Zheng Zhu

Scalable Training for Vector-Quantized Networks with 100% Codebook Utilization

ReconDreamer-RL: Enhancing Reinforcement Learning via Diffusion-based Scene Reconstruction

R2RGEN: Real-to-Real 3D Data Generation for Spatially Generalized Manipulation

Motion-R1: Enhancing Motion Generation with Decomposed Chain-of-Thought and RL Binding

One Graph Can Generalize: Graph-guided Structural Transfer for Source-free Open-set Domain-adaptive Object Detection

DD-Ranking: Rethinking the Evaluation of Dataset Distillation

GigaVideo-1: Advancing Video Generation via Automatic Feedback with 4 GPU-Hours Fine-Tuning

MoRe4D: Joint 3D Motion Generation and Geometry Reconstruction for 4D Synthesis from a Single Image

RADAR: A Risk-Aware Dynamic Multi-Agent Framework for LLM Safety Evaluation via Role-Specialized Collaboration

Erased, But Not Forgotten: Erased Rectified Flow Transformers Still Remain Unsafe Under Concept Attack

EgoDemoGen: Novel Egocentric Demonstration Generation Enables Viewpoint-Robust Manipulation

WonderFree: Enhancing 3D World Generation via Video Diffusion Prior with Multi-view Consistency

RoboTransfer: Geometry-Consistent Video Diffusion for Robotic Visual Policy Transfer

MimicDreamer: Aligning Human and Robot Demonstrations for Scalable VLA Training

EMMA: Generalizing Real-World Robot Manipulation via Generative Visual Transfer

Anchor-Guided Behavior Cloning with Offline Reinforcement Learning for Robust Autonomous Driving

ResearchGPT: Benchmarking and Training LLMs for End-to-End Computer Science Research Workflows

MambaMatch: SLAM Front-End Feature Matching with State Space Models

Pruning-Robust Mamba with Asymmetric Multi-Scale Scanning Paths

OpenStereo: A Comprehensive Benchmark for Stereo Matching and Strong Baseline