Yang Li

Vision-based tactile signals in the VTOUCH dataset significantly enhance bimanual manipulation capabilities, paving the way for more effective robotic interactions.

A lightweight, RL-trained context curator can match GPT-4o's context management abilities, slashing token consumption by 8x and opening the door to efficient long-horizon LLM agents.

Domain-specific reasoning and tool coordination in materials science no longer require massive LLMs: a lightweight, dual-model agent outperforms larger general-purpose models while slashing hardware costs.

LLM-generated text detection gets a major upgrade: RACE spots the difference between AI as author versus AI as editor, unlocking policy-aligned regulation.