Li Dong

VibeVoice: Expressive Podcast Generation with Next-Token Diffusion

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

Sparse Attention Adaptation for Long Reasoning

Multimodal Latent Language Modeling with Next-Token Diffusion

BitNet Distillation

Rectified Sparse Attention for Efficient Long-Sequence Generation

WildLong: Synthesizing Realistic Long-Context Instruction Data at Scale

Breaking Training Bottlenecks: Effective Reinforcement Learning for Modern Coding Models

Data Efficacy for Language Model Training

Demystifying Numerosity in Diffusion Models — Limitations and Remedies

Towards Stable and Effective Reinforcement learning for Mixture-of-Experts

DocReward: A Document Reward Model for Structuring and Stylizing

Thinking Augmented Pre-training

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

On-Policy RL with Optimal Reward Baseline

Information-Preserving Reformulation of Reasoning Traces for Antidistillation

Data Selection via Optimal Control for Language Models

Differential Transformer

Think Only When You Need with Large Hybrid-Reasoning Models

Semi-Parametric Retrieval via Binary Bag-of-Tokens Index

Self-Boosting Large Language Models with Synthetic Preference Data

Scaling Laws of Synthetic Data for Language Model

Reward Reasoning Models

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

Synthetic Data (Almost) from Scratch: Generalized Instruction Tuning for Language Models