From the 1 of 10 linked papers with an AI index.
10 papers
Look, Focus, Act: Efficient and Robust Robot Learning via Human Gaze and Foveated Vision Transformers
Ian Chuang, Jinyu Zou, Andrew Lee +2
The paper introduces GIAVA, a robot vision system that incorporates human-like gaze and foveated processing into Vision Transformers, reducing computational load and improving robu…
Personalized RewardBench: Evaluating Reward Models with Human Aligned Personalization
Qiyao Ma, Dechen Gao, Rui Cai +4
Pluralistic alignment has emerged as a critical frontier in the development of Large Language Models (LLMs), with reward models (RMs) serving as a central mechanism for capturing d…
VITA: Vision-to-Action Flow Matching Policy
Dechen Gao, Boqi Zhao, Andrew Lee +6
Conventional flow matching and diffusion-based policies sample via iterative denoising from standard noise distributions (e.g., Gaussian), and require conditioning modules to repea…
Gaze on the Prize: Shaping Visual Attention with Return-Guided Contrastive Learning
Andrew Lee, Ian Chuang, Dechen Gao +2
Visual Reinforcement Learning (RL) agents must learn to act based on high-dimensional image data where only a small fraction of the pixels is task-relevant. This forces agents to w…
MarineFormer: A Spatio-Temporal Attention Model for USV Navigation in Dynamic Marine Environments
Ehsan Kazemi, Dechen Gao, Iman Soltani
Autonomous navigation in marine environments can be extremely challenging, especially in the presence of spatially varying flow disturbances and dynamic and static obstacles. In th…
Ego-centric Learning of Communicative World Models for Autonomous Driving
Hang Wang, Dechen Gao, Junshan Zhang
We study multi-agent reinforcement learning (MARL) for tasks in complex high-dimensional environments, such as autonomous driving. MARL is known to suffer from the \textit{partial…