Daily Papers of 2026-11-19

  1. PROLA: Principal-Orthogonal Low-rank Adaptation for Predictive Spatiotemporal Weather Downscaling 22 upvotes, #1 of 2026-11-19
  2. Game2Player: Scaling Gameplay Experience for Visual Agents through Environment-Player Co-Development 18 upvotes, #2 of 2026-11-19
  3. The Resolution Hypothesis: Agent Evolution's Key Is Identifying Improvements 13 upvotes, #3 of 2026-11-19
  4. ALIVE: Making Streaming Video Models Interactive 11 upvotes, #4 of 2026-11-19
  5. Code World Model 2.0: Towards Infinite Controllable Video Generation 7 upvotes, #5 of 2026-11-19
  6. Mechanistic Critics for Sample-Efficient NPU Design-Space Exploration 6 upvotes, #6 of 2026-11-19
  7. Tideway: Phase-Aware Tiered Memory Management for MoE Inference on Consumer Devices 5 upvotes, #7 of 2026-11-19
  8. Decoding Without a Decoder: Direct Pixel Prediction from Diffusion Transformers 5 upvotes, #7 of 2026-11-19
  9. QDA: Closed-Loop LLM Quantization Design with Agents 4 upvotes, #9 of 2026-11-19
  10. Jeveration: System One Models Now Generate 4 upvotes, #9 of 2026-11-19
  11. Learning Anisotropic Prediction Targets for Flow Models 3 upvotes, #11 of 2026-11-19
  12. LogT: Logically Think with Images for Visual Search 2 upvotes, #12 of 2026-11-19
  13. Let Samples Sing in Chorus: Mitigating Spurious Correlations via Cross-view Consensus 2 upvotes, #12 of 2026-11-19
  14. Evidence-Based Credit Assignment for Search-Augmented Language Models 2 upvotes, #12 of 2026-11-19
  15. Recurrent Domain Incremental Adaptation of Time-Series Foundation Models 2 upvotes, #12 of 2026-11-19
  16. IDEA: Intent-Dominance Evidence Audit for Inference-Time Backdoor Detection in GUI Agents 2 upvotes, #12 of 2026-11-19
  17. VAE Rhythm: Temporal Decoding Traces for AI-Generated Video Detection 1 upvotes, #17 of 2026-11-19
  18. Thinking Harder Doesn't Lead to Better Choices: Reasoning Effort Increases the Confidence but Not the Correctness of LLM Shopping Agents 1 upvotes, #17 of 2026-11-19
  19. A Foundation Model to Measure and Predict Human Behaviour 1 upvotes, #17 of 2026-11-19
  20. Out of Sight, Still in Mind: Token Compression for Omni-LLMs 0 upvotes, #20 of 2026-11-19
  21. NexSight: Verifiable Tasks for Fine-Grained Agentic Long-Video Understanding 0 upvotes, #20 of 2026-11-19
  22. PReMind: When Personal Memory Meets Visual Hazards 0 upvotes, #20 of 2026-11-19
  23. RoughCut-Bench: A Benchmark for Automatic Video Rough-Cut with Large Vision-Language Models 0 upvotes, #20 of 2026-11-19
  24. Late Entry in Looped Language Models 0 upvotes, #20 of 2026-11-19
  25. DrawScore: Evaluating Generated CAD Models against Engineering Drawings 0 upvotes, #20 of 2026-11-19

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.