3 papers
cs.LG2026
TQL: Scaling Q-Functions with Transformers by Preventing Attention Collapse
Perry Dong, Kuo-Han Hung, Alexander Swerdlow +2
Despite scale driving substantial recent advancements in machine learning, reinforcement learning (RL) methods still primarily use small value functions. Naively scaling value func…
cs.RO2025
DexMan: Learning Bimanual Dexterous Manipulation from Human and Generated Videos
Jhen Hsieh, Kuan-Hsun Tu, Kuo-Han Hung +1
We present DexMan, an automated framework that converts human visual demonstrations into bimanual dexterous manipulation skills for humanoid robots in simulation. Operating directl…
cs.CR2024
Attention Tracker: Detecting Prompt Injection Attacks in LLMs
Kuo-Han Hung, Ching-Yun Ko, Ambrish Rawat +3
Large Language Models (LLMs) have revolutionized various domains but remain vulnerable to prompt injection attacks, where malicious inputs manipulate the model into ignoring origin…