: Residual-Directional Local Rollout Consistency for Timeseries Forecasting
- Nov 4 FastAFD: When Does Attention-FFN Disaggregation Pay on Rack-Scale NVLink?
- Nov 4 Procedural Adversarial Learning
- Nov 4 Adaptive Multi Mode: Budget-Aware Routing of Optimizers By Online Landscape Probes
- Nov 4 Batch-Conditioned Semantic Anchors for Robust Transductive Adaptation of Vision--Language Models
- Nov 4 Big Models, Small Gains: Frozen Forecasters as Classifiers on MONSTER
- Nov 4 Sekai: Incremental Event Memory for Generalized Reasoning Video Segmentation
- Nov 4 LungMend: A Healthy-Only Latent Diffusion Shape Prior for Lung Mask Correction in Severe Tuberculosis CT
- Nov 4 CoDecide: Content-Adaptive Video Decoding for High-Throughput Video Analytics
- Nov 4 DreamRealm: Exploring and Materializing Hallucination Worlds for Trustworthy Vision-Language Models
- Nov 4 TOP: Transmission-Oriented Remote Sensing Pansharpening
- Nov 4 Twists and Turns: A Graph-Based Benchmark and Framework for Long-Term Memory in Exploration Tasks
- Nov 4 FlashRelight: Portrait Video Relighting with Dynamic Lighting
- Nov 4 Conformal Prediction for Distribution-to-Distribution Regression
- Nov 4 DyPSI: Dynamic Physics Sensing via Joint Field and Sensor-Trajectory Generation
- Nov 4 NextGAN: Towards Simple and Scalable GAN Training for Image and Video Generation
- Nov 4 ChanSFormer: A Channel Agnostic Vision Transformer for Multi-Channel Cell Painting Images
- Nov 4 Decouple to Reuse: Fine-Grained Knowledge Augmentation for Time Series Foundation Models
- Nov 4 PathoS2VD: From 2D Histopathology to Pseudo Z-Stack Representations
- Nov 4 Split-KV: Efficient Context Parallelism for Training Diffusion Drafters
- Nov 3 CARTBench: Rubric-Based Evaluation of Shopping Advice for Complex and Ambiguous Requests with Timelines
- Nov 4 Navigational Safety of Marine Surface Vehicles in Restricted Visibility: From Intelligent Vision to Vision-Centered Multi-Sensor Fusion
- Nov 5 Label-Wording Augmentation in a Typed-Decision Encoder: Gains on Unfamiliar Words, Not on Abbreviations or Codes
- Nov 5 Static Recovery Is Not Dynamic Stability: Dynamics-Aware Benchmarking of Protein Motif Scaffolding
- Nov 5 MetricTrail: Revisiting the Power of Metric Depth and Local Optimization for Long-Sequence Streaming 3D Reconstruction
- Nov 4 $D^2$-OPD: Separating Direction and Distance in Extrapolative On-Policy Distillation
- Nov 4 Replicability, Reproducibility, and Robustness in Political and Social Science Research with Large Language Models
- Nov 4 Softmax Attention with Any Temperature in Fixed Dimension: Matching the Best Known Maximum-Inner-Product Bounds
- Nov 5 User Embeddings are Superpositions of Interpretable Behavioral Modes
- Nov 5 Do You Miss the Nights We Spent Crafting Figures? Rethinking Teaser and Framework Figures in the Age of Generative AI
- Nov 5 Where and Why is Grounded Reasoning Useful?
