Subscribe freeOpen sourceView on GitHubStarThis project is open sourceRead the code or use it in your own project. If you like it, don’t forget to give it a ★ star on GitHub.
Every edition
26 days of papers, newest first. Each day lists its top picks and everything else we found.
Nov 1414 Nov 2026WaveGen: Truly End-to-End Waveform Generation via Internal Spectral Trajectory Learning; Don't Just Trust Your Memory: Evidence-Linked Memory Reduces Memory-Induced Degradation in LLM Agents
200 papers
Nov 1313 Nov 2026The Surprising Effectiveness of Deleting Weights in LLM Post-Training; Few-Step Streaming Video Generation via Condition Shifting
200 papers
Nov 1212 Nov 2026World In-Context Learning for Agentic Robot Manipulation; Learning Heterogeneous Tactile Representation for General Dexterous Manipulation
200 papers
Nov 1111 Nov 2026LowRAM: Low-Rank Keys and Amortised Values for Composable KV Cache Compression at Test-Time; SplatAnything: Gaussian Spacing Normalization for Feed-forward 3DGS across Arbitrary Scenes
200 papers
Nov 1010 Nov 2026D3D: Decoupled Diffusion Drafting for Asynchronous Speculative Decoding; SLA: Scaling Spatial-Language-Action Model via Continual Pre-training
51 papers
Nov 99 Nov 2026EvoMemState: Evolving Memory State for Personal Agents; From Autonomous Agents to Cognitive Symbionts: Toward AI-Augmented Human Intelligence
200 papers
Nov 88 Nov 2026Random Is Almost Enough? Stable and Low-Cost Benchmark Compression via BestRand; VFlash: Fast, Accurate Visual Planning via Flash Primitive Decoding
200 papers
Nov 77 Nov 2026Hybrid Computer Use: A Unified Programmatic, Semantic, and Visual Interface for General Agents; TailSteer: Trajectory-Tail Steering for Drift-Resistant Multi-turn Image Editing
200 papers
Nov 66 Nov 2026From Pixels to Actions - Towards Native Vision-Language-Action Policies; FrontierPhysics: Evaluating Agents for End-to-End Physics Research
200 papers
Nov 55 Nov 2026Turns Matter: Advancing Streaming Video RL via Turn-Level Credit; Think Less, Locally: Local Preference Learning for Reasoning Compression
200 papers
Nov 44 Nov 2026CUA-Master: Scaling Computer-use Agents through Open-World Recursive Improvements; Advances in Agentic Computer Graphics
200 papers
Nov 33 Nov 2026FrameForge: Harnessing Priors of Video Foundation Models for Unified Image Generation; R^2Orch: Recursive Self-Improvement for Agent Orchestration via Self-Play within a Skill-Internalization Loop
47 papers
Nov 22 Nov 2026Does Scaling Toward AGI Depend on What System-1 Lets System-2 Execute?; L3G-World: Real-Time Infinite World Generation with Latent 3D Gaussian Memory
200 papers
Nov 11 Nov 2026Look Only When Needed: Certificate-Guided Visual Routing for Efficient Diffusion VLMs; Proving and Improving the Platonic Representation Hypothesis with JEPAs
200 papers
Oct 3131 Oct 2026Youtu-Parsing-Omni: One Encoder, One Schema, All Modalities; A-RSI: Adaptive Task Refresh for Zero-Data Multimodal Self-Improvement
190 papers
Oct 3030 Oct 2026Your Benchmark Is an Empirical Measure Over Difficulty; Efficient Streaming Audio-Visual Target Speaker Extraction for Real-World Acoustic Scenes
2 papers
Oct 2929 Oct 2026Can Test-Time Memory Evolution Outperform Test-Time Training for Scientific Discovery?; VibeVideoBench: Evaluating Multimodal Agents on Code-Driven Video Generation
2 papers
Oct 2828 Oct 2026PDRVLA: A Vision-Language-Action Model with Physical Dynamics Representations; Hy-Nomas: Towards Free-form Interactive World Generation
2 papers
Oct 2727 Oct 2026Novel or Not? PatEx-Gym: Agentic Prior-Art Search for Novelty Assessment in Patent Examination; SliderEdit++: Improved Slider Trajectories in Instruction-Based Image Editing
2 papers
Oct 2626 Oct 2026Editing Images into Reusable Layers via Compositional Edit-Prior Distillation; UserArena: Benchmarking Interactive User Simulation for Long-Horizon Shopping Agents
2 papers
Oct 2525 Oct 2026Editing Images into Reusable Layers via Compositional Edit-Prior Distillation; What Generation Knows: Unlocking Fine-Grained Understanding in Unified Multimodal Models
2 papers
Oct 2424 Oct 2026Editing Images into Reusable Layers via Compositional Edit-Prior Distillation; What Generation Knows: Unlocking Fine-Grained Understanding in Unified Multimodal Models
2 papers
Oct 2323 Oct 2026Editing Images into Reusable Layers via Compositional Edit-Prior Distillation; What Generation Knows: Unlocking Fine-Grained Understanding in Unified Multimodal Models
2 papers
Oct 2222 Oct 2026Socratic Skill Learning: Interleaving Teaching and Practice for Transferable Agent Skills; Think Harder Where It Matters: Item-Level Adaptive Recursion for Sequential Recommendation
2 papers
Oct 2121 Oct 2026Ropedia W0: Scaling Loco-Manipulation World Models across Embodiments with Human Experience; Painting Change Map as guidance for generating painting processes
2 papers
Oct 2020 Oct 2026Evidence-First Agentic Verification; Where is Physical RSI capability from? An Observational Scaling Law of LLM-as-policy