Yansong Tang

VARestorer: One-Step VAR Distillation for Real-World Image Super-Resolution

AgentMath: Empowering Mathematical Reasoning for Large Language Models via Tool-Augmented Agent

SoftPose: Learning Soft Attention for Interaction-Aware Multi-Person Image Generation

Sparse-Art: Enabling Interactable Articulated Objects from Unposed Sparse-View Input

MVP: Memory-enhanced Vision-Language-Action Policy with Feedback Learning

SparseCodeQ: Extreme Sparse Coding Quantization for Large Vision-Language Models

Directly Aligning the Full Diffusion Trajectory with Semantic Relative Preference Optimization

WizardMath: Empowering Mathematical Reasoning for Large Language Models via Reinforced Evol-Instruct

DreamLight: Towards Harmonious and Consistent Image Relighting

InstaRevive: One-Step Image Enhancement via Dynamic Score Matching

ThinkBot: Embodied Instruction Following with Thought Chain Reasoning

Coarse Correspondences Boost 3D Spacetime Understanding in Multimodal Language Model

Accelerate Quantization Aware Training for Diffusion Models with Difficulty-aware Time Allocation

VIDEOGUARD: PROTECTING VIDEO CONTENT FROM UNAUTHORIZED EDITING

AnyBimanual: Transferring Single-arm Policy for General Bimanual Manipulation

OpenCarbonEval: How much $CO_2$ will your large model exhale in training process?