2 papers
cs.LG2026
TabSwift: An Efficient Tabular Foundation Model with Row-Wise Attention
Si-Yang Liu, Han-Jia Ye
Tabular foundation models, exemplified by TabPFN, perform prediction via in-context learning, inferring test labels directly from labeled training examples. They have demonstrated…
cs.CR2026
Defending Jailbreak Attacks on Large Language Models via Manifold Trajectory Kinetics
Hangtao Zhang, Yucheng Zhao, Sishun Liu +8
Jailbreak prompts can bypass alignment guardrails in large language models (LLMs) and elicit unsafe outputs, making reliable deployment-time detection critical. Prior detection app…