Hanwang Zhang

Benchmarking Open-Set Recognition Beyond Vision-Language Pre-training

Streaming Drag-Oriented Interactive Video Manipulation: Drag Anything, Anytime!

Reducing Class-Wise Performance Disparity via Margin Regularization

Real-Time Motion-Controllable Autoregressive Video Diffusion

Look Carefully: Adaptive Visual Reinforcements in Multimodal Large Language Models for Hallucination Mitigation

Generative Distribution Distillation

On Path to Multimodal Generalist: General-Level and General-Bench

Enhancing CLIP Robustness via Cross-Modality Alignment

Selftok-Zero: Reinforcement Learning for Visual Generation via Discrete and Autoregressive Visual Tokens

$\mathcal{V}ista\mathcal{DPO}$: Video Hierarchical Spatial-Temporal Direct Preference Optimization for Large Video Models

Co-Reinforcement Learning for Unified Multimodal Understanding and Generation

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

Towards Semantic Equivalence of Tokenization in Multimodal LLM

VR-Sampling: Accelerating Flow Generative Model Training with Variance Reduction Sampling

Learning to Animate Images from A Few Videos to Portray Delicate Human Actions

3D Question Answering via only 2D Vision-Language Models

Geo-3DGS: Multi-view Geometry Consistency for 3D Gaussian Splatting and Surface Reconstruction

Ca2-VDM: Efficient Autoregressive Video Diffusion Model with Causal Generation and Cache Sharing

Object Fusion via Diffusion Time-step for Customized Image Editing with Single Example

Towards Debiased Source-Free Domain Adaptation

A Closer Look at Time Steps is Worthy of Triple Speed-Up for Diffusion Model Training