Li Dong

Li Dong on Hugging Face Daily Papers: 44 papers, 12 in the top 3 of their day, 2,603 upvotes.

  1. Agensh: Scaling Organizational Intelligence to 1,024 Agents 27 upvotes, #12 of 2026-09-23
  2. VibeVoice-ASR-Streaming Technical Report 17 upvotes, #16 of 2026-09-03
  3. Multi-Turn On-Policy Distillation with Prefix Replay 12 upvotes, #14 of 2026-07-24
  4. LLM-as-a-Coach: Experiential Learning for Non-Verifiable Tasks 14 upvotes, #19 of 2026-07-21
  5. Universal YOCO for Efficient Depth Scaling 17 upvotes, #13 of 2026-04-02
  6. Online Experiential Learning for Language Models 55 upvotes, #10 of 2026-03-18
  7. Sparse-BitNet: 1.58-bit LLMs are Naturally Friendly to Semi-Structured Sparsity 4 upvotes, #27 of 2026-03-10
  8. Breaking Training Bottlenecks: Effective and Stable Reinforcement Learning for Coding Models 5 upvotes, #24 of 2026-03-10
  9. VIBEVOICE-ASR Technical Report 19 upvotes, #11 of 2026-01-27
  10. LLM-in-Sandbox Elicits General Agentic Intelligence 82 upvotes, #2 of 2026-01-23
  11. Multiplex Thinking: Reasoning via Token-wise Branch-and-Merge 38 upvotes, #2 of 2026-01-20
  12. Black-Box On-Policy Distillation of Large Language Models 39 upvotes, #4 of 2025-11-14
  13. The Era of Agentic Organization: Learning to Organize with Language Models 23 upvotes, #11 of 2025-10-31
  14. Latent Sketchpad: Sketching Visual Thoughts to Elicit Multimodal Reasoning in MLLMs 20 upvotes, #14 of 2025-10-29
  15. BitNet Distillation 47 upvotes, #8 of 2025-10-17
  16. Information-Preserving Reformulation of Reasoning Traces for Antidistillation 1 upvotes, #38 of 2025-10-15
  17. DocReward: A Document Reward Model for Structuring and Stylizing 26 upvotes, #12 of 2025-10-14
  18. Benefits and Pitfalls of Reinforcement Learning for Language Model Planning: A Theoretical Perspective 7 upvotes, #33 of 2025-10-01
  19. Thinking Augmented Pre-training 22 upvotes, #9 of 2025-09-26
  20. VibeVoice Technical Report 118 upvotes, #1 of 2025-08-27
  21. Data Efficacy for Language Model Training 10 upvotes, #9 of 2025-07-02
  22. SeerAttention-R: Sparse Attention Adaptation for Long Reasoning 24 upvotes, #8 of 2025-06-12
  23. Reinforcement Pre-Training 209 upvotes, #1 of 2025-06-10
  24. Rectified Sparse Attention 10 upvotes, #19 of 2025-06-05
  25. On-Policy RL with Optimal Reward Baseline 14 upvotes, #25 of 2025-05-30
  26. Think Only When You Need with Large Hybrid-Reasoning Models 18 upvotes, #11 of 2025-05-21
  27. Reward Reasoning Model 32 upvotes, #5 of 2025-05-21
  28. Multimodal Latent Language Modeling with Next-Token Diffusion 38 upvotes, #5 of 2024-12-13
  29. Self-Boosting Large Language Models with Synthetic Preference Data 14 upvotes, #15 of 2024-10-10
  30. Data Selection via Optimal Control for Language Models 8 upvotes, #26 of 2024-10-10
  31. Differential Transformer 148 upvotes, #1 of 2024-10-08
  32. Direct Preference Knowledge Distillation for Large Language Models 21 upvotes, #3 of 2024-07-01
  33. The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits 630 upvotes, #1 of 2024-02-28
  34. Towards Optimal Learning of Language Models 18 upvotes, #10 of 2024-02-28
  35. Synthetic Data (Almost) from Scratch: Generalized Instruction Tuning for Language Models 52 upvotes, #2 of 2024-02-21
  36. BitNet: Scaling 1-bit Transformers for Large Language Models 108 upvotes, #1 of 2023-10-18
  37. Kosmos-2.5: A Multimodal Literate Model 56 upvotes, #4 of 2023-09-21
  38. Large Language Model for Science: A Study on P vs. NP 22 upvotes, #4 of 2023-09-13
  39. Retentive Network: A Successor to Transformer for Large Language Models 173 upvotes, #1 of 2023-07-18
  40. LongNet: Scaling Transformers to 1,000,000,000 Tokens 82 upvotes, #2 of 2023-07-06
  41. Kosmos-2: Grounding Multimodal Large Language Models to the World 36 upvotes, #1 of 2023-06-27
  42. Knowledge Distillation of Large Language Models 24 upvotes, #5 of 2023-06-16
  43. Augmenting Language Models with Long-Term Memory 19 upvotes, #4 of 2023-06-13
  44. Pre-Training to Learn in Context 2 upvotes, #8 of 2023-05-17

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.