7 papers
SelfWAM: A Self-Grounded Unified World Action Model for Fast Robot Control
Bikang Pan, Fan Liu, Haotao Lu +2
World Action Models (WAMs) improve robot policy learning by jointly modeling actions and future observations. However, conditioning future prediction only on the task prompt and ob…
Sample-Efficient Diffusion-based Reinforcement Learning with Critic Guidance
Shutong Ding, Zejia Zhong, Zhongyi Wang +4
Recent advances in reinforcement learning (RL) have achieved great successes by leveraging the multimodality and exploration capability of diffusion policies. Among these approache…
NLPrompt: Noise-Label Prompt Learning for Vision-Language Models
Bikang Pan, Qun Li, Xiaoying Tang +6
The emergence of vision-language foundation models, such as CLIP, has revolutionized image-text representation, enabling a broad range of applications via prompt learning. Despite…
FLEx: Personalized Federated Learning for Mixture-of-Experts LLMs via Expert Grafting
Fan Liu, Bikang Pan, Zhongyi Wang +4
Federated instruction tuning of large language models (LLMs) is challenged by significant data heterogeneity across clients, demanding robust personalization. The Mixture of Expert…
Multi-modal Multi-platform Person Re-Identification: Benchmark and Method
Ruiyang Ha, Songyi Jiang, Bin Li +6
Conventional person re-identification (ReID) research is often limited to single-modality sensor data from static cameras, which fails to address the complexities of real-world sce…
Two-Stage Optimization for Efficient V2G Coordination in Distribution Power System
Pengchao Tian, Siqi Yan, Bikang Pan +1
With the growing popularity of electric vehicles (EVs), maintaining power grid stability has become a significant challenge. To address this issue, EV scheduling control strategies…