PPaperPicks

Ye Shi

ShanghaiTech University, School of Information Science Technology, Shanghai, China

21 papers at tracked venues · 21 at CORE A* · active 20242026

Venues

Frequent coauthors

Papers

  1. One-Step Generative Policies with Q-Learning: A Reformulation of MeanFlow
  2. AffordDP: Generalizable Diffusion Policy with Transferable Affordance
  3. FreqPolicy: Frequency Autoregressive Visuomotor Policy with Continuous Tokens
  4. GenPO: Generative Diffusion Models Meet On-Policy Reinforcement Learning
  5. NLPrompt: Noise-Label Prompt Learning for Vision-Language Models
  6. OpenHOI: Open-World Hand-Object Interaction Synthesis with Multimodal Large Language Model
  7. SeqAfford: Sequential 3D Affordance Reasoning via Multimodal Large Language Model
  8. Towards Immersive Human-X Interaction: A Real-Time Framework for Physically Plausible Motion Synthesis
  9. UniDB: A Unified Diffusion Bridge Framework via Stochastic Optimal Control
  10. A Unified Diffusion Framework for Scene-aware Human Motion Estimation from Sparse Signals
  11. Diffusion-based Reinforcement Learning via Q-weighted Variational Policy Optimization
  12. Federated Learning from Vision-Language Foundation Models: Theoretical Analysis and Method
  13. Global and Local Prompts Cooperation via Optimal Transport for Federated Learning
  14. Guidance with Spherical Gaussian Constraint for Conditional Diffusion
  15. HOI-M3: Capture Multiple Humans and Objects Interaction within Contextual Environment
  16. Harmonizing Generalization and Personalization in Federated Prompt Learning
  17. HybridGait: A Benchmark for Spatial-Temporal Cloth-Changing Gait Recognition with Hybrid Explorations
  18. Monocular Human-Object Reconstruction in the Wild
  19. Understanding Convergence and Generalization in Federated Learning through Feature Learning Theory
  20. Understanding Representation of Deep Equilibrium Models from Neural Collapse Perspective
  21. Unsupervised Cross-Domain Image Retrieval via Prototypical Optimal Transport