Shanghang Zhang

SimpleVLA-RL: Scaling VLA Training via Reinforcement Learning

SpikePingpong: Spike Vision-based Fast-Slow Pingpong Robot System

BranchGRPO: Stable and Efficient GRPO with Structured Branching in Diffusion Models

XR-1: Towards Versatile Vision-Language-Action Models via Learning Unified Vision-Motion Representations

HumanoidVerse: A Versatile Humanoid for Vision-Language Guided Multi-Object Rearrangement

WristWorld: Generating Wrist-Views via 4D World Models for Robotic Manipulation

SpikeGen: Decoupled “Rods and Cones” Visual Representation Processing with Latent Generative Framework

From Language to Locomotion: Retargeting-free Humanoid Control via Motion Latent Guidance

ZoomV: Temporal Zoom-in for Efficient Long Video Understanding

MC-LLaVA: Multi-Concept Personalized Vision-Language Model

HybridVLA: Collaborative Diffusion and Autoregression in a Unified Vision-Language-Action Model

OmniSAT: Compact Action Token, Faster Auto Regression

dVLA: Diffusion Vision-Language-Action Model with Multimodal Chain-of-Thought

WoW: Scaling Embodied Omni-World Model For Generalizable Manipulation Simulation

Robobench: A Comprehensive Evaluation Benchmark For Multimodal Large Language Models as Embodied Brain

FractalFold: Towards Fractal Structure Modeling for Hierarchical Inverse Protein Folding

Can World Models Benefit VLMs for World Dynamics?

PoseDiff: A Unified Diffusion Model Bridging Robot Pose Estimation and Video-to-Action Control

T-REX: Mixture-of-Rank-One-Experts with Semantic-aware Intuition for Multi-task Large Language Model Finetuning

Beyond Attention or Similarity: Maximizing Conditional Diversity for Token Pruning in MLLMs

RoboRefer: Towards Spatial Referring with Reasoning in Vision-Language Models for Robotics

Co$^{\mathbf{3}}$Gesture: Towards Coherent Concurrent Co-speech 3D Gesture Generation with Interactive Diffusion

Orochi: Versatile Biomedical Image Processor

Fast-in-Slow: A Dual-System VLA Model Unifying Fast Manipulation within Slow Reasoning

URDF-Anything: Constructing Articulated Objects with 3D Multimodal Language Model

SEEA-R1: Tree-Structured Reinforcement Fine-Tuning for Self-Evolving Embodied Agents

MAVIS: Mathematical Visual Instruction Tuning with an Automatic Data Engine

Reason-RFT: Reinforcement Fine-Tuning for Visual Reasoning of Vision Language Models

AC-DiT: Adaptive Coordination Diffusion Transformer for Mobile Manipulation

Uni-Map: Unified Camera-LiDAR Perception for Robust HD Map Construction

EmpathyRobot: A Dataset and Benchmark for Empathetic Task Planning of Robotic Agent

HybridVLA: Collaborative Autoregression and Diffusion in a Unified Vision-Language-Action Model

EVA: An Embodied World Model for Future Video Anticipation

Draw-and-Understand: Leveraging Visual Prompts to Enable MLLMs to Comprehend What You Want

OmniArch: Building Foundation Model for Scientific Computing

SAN: Hypothesizing Long-Term Synaptic Development and Neural Engram Mechanism in Scalable Model's Parameter-Efficient Fine-Tuning

Empowering World Models with Reflection for Embodied Video Prediction

SparseVLM: Visual Token Sparsification for Efficient Vision-Language Model Inference

CrayonRobo: Toward Generic Robot Manipulation via Crayon Visual Prompting

SparseVLM: Visual Token Sparsification for Efficient Vision Language Models Inference

Self-Corrected Multimodal Large Language Model for Robot Manipulation and Reflection

HyperAdapter: Generating Adapters for Pre-Trained Model-Based Continual Learning

Discovering Long-Term Effects on Parameter Efficient Fine-tuning

Frequency-Decoupled Cross-Modal Knowledge Distillation

ViML: A Video, Music, Language Unified Dataset for Understanding and Generation

$CoCoGesture$: Towards Coherent Co-speech 3D Gesture Generation in the Wild

PINNsAgent: Automated PDE Surrogation with Large Language Models