Wei Tang

9

Papers

41

Total Citations

Papers (9)

Towards Generalizable Multi-Object Tracking

FlowRAM: Grounding Flow Matching Policy with Region-Aware Mamba Framework for Robotic Manipulation

The Rise of Parameter Specialization for Knowledge Storage in Large Language Models

NeurIPS 2025arXiv

SAMPO: Scale-wise Autoregression with Motion Prompt for Generative World Models

Fast Multi-Instance Partial-Label Learning

Learning Partonomic 3D Reconstruction from Image Collections

Performative Prediction with Bandit Feedback: Learning through Reparameterization

Towards Precise Embodied Dialogue Localization via Causality Guided Diffusion

PDFactor: Learning Tri-Perspective View Policy Diffusion Field for Multi-Task Robotic Manipulation