7 citations · 16 across the 9 of their papers we have counts for
6 papers · 1 filter
Refuses in Chat, Complies with Arms: LLM Refusal Does Not Survive Robot Control
Edward Sun, Christopher Leet, Sravanthi Machcha +4
Frontier language models reliably refuse to explain how to cause physical harm. We ask whether this refusal survives when the same models control a robot. We introduce RoboHarm, a…
Visible Touch: Rendering Contact for Visuomotor Policies
Metin Alp Dogan, Edward Sun, Feng Xu +4
Integrating contact information into visuomotor policies remains an open problem. Touch is essential to robust manipulation, yet most modern policies, including pretrained vision-l…
When Seeing Overrides Knowing: Visual Dominance and Deferral-Based Method for Personalized Safety in VLMs
Edward Sun, Yuchen Wu, Zixian Ma +7
Vision-language models (VLMs) are increasingly deployed in high-stakes settings, where a response that is reasonable in general may still be unsafe for a particular user whose medi…
Meta-Ctrl: Guaranteed Plan Generation by Decoupling Syntactic and Semantic Constraints
Gwen Yidou-Weng, Edward Sun, Tianyi Ma +5
LLMs generate fluent plans for robots but routinely violate the syntactic and se8mantic constraints they must satisfy to execute, and existing remedies trade formal guarantees agai…
Memory as a Controlled Process: Learned Adaptive Memory Management for LLM Agents
Eric Hanchen Jiang, Zhi Zhang, Yuchen Wu +11
Large Language Model (LLM) agents increasingly rely on external memory systems to accumulate experience across tasks. Yet nearly all existing approaches, from graph-structured memo…
Shortcuts in the Tail: Debiasing via Post-Hoc Spectral Compression of Fine-Tuning Updates
Edward Sun, Dmitrii Troitskii
Fine-tuning often introduces spurious correlations alongside task knowledge, causing systematic failures on underrepresented groups. Existing mitigations require retraining, group…