activity
20222026
most citedStackFLOW: Monocular Human-Object Reconstruction by Stacked Normalizing Flow with Offset

4 citations · 8 across the 26 of their papers we have counts for

collaborators
Showing cs.LGShow all

9 papers · 1 filter

cs.LG2026

GenPO++: Generative Policy Optimization with Jacobian-free Likelihood Ratios

Ke Hu, Shutong Ding, Panxin Tao +2

Generative policies provide expressive and multimodal action distributions, making them attractive for reinforcement learning (RL) in complex continuous-control tasks. Among them,…

cs.LG2026

Conformal Reliability: A New Evaluation Metric for Conditional Generation

Yachen Gao, Xinwei Sun, Yikai Wang +4

Conditional generative models have recently achieved remarkable success in various applications. However, a suitable metric for evaluating the reliability of these models, which ta…

cs.LG2025

GenPO: Generative Diffusion Models Meet On-Policy Reinforcement Learning

Shutong Ding, Ke Hu, Shan Zhong +5

Recent advances in reinforcement learning (RL) have demonstrated the powerful exploration capabilities and multimodality of generative diffusion-based policies. While substantial p…

cs.LG2024

Diffusion-based Reinforcement Learning via Q-weighted Variational Policy Optimization

Shutong Ding, Ke Hu, Zhenhao Zhang +5

Diffusion models have garnered widespread attention in Reinforcement Learning (RL) for their powerful expressiveness and multimodality. It has been verified that utilizing diffusio…

cs.LG2024

Harmonizing Generalization and Personalization in Federated Prompt Learning

Tianyu Cui, Hongxia Li, Jingya Wang +1

Federated Prompt Learning (FPL) incorporates large pre-trained Vision-Language models (VLM) into federated learning through prompt tuning. The transferable representations and rema…

cs.LG20241 cited

Global and Local Prompts Cooperation via Optimal Transport for Federated Learning

Hongxia Li, Wei Huang, Jingya Wang +1

Prompt learning in pretrained visual-language models has shown remarkable flexibility across various downstream tasks. Leveraging its inherent lightweight nature, recent research a…