Daily Papers of 2026-05-11

  1. Mean Mode Screaming: Mean--Variance Split Residuals for 1000-Layer Diffusion Transformers 183 upvotes, #1 of 2026-05-11
  2. Flow-OPD: On-Policy Distillation for Flow Matching Models 95 upvotes, #2 of 2026-05-11
  3. MACE-Dance: Motion-Appearance Cascaded Experts for Music-Driven Dance Video Generation 85 upvotes, #3 of 2026-05-11
  4. Listwise Policy Optimization: Group-based RLVR as Target-Projection on the LLM Response Simplex 65 upvotes, #4 of 2026-05-11
  5. LLMs Improving LLMs: Agentic Discovery for Test-Time Scaling 64 upvotes, #5 of 2026-05-11
  6. HyperEyes: Dual-Grained Efficiency-Aware Reinforcement Learning for Parallel Multimodal Search Agents 62 upvotes, #6 of 2026-05-11
  7. HumanNet: Scaling Human-centric Video Learning to One Million Hours 51 upvotes, #7 of 2026-05-11
  8. Rubric-based On-policy Distillation 39 upvotes, #8 of 2026-05-11
  9. Anisotropic Modality Align 27 upvotes, #9 of 2026-05-11
  10. TextLDM: Language Modeling with Continuous Latent Diffusion 26 upvotes, #10 of 2026-05-11
  11. Beyond Retrieval: A Multitask Benchmark and Model for Code Search 23 upvotes, #11 of 2026-05-11
  12. Rethinking State Tracking in Recurrent Models Through Error Control Dynamics 23 upvotes, #11 of 2026-05-11
  13. AEM: Adaptive Entropy Modulation for Multi-Turn Agentic Reinforcement Learning 21 upvotes, #13 of 2026-05-11
  14. UniPrefill: Universal Long-Context Prefill Acceleration via Block-wise Dynamic Sparsification 21 upvotes, #13 of 2026-05-11
  15. DecodingTrust-Agent Platform (DTap): A Controllable and Interactive Red-Teaming Platform for AI Agents 20 upvotes, #15 of 2026-05-11
  16. MatryoshkaLoRA: Learning Accurate Hierarchical Low-Rank Representations for LLM Fine-Tuning 18 upvotes, #16 of 2026-05-11
  17. 4DThinker: Thinking with 4D Imagery for Dynamic Spatial Understanding 17 upvotes, #17 of 2026-05-11
  18. UniSD: Towards a Unified Self-Distillation Framework for Large Language Models 15 upvotes, #18 of 2026-05-11
  19. A^2RD: Agentic Autoregressive Diffusion for Long Video Consistency 15 upvotes, #18 of 2026-05-11
  20. Q-RAG: Long Context Multi-step Retrieval via Value-based Embedder Training 14 upvotes, #20 of 2026-05-11
  21. Normalizing Trajectory Models 14 upvotes, #20 of 2026-05-11
  22. MISA: Mixture of Indexer Sparse Attention for Long-Context LLM Inference 12 upvotes, #22 of 2026-05-11
  23. Scaling Continual Learning to 300+ Tasks with Bi-Level Routing Mixture-of-Experts 11 upvotes, #23 of 2026-05-11
  24. Fast Byte Latent Transformer 11 upvotes, #23 of 2026-05-11
  25. STARFlow2: Bridging Language Models and Normalizing Flows for Unified Multimodal Generation 10 upvotes, #25 of 2026-05-11
  26. SCOPE: Structured Decomposition and Conditional Skill Orchestration for Complex Image Generation 10 upvotes, #25 of 2026-05-11
  27. ModelLens: Finding the Best for Your Task from Myriads of Models 9 upvotes, #27 of 2026-05-11
  28. What if AI systems weren't chatbots? 8 upvotes, #28 of 2026-05-11
  29. What Matters for Diffusion-Friendly Latent Manifold? Prior-Aligned Autoencoders for Latent Diffusion 8 upvotes, #28 of 2026-05-11
