Li Dong

unilm's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

authored 6 papers 10 days ago

Benefits and Pitfalls of Reinforcement Learning for Language Model Planning: A Theoretical Perspective

Paper • 2509.22613 • Published Sep 26 • 9

DocReward: A Document Reward Model for Structuring and Stylizing

Paper • 2510.11391 • Published 28 days ago • 26

Information-Preserving Reformulation of Reasoning Traces for Antidistillation

Paper • 2510.11545 • Published 27 days ago • 1

BitNet Distillation

Paper • 2510.13998 • Published 25 days ago • 52

Latent Sketchpad: Sketching Visual Thoughts to Elicit Multimodal Reasoning in MLLMs

Paper • 2510.24514 • Published 13 days ago • 20

The Era of Agentic Organization: Learning to Organize with Language Models

Paper • 2510.26658 • Published 10 days ago • 23

upvoted 3 papers 10 days ago

The Era of Agentic Organization: Learning to Organize with Language Models

Paper • 2510.26658 • Published 10 days ago • 23

The Principles of Diffusion Models

Paper • 2510.21890 • Published 17 days ago • 52

The Tool Decathlon: Benchmarking Language Agents for Diverse, Realistic, and Long-Horizon Task Execution

Paper • 2510.25726 • Published 11 days ago • 44

upvoted 3 papers 17 days ago

Every Attention Matters: An Efficient Hybrid Architecture for Long-Context Reasoning

Paper • 2510.19338 • Published 19 days ago • 110

Pico-Banana-400K: A Large-Scale Dataset for Text-Guided Image Editing

Paper • 2510.19808 • Published 18 days ago • 28

AdaSPEC: Selective Knowledge Distillation for Efficient Speculative Decoders

Paper • 2510.19779 • Published 18 days ago • 58

liked a dataset 19 days ago

HuggingFaceFW/finewiki

Viewer • Updated 19 days ago • 61.6M • 18.5k • 235

upvoted 2 papers 19 days ago

BitNet Distillation

Paper • 2510.13998 • Published 25 days ago • 52

FineVision: Open Data Is All You Need

Paper • 2510.17269 • Published 21 days ago • 63

upvoted a paper 20 days ago

QueST: Incentivizing LLMs to Generate Difficult Problems

Paper • 2510.17715 • Published 20 days ago • 32

upvoted 2 papers 26 days ago

Webscale-RL: Automated Data Pipeline for Scaling RL Data to Pretraining Levels

Paper • 2510.06499 • Published Oct 7 • 31

DocReward: A Document Reward Model for Structuring and Stylizing

Paper • 2510.11391 • Published 28 days ago • 26

upvoted 2 papers about 1 month ago

Fast-dLLM v2: Efficient Block-Diffusion LLM

Paper • 2509.26328 • Published Sep 30 • 51

Less is More: Recursive Reasoning with Tiny Networks

Paper • 2510.04871 • Published Oct 6 • 468