Zhendong Wang

Score Distillation Beyond Acceleration: Generative Modeling from Corrupted Data

Distilled Protein Backbone Generation

EdiVal-Agent: An Object-Centric Framework for Automated, Fine-Grained Evaluation of Multi-Turn Editing

STITCH: Simultaneous Thinking and Talking with Chunked Reasoning for Spoken Language Models

MV-Diffus3R: Refining Multi-View Diffusions for Geometric Coherence 3D Reconstruction

Shanks: Simultaneous Hearing and Thinking for Spoken Language Models

Guided Score identity Distillation for Data-Free One-Step Text-to-Image Generation

Improving Data Efficiency for LLM Reinforcement Fine-tuning Through Difficulty-targeted Online Data Selection and Rollout Replay

Adversarial Score identity Distillation: Rapidly Surpassing the Teacher in One Step

One-Step Diffusion Policy: Fast Visuomotor Policies via Diffusion Distillation

Relative Preference Optimization: Enhancing LLM Alignment through Contrasting Responses across Identical and Diverse Prompts

One-Step Diffusion Policy: Fast Visuomotor Policies via Diffusion Distillation

Diffusion Preference Alignment via Relative Text-Image Contrast

Self-Augmented Preference Optimization: Off-Policy Paradigms for Language Model Alignment