Shaohan Huang

VibeVoice: Expressive Podcast Generation with Next-Token Diffusion

VisCodex: Unified Multimodal Code Generation via Merging Vision and Coding Models

Code Aesthetics with Agentic Reward Feedback

Multimodal Latent Language Modeling with Next-Token Diffusion

Geometric-Mean Policy Optimization

BitNet Distillation

Breaking Training Bottlenecks: Effective Reinforcement Learning for Modern Coding Models

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

DocReward: A Document Reward Model for Structuring and Stylizing

Thinking Augmented Pre-training

Learning to Refine: Self-Refinement of Parallel Reasoning in LLMs

Efficient RL Training for Reasoning Models via Length-Aware Optimization

On-Policy RL with Optimal Reward Baseline

Think Only When You Need with Large Hybrid-Reasoning Models

Reward Reasoning Models

E5-V: Universal Embeddings with Multimodal Large Language Models

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

MoRA: High-Rank Updating for Parameter-Efficient Fine-Tuning

Textual Aesthetics in Large Language Models