- Nov 5 EgoGeneralist: Unifying Egocentric Action-Video Tasks through Video-Native Modeling
- Nov 5 XStack: A Benchmark for ML Repo Migration
- Nov 5 Towards interpreting any residual stream direction by scaling activation inversion
- Nov 5 MedGraph: Maintaining Patient State with Graph Memory for Long-Term Medical Dialogue
- Nov 5 The Power of Meta Access in the Software of the Future --- Demonstrated on LLM Chat UIs and Chat AI
- Nov 5 Benchmarks as Software: Terminal-Bench and the Case for Continuous Benchmarks
- Nov 5 Spectral and Subspace Dynamics of LoRA in Supervised Fine-Tuning and Reinforcement Learning
- Nov 5 T3R: Training-Free Two-Stage Token Refinement Towards Efficient and Robust VLA Models
- Nov 5 StepBack: Step-Level Error-Localized Resampling for Efficient Test-Time Reasoning
- Nov 5 Adaptive Low-Light Enhancement for Road Anomaly Detection: A Multi-Architecture Benchmark and Edge Deployment Study
- Nov 5 FedReason: Large Language Models as Weight-Space Meta-Aggregators for Heterogeneous Federated Learning
- Nov 5 MOMASPLAT: Dynamic Novel-View Demonstration Augmentation for Mobile Manipulation
- Nov 5 StrataFlux: Memory-Hierarchy-Native Low-Bit LLM Inference
- Nov 5 Enhancing Local and Global Structure in Compressed AI Agent Memory
- Nov 5 Cultural Adaptation within Repeated Social Interactions
- Nov 5 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 RM-VLM: From Natural-Language Task Descriptions to Vision-Grounded Reward Machines
- Nov 5 Dynamic Optimistic Constrained OCO with Memory via Delay Equivalence
- Nov 5 Transformer-Based Trajectory Prescription for sEMG-Optimizing Robot-Mediated Rehabilitation
- Nov 5 ManimCode: Learning Visual Self-Correction for Educational Animation
- Nov 5 AutoCompress: Automated Hardware-Guided Model Compression
- Nov 4 Interactive Visual Gym: Evaluating Visual Interaction Models with Simulated Users in Interactive Worlds
- Nov 5 Multimodal-SEA: Benchmarking AI Agent Security under Multimodal Social Engineering Attacks
- Nov 5 Accelerating Safe Reinforcement Learning with Massive Parallelism
- Nov 5 The Geometry of Simulated Perspectives: Dissociating Representation and Behaviour in a Multimodal Language Model
- Nov 5 FewStepRL: Fine-tuning Few-step Diffusion Models with Reinforcement Learning
- Nov 5 Beyond Quadratic Attention: Separable Gaussian Operators for ODE Vision Transformers
- Nov 5 Signals, Evidence, and Context: User Scrutiny in Real-World LLM Conversations
- Nov 5 From Twisted Facts to Rogue Agents: Can LLMs Reliably Detect Multi-Dimensional Hallucinations?
- Nov 4 Agent-R^2: Scaling Agents for Realistic Productivity Work via Real-Source Data Synthesis
- Nov 5 Do sEMG Foundation Models Improve Cross-Subject Generalisation?
- Nov 5 SMART: State-based Multi Agent Reasoning Traces for Verification-oriented Problem-Solving
- Nov 5 Multimodal Hierarchical Mixture-of-Experts for 3D Medical Vision-Language Modeling
- Nov 5 Knowing When to Teach: Learning from Teachable Prefixes in Multilingual Reasoning Distillation
- Nov 5 PCBRouteAgent: How Close Are LLM Agents to Becoming PCB Routing Engineers?
- Nov 5 La-JEPA: Compact Robot Policies with Latent World Modeling
- Nov 5 Interpretable Multimodal MRI-Clinical Fusion for Functional Outcome Prediction After Acute Ischemic Stroke
- Nov 5 MCUFlowNet: Hardware-Aware Neural Architecture Search for Optical Flow on Microcontrollers
- Nov 5 Fault-Guided Cross-Layer Prediction for Unsupervised Anomaly Detection
- Nov 5 Describe Your Facial Expressions by Linking Image Encoders and Large Language Models
- Nov 5 How Far Can Untrained Neural Networks Go in Anomaly Detection? From Tables to Pixels
- Nov 5 Create Your Own Work Stack: Deploying Self-hosted AI and Tooling in a Tech Startup
- Nov 5 Towards Practical 20 kbps Generative Video Compression via Adaptive Tokenization and Entropy Modeling
- Nov 5 PersonaAgent: Retrieval-Augmented Transaction Anomaly Scoring with Refreshable Multi-Entity Persona Memory
- Nov 5 Gabor Gabor: E-Gaborformer, a Strictly Causal Speech Recognizer with Gabor-Dictionary Convolutions and Delta-Rule Memory
- Nov 5 ATHAAR: A Medieval Scientific Arabic Manuscript Dataset for Handwritten Text Recognition
- Nov 5 DictLLM: Post-training Compression of Large Language Model with Dictionary Kernels
- Nov 5 Spatiotemporal Dynamics-Aware Industrial Anomaly Detection and Reasoning
- Nov 5 Can an LLM Actually Reason and Program about Neural Network's Weights or is it just memorization on steroids? Exploring "Weight-Space Programming"
- Nov 5 NutriVisRAG: Multimodal Exemplar Grounding for Nutrient Estimation with Vision-Language Models
- Nov 5 Should We Pay This Much for Robustness? Efficient Proxy Certificates with Marginal Guarantees