Trendoday
Hugging FaceArchive · daily

HF Daily Papers on October 23, 2026

On October 23, 2026, Trendoday checked HF Daily Papers 12 times and recorded 71 different entries. “Making MLLM Latents Matter: Factor-Aware Predictive…” ranked highest over the day: on the list in 92% of checks, best #1, average #3.9. “Policy-Mask: Budget-Aware Adaptation of Diffusion Features…” and “Deep Search in Real-World Web Environments” followed. 0 entries were on the list at every check. 42 entries made their first appearance, led by “Making MLLM Latents Matter: Factor-Aware Predictive…”.

  1. 1
    92%of checks
  2. 2
    92%of checks
  3. 3
    83%of checks
  4. 4
    92%of checks
  5. 5
    83%of checks
  6. 6
    92%of checks
  7. 7
    75%of checks
  8. 8
    75%of checks
  9. 9
    83%of checks
  10. 10
    67%of checks
  11. 11
    75%of checks
  12. 12
    67%of checks
  13. 13
    75%of checks
  14. 14
    83%of checks
  15. 15
    75%of checks
  16. 16
    83%of checks
  17. 17
    83%of checks
  18. 18
    83%of checks
  19. 19
    75%of checks
  20. 20
    83%of checks
  21. 21
    67%of checks
  22. 22
    83%of checks
  23. 23
    50%of checks
  24. 24
    83%of checks
  25. 25
    67%of checks
  26. 26
    75%of checks
  27. 27
    58%of checks
  28. 28
    58%of checks
  29. 29
    33%of checks
  30. 30
    25%of checks
  31. 31
    25%of checks
  32. 32
    42%of checks
  33. 33
    50%of checks
  34. 34
    33%of checks
  35. 35
    25%of checks
  36. 36
    25%of checks
  37. 37
    33%of checks
  38. 38
    17%of checks
  39. 39
    25%of checks
  40. 40
    17%of checks
  41. 41
    25%of checks
  42. 42
    17%of checks
  43. 43
    17%of checks
  44. 44
    25%of checks
  45. 45
    33%of checks
  46. 46
    25%of checks
  47. 47
    17%of checks
  48. 48
    25%of checks
  49. 49
    17%of checks
  50. 50
    17%of checks

Also on the list that day (21)

Building AI Research Teams for Autonomous Discovery of Linear… · Language Models Learn to Improve Language Models · Automating ML for Science: Can Frontier Agents Climb Scientific… · Entertain, then Cancel: How Thinking Makes Reasoning Models Read… · SpatialBrain: Spatial Intelligence Growing from Experience · Qwen-Audio-3.1-ASR Technical Report · ToM2Vec: Continuous Theory-of-Mind Tokens for Multi-Agent Coordination · StreamEval: Evaluating Interactive Streaming Video Generation Models · Think Harder Where It Matters: Item-Level Adaptive Recursion for… · Spectral-Spatial Interpretation · Evolving with Open Worlds: Towards Recursive Self-Improvement for… · Reading, Writing, Sharing, and Interacting with the World through… · SCOPE: Compiling Natural-Language Policies into Neurosymbolic… · Socratic Skill Learning: Interleaving Teaching and Practice for… · AgenticRoboRL: Bringing Coding-Agent Post-Training to Agentic Robotics · Memory-Centric Continual Learning for AI Agents · CulturalRiddles: A Multicultural Benchmark of Riddles · Sparsity Should Be ALLOTted by Output: Training-Free Allocation of… · Real In, Real Out: What If We Only Use Real Data for Scene Text… · Answering in the User's Variety: Calibrated Accommodation Pairs for… · Looped Uniform Diffusion Language Models

Ordered by average position weighted by how often the entry was on the list that day. Ranks are UTC days. All HF Daily Papers archives

Part of week 43 and October 2026.