collaborators

8 papers

cs.LG2026

Write-Protected Discrete Bottlenecks for Language-Grounded World Models: A Structural Limitation and Sufficient Fix

Jiayi Fang

How should language interface with a world model's discrete symbol system? The dominant paradigm -- end-to-end injection of LLM/VLM features into robot world models (RT-2, Octo, Pa…

cs.LG2026

Emergent Semantic Representations in World Models through Physical Interaction without Linguistic Supervision

Jiayi Fang

What does a world model learn from physical exploration, without any linguistic supervision? We argue the answer is organized by a single principle: the geometric structure of the…

cs.RO2026

Embodiment Meets Environment: Toward Context-Aware, Safe Physical Caregiving Robots

Zhanxin Wu, Ruofei Tong, Jiaying Fang +1

Physical caregiving robots need to assist different users with different tasks in diverse environments, and they come in many embodiments. While substantial progress has been made…

cs.RO2026

Beyond Failure Recovery: An Engagement-Aware Human-in-the-loop Framework for Robotic Systems

Jiaying Fang, Joyce Yang, Zhanxin Wu +2

Conventional human-in-the-loop approaches typically involve users only when a robot encounters failure or uncertainty, treating humans primarily as tools for improving robot perfor…

cs.RO2026

Phantom: Training Robots Without Robots Using Only Human Videos

Marion Lepert, Jiaying Fang, Jeannette Bohg

Training general-purpose robots requires learning from large and diverse data sources. Current approaches rely heavily on teleoperated demonstrations which are difficult to scale.…

cs.RO2026

A Human-in-the-Loop Confidence-Aware Failure Recovery Framework for Modular Robot Policies

Rohan Banerjee, Krishna Palempalli, Bohan Yang +5

Robots operating in unstructured human environments inevitably encounter failures, especially in robot caregiving scenarios. While humans can often help robots recover, excessive o…