  30. MLS-Bench: A Holistic and Rigorous Assessment of AI Systems on Building Better AI 8 upvotes, #28 of 2026-05-11
  31. SkCC: Portable and Secure Skill Compilation for Cross-Framework LLM Agents 7 upvotes, #31 of 2026-05-11
  32. IntentGrasp: A Comprehensive Benchmark for Intent Understanding 7 upvotes, #31 of 2026-05-11
  33. LiVeAction: a Lightweight, Versatile, and Asymmetric Neural Codec Design for Real-time Operation 6 upvotes, #33 of 2026-05-11
  34. InterLV-Search: Benchmarking Interleaved Multimodal Agentic Search 6 upvotes, #33 of 2026-05-11
  35. MDN: Parallelizing Stepwise Momentum for Delta Linear Attention 5 upvotes, #35 of 2026-05-11
  36. From Storage to Experience: A Survey on the Evolution of LLM Agent Memory Mechanisms 5 upvotes, #35 of 2026-05-11
  37. Steering Visual Generation in Unified Multimodal Models with Understanding Supervision 4 upvotes, #37 of 2026-05-11
  38. Rethinking RL for LLM Reasoning: It's Sparse Policy Selection, Not Capability Learning 4 upvotes, #37 of 2026-05-11
  39. Empirical Evidence for Simply Connected Decision Regions in Image Classifiers 4 upvotes, #37 of 2026-05-11
  40. PACEvolve++: Improving Test-time Learning for Evolutionary Search Agents 4 upvotes, #37 of 2026-05-11
  41. Learning Visual Feature-Based World Models via Residual Latent Action 4 upvotes, #37 of 2026-05-11
  42. DiffRetriever: Parallel Representative Tokens for Retrieval with Diffusion Language Models 4 upvotes, #37 of 2026-05-11
  43. SpecBlock: Block-Iterative Speculative Decoding with Dynamic Tree Drafting 4 upvotes, #37 of 2026-05-11
  44. BalCapRL: A Balanced Framework for RL-Based MLLM Image Captioning 4 upvotes, #37 of 2026-05-11
  45. Sparse Autoencoders as Plug-and-Play Firewalls for Adversarial Attack Detection in VLMs 4 upvotes, #37 of 2026-05-11
  46. R^3-SQL: Ranking Reward and Resampling for Text-to-SQL 3 upvotes, #46 of 2026-05-11
  47. Discovering Reinforcement Learning Interfaces with Large Language Models 3 upvotes, #46 of 2026-05-11
  48. Who Prices Cognitive Labor in the Age of Agents? Compute-Anchored Wages 3 upvotes, #46 of 2026-05-11
  49. Shallow Prefill, Deep Decoding: Efficient Long-Context Inference via Layer-Asymmetric KV Visibility 3 upvotes, #46 of 2026-05-11
  50. PrefixGuard: From LLM-Agent Traces to Online Failure-Warning Monitors 3 upvotes, #46 of 2026-05-11
  51. CGM-JEPA: Learning Consistent Continuous Glucose Monitor Representations via Predictive Self-Supervised Pretraining 2 upvotes, #51 of 2026-05-11
  52. CASCADE: Case-Based Continual Adaptation for Large Language Models During Deployment 2 upvotes, #51 of 2026-05-11
  53. Gated QKAN-FWP: Scalable Quantum-inspired Sequence Learning 2 upvotes, #51 of 2026-05-11
  54. CPCANet: Deep Unfolding Common Principal Component Analysis for Domain Generalization 1 upvotes, #54 of 2026-05-11
  55. Trajectory as the Teacher: Few-Step Discrete Flow Matching via Energy-Navigated Distillation 1 upvotes, #54 of 2026-05-11
  56. Delta-Adapter: Scalable Exemplar-Based Image Editing with Single-Pair Supervision 1 upvotes, #54 of 2026-05-11
  57. From Holo Pockets to Electron Density: GPT-style Drug Design with Density 1 upvotes, #54 of 2026-05-11

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.