Tong Xu

ZK-Value introduces a practical, scalable zero-knowledge system for calculating data valuations (Shapley values) in data marketplaces, significantly reducing proving time while maintaining high accuracy.

This paper addresses the threat of coordinated misinformation in LLM-based Multi-Agent Systems by proposing a defense framework, STAR, that effectively identifies and rectifies misleading information at the sentence level.

The paper proposes EKSFT, a selective fine-tuning method that masks high-entropy or high-KL divergence tokens during Supervised Fine-Tuning (SFT) to prevent distribution shift and improve subsequent Reinforcement Learning (RL) performance.

The paper proposes VISTA, a multi-level event semantics mining framework, to accurately predict complex events in long videos, addressing the limitations of current LLMs in this domain.

This paper reveals a denial-of-service vulnerability in LLM-based guardrails for autonomous agents and proposes two attack frameworks.

AutoSpec is a framework that uses counterexample-guided inductive synthesis and inductive logic programming to automatically evolve safety rules for large language model agents.