Yang Zhou

29

Papers

264

Total Citations

Papers (29)

FedASMU: Efficient Asynchronous Federated Learning with Dynamic Staleness-Aware Model Update

Aether: Geometric-Aware Unified World Modeling

SmartRefine: A Scenario-Adaptive Refinement Framework for Efficient Motion Prediction

HiSplat: Hierarchical 3D Gaussian Splatting for Generalizable Sparse-View Reconstruction

The Curse of Multi-Modalities: Evaluating Hallucinations of Large Multimodal Models across Language, Visual, and Audio

Attention Distillation: A Unified Approach to Visual Characteristics Transfer

In-Hand 3D Object Reconstruction from a Monocular RGB Video

Visual Persona: Foundation Model for Full-Body Human Customization

Self-Evolutionary Large Language Models Through Uncertainty-Enhanced Preference Optimization

DMesh++: An Efficient Differentiable Mesh for Complex Shapes

ShotVL: Human-Centric Highlight Frame Retrieval via Language Queries

Bridging Symmetry and Robustness: On the Role of Equivariance in Enhancing Adversarial Robustness

NeurIPS 2025arXiv

Describe, Adapt and Combine: Empowering CLIP Encoders for Open-set 3D Object Retrieval

PAC-Bayes Bounds for Multivariate Linear Regression and Linear Autoencoders

Free-viewpoint Human Animation with Pose-correlated Reference Selection

HexGen: Generative Inference of Large Language Model over Heterogeneous Environment

Move-in-2D: 2D-Conditioned Human Motion Generation

VideoGigaGAN: Towards Detail-rich Video Super-Resolution

VEGGIE: Instructional Editing and Reasoning Video Concepts with Grounded Generation

Video Motion Graphs

Visual Textualization for Image Prompted Object Detection

Instance-Level Video Depth in Groups Beyond Occlusions

Privacy-Preserving V2X Collaborative Perception Integrating Unknown Collaborators

Treasures in Discarded Weights for LLM Quantization

Tuning Stable Rank Shrinkage: Aiming at the Overlooked Structural Risk in Fine-tuning

Deformable One-shot Face Stylization via DINO Semantic Guidance

Leveraging Frame Affinity for sRGB-to-RAW Video De-rendering

Generating Non-Stationary Textures using Self-Rectification

Effective Federated Graph Matching