Xiaokang Yang

AutoBio: A Simulation and Benchmark for Robotic Automation in Digital Biology Laboratory

Dens3R: A Foundation Model for 3D Geometry Prediction

RoboTwin 2.0: A Scalable Data Generator and Benchmark with Strong Domain Randomization for Robust Bimanual Robotic Manipulation

Riesz Neural Operator for Solving Partial Differential Equations

Discrete Diffusion VLA: Bringing Discrete Diffusion to Action Decoding in Vision-Language-Action Policies

FOCUS: High-Dimensional Model-Based RL via Focused Control Unit Sampling

ReAugment: Learning to Augment Few-Shot Time Series with Model Zoo Guidance

NeoWorld: Neural Simulation of Explorable Virtual Worlds via Progressive 3D Unfolding

DVD-Quant: Data-free Video Diffusion Transformers Quantization

P-LoRA: Posterior Knowledge Enables Training-Free Fusion of Subject and Style LoRAs

ReCalKV: Low-Rank KV Cache Compression via Head Reordering and Offline Calibration

Asymmetric VAE for One-Step Video Super-Resolution Acceleration

SimTrack3D: A Simple Sequential Motion Modeling for Efficient 3D Single Object Tracking

Flow-Matching Guided Deep Unfolding for Hyperspectral Image Reconstruction

AdaSVD: Adaptive Singular Value Decomposition for Large Language Models

Expertise need not monopolize: Action-Specialized Mixture of Experts for Vision-Language-Action Learning

CLQ: Cross-Layer Guided Orthogonal-based Quantization for Diffusion Transformers

FlashEdit: Decoupling Speed, Structure, and Semantics for Precise Image Editing

Open-World Reinforcement Learning over Long Short-Term Imagination

OmniVCus: Feedforward Subject-driven Video Customization with Multimodal Control Conditions

Human Body Restoration with One-Step Diffusion Model and A New Benchmark

ARB-LLM: Alternating Refined Binarizations for Large Language Models

OPMapper: Enhancing Open-Vocabulary Semantic Segmentation with Multi-Guidance Information

HAODiff: Human-Aware One-Step Diffusion via Dual-Prompt Guidance

Unleashing the Power of One-Step Diffusion based Image Super-Resolution via a Large-Scale Diffusion Discriminator

DAWP: A framework for global observation forecasting via Data Assimilation and Weather Prediction in satellite observation space

PostEdit: Posterior Sampling for Efficient Zero-Shot Image Editing

AniSDF: Fused-Granularity Neural Surfaces with Anisotropic Encoding for High-Fidelity 3D Reconstruction

HyperET: Efficient Training in Hyperbolic Space for Multi-modal Large Language Models

Rethinking Classifier Re-Training in Long-Tailed Recognition: Label Over-Smooth Can Balance

KinFormer: Generalizable Dynamical Symbolic Regression for Catalytic Organic Reaction Kinetics

Unleashing the Power of Task-Specific Directions in Parameter Efficient Fine-tuning

Maintaining Structural Integrity in Parameter Spaces for Parameter Efficient Fine-tuning

PostCast: Generalizable Postprocessing for Precipitation Nowcasting via Unsupervised Blurriness Modeling

EvoMesh: Adaptive Physical Simulation with Hierarchical Graph Evolutions

Discovering Message Passing Hierarchies for Mesh-Based Physics Simulation

BiDRN: Binarized 3D Whole-body Human Mesh Recovery

Text-Augmented Multimodal LLMs for Chemical Reaction Condition Recommendation

Video-Enhanced Offline Reinforcement Learning: A Model-Based Approach

Bilevel Reinforcement Learning for Stock Data with A Conservative TD Ensemble

Realistic Surgical Simulation from Monocular Videos

Distillation-Free One-Step Diffusion for Real-World Image Super-Resolution

Learning Augmentation Policies from A Model Zoo for Time Series Forecasting

Image Super-Resolution with Text Prompt Diffusion

ActiveAD: Planning-Oriented Active Learning for End-to-End Autonomous Driving

DimOL: Dimensional Awareness as a New 'Dimension' in Operator Learning