Li Dong

unilm's activity

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

authored 6 papers 2 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 20 days ago • 26

Information-Preserving Reformulation of Reasoning Traces for Antidistillation

Paper • 2510.11545 • Published 20 days ago • 1

BitNet Distillation

Paper • 2510.13998 • Published 18 days ago • 52

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

Paper • 2510.24514 • Published 5 days ago • 20

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

Paper • 2510.26658 • Published 3 days ago • 21

authored 2 papers about 1 month ago

AdaPrompt: Adaptive Model Training for Prompt-based NLP

Paper • 2202.04824 • Published Feb 10, 2022

Thinking Augmented Pre-training

Paper • 2509.20186 • Published Sep 24 • 23

authored 4 papers 2 months ago

SeerAttention-R: Sparse Attention Adaptation for Long Reasoning

Paper • 2506.08889 • Published Jun 10 • 23

Model as a Game: On Numerical and Spatial Consistency for Generative Games

Paper • 2503.21172 • Published Mar 27

Data Efficacy for Language Model Training

Paper • 2506.21545 • Published Jun 26 • 11

VibeVoice Technical Report

Paper • 2508.19205 • Published Aug 26 • 123

authored 4 papers 5 months ago

Think Only When You Need with Large Hybrid-Reasoning Models

Paper • 2505.14631 • Published May 20 • 20

On-Policy RL with Optimal Reward Baseline

Paper • 2505.23585 • Published May 29 • 14

Rectified Sparse Attention

Paper • 2506.04108 • Published Jun 4 • 10

Reinforcement Pre-Training

Paper • 2506.08007 • Published Jun 9 • 262

authored 4 papers 6 months ago

Imagine while Reasoning in Space: Multimodal Visualization-of-Thought

Paper • 2501.07542 • Published Jan 13 • 3

Zero-shot Cross-lingual Transfer of Neural Machine Translation with Multilingual Pretrained Encoders

Paper • 2104.08757 • Published Apr 18, 2021

WildLong: Synthesizing Realistic Long-Context Instruction Data at Scale

Paper • 2502.16684 • Published Feb 23 • 1

Scaling Laws of Synthetic Data for Language Models

Paper • 2503.19551 • Published Mar 25 • 1