Wei Xue

AudioX: A Unified Framework for Anything-to-Audio Generation

PrismAudio: Decomposed Chain-of-Thought and Multi-dimensional Rewards for Video-to-Audio Generation

YuE: Scaling Open Foundation Models for Long-Form Music Generation

TreePO: Enhancing Policy Efficacy and Inference Efficiency with Tree Modeling

Pixel-Perfect Puppetry: Precision-Guided Enhancement for Face Image and Video Editing

Style Waltz: Dancing Between Content and Style in Face Stylization

PodEval: A Multimodal Evaluation Framework for Podcast Audio Generation

UniSS: Unified Expressive Speech-to-Speech Translation with Your Voice

Reinforcement Learning for Generalized Label Aggregation

Semantic Voting: A Self-Evaluation-Free Approach for Efficient LLM Self-Improvement on Unverifiable Open-ended Tasks

WoW: Scaling Embodied Omni-World Model For Generalizable Manipulation Simulation

Audio-FLAN: An Instruction-Following Dataset for Unified Understanding and Generation of Speech, Music, and Sound

Forging a Masterpiece from Any Face: A Universal Framework for Face Stylization

SongEval: A Benchmark Dataset for Song Aesthetics Evaluation

Light-Search: Reducing Retrieval Cost in RAG via Curriculum-Based Policy Optimization

Alignment Does Matter: Enables Pure-Speech-Token Dialogue with Frozen Text LLMs

Co$^{\mathbf{3}}$Gesture: Towards Coherent Concurrent Co-speech 3D Gesture Generation with Interactive Diffusion

Both Ears Wide Open: Towards Language-Driven Spatial Audio Generation

Delta Decompression for MoE-based LLMs Compression

ThinkSound: Chain-of-Thought Reasoning in Multimodal LLMs for Audio Generation and Editing

Foundation Cures Personalization: Improving Personalized Models’ Prompt Consistency via Hidden Foundation Knowledge

MoE-SVD: Structured Mixture-of-Experts LLMs Compression via Singular Value Decomposition

OmniAudio: Generating Spatial Audio from 360-Degree Video

MuPT: A Generative Symbolic Music Pretrained Transformer

STBLLM: Breaking the 1-Bit Barrier with Structured Binary LLMs

EVA: An Embodied World Model for Future Video Anticipation

You Know What I'm Saying: Jailbreak Attack via Implicit Reference

Empowering World Models with Reflection for Embodied Video Prediction

Structured Mixture-of-Experts LLMs Compression via Singular Value Decomposition

PSHuman: Photorealistic Single-view Human Reconstruction using Cross-Scale Diffusion

AgentMonitor: A Plug-and-Play Framework for Predictive and Secure Multi-Agent Systems

VidMuse: A Simple Video-to-Music Generation Framework with Long-Short-Term Modeling

ViML: A Video, Music, Language Unified Dataset for Understanding and Generation

GuideEdit: Enhancing Face Video Editing with Fine-grained Control

NoRA: Nested Low-Rank Adaptation for Efficient Fine-Tuning Large Models

$CoCoGesture$: Towards Coherent Co-speech 3D Gesture Generation in the Wild