Daily Papers of 2026-11-11

  1. Few-Step Streaming Video Generation via Condition Shifting 88 upvotes, #1 of 2026-11-11
  2. Tree-Ising: Repairing Language Models with Bit-Level Ising Edits 62 upvotes, #2 of 2026-11-11
  3. Don't Just Trust Your Memory: Evidence-Linked Memory Reduces Memory-Induced Degradation in LLM Agents 61 upvotes, #3 of 2026-11-11
  4. World In-Context Learning for Agentic Robot Manipulation 58 upvotes, #4 of 2026-11-11
  5. One Table, Many Queries: Benchmarking Generalist Tabular Models Across Generation, Imputation, and Prediction 39 upvotes, #5 of 2026-11-11
  6. dNaViT: Discrete Codes are General-Purpose Visual Representations 35 upvotes, #6 of 2026-11-11
  7. MACaQ: Fast, Model Agnostic Calibrated Quantization for Low-Precision Weights and Activations 30 upvotes, #7 of 2026-11-11
  8. Embodied First Exam 27 upvotes, #8 of 2026-11-11
  9. MMDM: Measuring Massive Multitask Decision Making 27 upvotes, #8 of 2026-11-11
  10. FINCOSMOS: An Open-World Evaluation Paradigm for Agents in Finance 25 upvotes, #10 of 2026-11-11
  11. DexForesight: Grounding Dexterous Policies with Implicit Spatial Foresight 25 upvotes, #10 of 2026-11-11
  12. WaveGen: Truly End-to-End Waveform Generation via Internal Spectral Trajectory Learning 16 upvotes, #12 of 2026-11-11
  13. DepthGraft: Structural Regularization through Hierarchical Cross-Layer KV Reconstruction 15 upvotes, #13 of 2026-11-11
  14. ProTEUS: A mutation-resolved world model for closed-loop protein evolution 14 upvotes, #14 of 2026-11-11
  15. The Surprising Effectiveness of Deleting Weights in LLM Post-Training 13 upvotes, #15 of 2026-11-11
  16. From Tool State to Scientific Action: Auditing Decision Provenance in Biomedical Research Agents 10 upvotes, #16 of 2026-11-11
  17. PhyRubric: Rubric-Grounded Diagnostic Evaluation of Physical Commonsense in Text-to-Video Generation 10 upvotes, #16 of 2026-11-11
  18. Micius-Flash: Lightweight Agentic Intelligence for Engineering 8 upvotes, #18 of 2026-11-11
  19. Test-Time Scaling for Diffusion Language Models with Frequency-Aware Remasking 8 upvotes, #18 of 2026-11-11
  20. PhysOPSD: Code as Privilege for Physically Plausible Video Generation 8 upvotes, #18 of 2026-11-11
  21. Is Your Robot's Memory Just a Clock? Temporal Shortcuts in Memory-Augmented VLA Policies 7 upvotes, #21 of 2026-11-11
  22. Are Causal Neuron Circuits Unique and Transferable? 6 upvotes, #22 of 2026-11-11
  23. Market-Conditioned JEPA: Learning from Unpredictable Market Shocks 5 upvotes, #23 of 2026-11-11
  24. LEASH: Stay Safe in Agentic Robotics 5 upvotes, #23 of 2026-11-11
  25. DyCraft: An Agentic System for Long-Horizon 4D Scene Generation 4 upvotes, #25 of 2026-11-11
  26. Blind Variation, Selective Retention: Improving Creative Idea Generation in AI Scientists 4 upvotes, #25 of 2026-11-11
  27. Shortcuts and Boundaries: Verifiable RL Misalignment and Contextual Safety Learning 4 upvotes, #25 of 2026-11-11
  28. EarthRecord: From Pixels to Land Change with Multimodal Agents over Four Decades of Satellite Imagery 4 upvotes, #25 of 2026-11-11
  29. ExRL: Sample-Efficient Online Adaptation of Long-Chunk Policies via Execution Length Control 4 upvotes, #25 of 2026-11-11
  30. Are Dense Rewards Worth Their Tokens in GRPO? 4 upvotes, #25 of 2026-11-11
  31. Learning to Act with World Models by Valuing What Comes Next 3 upvotes, #31 of 2026-11-11
  32. Predictive Surprise as Self-Grounding Concept Bottleneck for Interpretable Time Series 3 upvotes, #31 of 2026-11-11
  33. EVAThink: Evidence Sufficiency-Guided Training for Adaptive Thinking in Video Understanding 3 upvotes, #31 of 2026-11-11
  34. Visual Similarity in Adult Word Extension and Artificial Word Learning 3 upvotes, #31 of 2026-11-11
  35. TorchCurves: Differentiable Parametric Curves 3 upvotes, #31 of 2026-11-11
  36. Lipschitz-Controlled Flow Matching for Robust Image Restoration 2 upvotes, #36 of 2026-11-11
  37. Sable: A Small-Field Sumcheck Argument for Bit-Exact Inference of Large Language Models 2 upvotes, #36 of 2026-11-11
  38. LO-World: Unified BEV Latent Modeling for Joint 4D Occupancy and LiDAR Forecasting 1 upvotes, #38 of 2026-11-11
  39. Prompt2Echo (P2Echo): Text-Prompted Multi-View Echocardiography Segmentation with One Model 1 upvotes, #38 of 2026-11-11

Data: hysts-bot-data/daily-papers-stats and the Daily Papers API. Open data: tardellirs/paper-pulse-data. Sister project: Model Pulse, the download history of every model on the Hub.