3 papers
cs.CV2026
CATA: Continual Machine Unlearning via Conflict-Averse Task Arithmetic
Shen Lin, Junhao Dong, Rongjie Chen +3
Vision-language models (VLMs) have shown remarkable ability in aligning visual and textual representations, enabling a wide range of multimodal applications. However, their large-s…
cs.CR2026
Knowing without Acting: The Disentangled Geometry of Safety Mechanisms in Large Language Models
Jinman Wu, Yi Xie, Shen Lin +2
Safety alignment is often conceptualized as a monolithic process wherein harmfulness detection automatically triggers refusal. However, the persistence of jailbreak attacks suggest…
cs.CV2026
RxnBench: A Multimodal Benchmark for Evaluating Large Language Models on Chemical Reaction Understanding from Scientific Literature
Hanzheng Li, Xi Fang, Yixuan Li +9
The integration of Multimodal Large Language Models (MLLMs) into chemistry promises to revolutionize scientific discovery, yet their ability to comprehend the dense, graphical lang…