Nan Huang

The paper proposes a multi-modal contrastive learning framework to improve the generalization of machine learning models in cybersecurity by transferring knowledge from rich textual vulnerability descriptions to data-scarce payload classification.

The paper introduces TouchSafeBench, a physics-grounded benchmark, to evaluate collision grounding—the ability to predict robot-human collisions—and finds that current Vision-Language Models (VLMs) are unreliable for safe human-robot collaboration.

TAPS introduces a target-aware prefix selection method that optimizes the trade-off between draft tree acceptance and verification cost, achieving significant speedups in speculative decoding.

An autonomous research agent is developed to automate end-to-end LLM in high-stakes scientific domains, specifically condensed matter physics, by mapping the corpus, calibrating methodology, conducting computations, and writing a publication-grade manuscript.

This paper introduces the asymmetric origami bending (AOB) pattern and asymmetric dual-chamber (ADC) design for creating a soft robotic hand called OSOR, which achieves bio-inspired motions and simplified manufacturing.