Zhixiong Huang — accepted AI-conference papers

2025

DTOS: Dynamic Time Object Sensing with Large Multimodal Model

Jirui Tian, Jinrong Zhang, Shenglan Liu, Luhao Xu, Zhixiong Huang, Gao Huang

CVPR 2025poster

Existing multimodal large language models (MLLMs) face significant challenges in Referring Video Object Segmentation(RVOS). We identify three critical challenges: (C1) insufficient quantitative representation of textual numerical data, (C2) repetitive and degraded response templates for spatiotempor…

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗

2024

Langevin Policy for Safe Reinforcement Learning

Fenghao Lei, Long Yang, Shiting Wen, Zhixiong Huang, Zhiwang Zhang, Chaoyi Pang

ICML 2024poster

Optimization and sampling based algorithms are two branches of methods in machine learning, while existing safe reinforcement learning (RL) algorithms are mainly based on optimization, it is still unclear whether sampling based methods can lead to desirable performance with safe policy. This paper f…

Cited by 1 Source ↗PDF ↗Scholar ↗