Zhou Zhao

SpatialHand: Generative Object Manipulation from 3D Prespective

WorldEdit: Towards Open-World Image Editing with a Knowledge-Informed Benchmark

MARS-Sep: Multimodal-Aligned Reinforced Sound Separation

Depth Anything with Any Prior

Figma2Code: Automating Multimodal Design to Code in the Wild

Vox-Infinity: Benchmarking the Limits of Long-Context Spoken Language Models

AlignSep: Temporally-Aligned Video-Queried Sound Separation with Flow Matching

CIAR: Interval-based Collaborative Decoding for Image Generation Acceleration

WavReward: Spoken Dialogue Models With Generalist Reward Evaluators

ETC: training-free diffusion models acceleration with Error-aware Trend Consistency

PSR: Subject-Consistency Rewards for Multi-Subject Personalized Generation

DSI-Bench: A Benchmark for Dynamic Spatial Intelligence

Keep Refining Your Discrete Diffusion Model: A Mixture of Absorbing and Uniform Processes

OmniChat: Enhancing Spoken Dialogue Systems with Scalable Synthetic Data for Diverse Scenarios

ACDC: Adaptive Cloud-Device Collaboration for Efficient and Accurate Semantic Segmentation

Orient Anything V2: Unifying Orientation and Rotation Understanding

SPMDM: Enhancing Masked Diffusion Models through Simplifing Sampling Path

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

OmniAudio: Generating Spatial Audio from 360-Degree Video

VoxDialogue: Can Spoken Dialogue Systems Understand Information Beyond Words?

EcoFace: Audio-Visual Emotional Co-Disentanglement Speech-Driven 3D Talking Face Generation

WavTokenizer: an Efficient Acoustic Discrete Codec Tokenizer for Audio Language Modeling

Vinci: Deep Thinking in Text-to-Image Generation using Unified Model with Reinforcement Learning

OmniBind: Large-scale Omni Multimodal Representation via Binding Spaces

OmniSep: Unified Omni-Modality Sound Separation with Query-Mixup

Sparse Alignment Enhanced Latent Diffusion Transformer for Zero-Shot Speech Synthesis

MuVi: Video-to-Music Generation with Semantic Alignment and Rhythmic Synchronization

Dataflow-Guided Neuro-Symbolic Language Models for Type Inference

Orient Anything: Learning Robust Object Orientation Estimation from Rendering 3D Models

ControlSpeech: Towards Simultaneous Zero-shot Speaker Cloning and Zero-shot Language Style Control

T2A-Feedback: Improving Basic Capabilities of Text-to-Audio Generation via Fine-grained AI Feedback

OmniChat: Enhancing Spoken Dialogue Systems with Scalable Synthetic Data for Diverse Scenarios

IRBridge: Solving Image Restoration Bridge with Pre-trained Generative Diffusion Models

CodeSync: Synchronizing Large Language Models with Dynamic Code Evolution at Scale

AVSET-10M: An Open Large-Scale Audio-Visual Dataset with High Correspondence

Analyzing and Mitigating Inconsistency in Discrete Audio Tokens for Neural Codec Language Models

Noise-Robust Audio-Visual Speech-Driven Body Language Synthesis

Advancing Multimodal Unified Discrete Representations

MultiBand: Multi-Task Song Generation with Personalized Prompt-Based Control

Controllable Text-to-Speech Synthesis with Masked-Autoencoded Style Representation

MEDIC: Zero-shot Music Editing with Disentangled Inversion Control

Fox-TTS: Scalable Flow Transformers for Expressive Zero-Shot Text to Speech

MindLoc: A Secure Brain-Based System for Object Localization