Xin Cao

The paper demonstrates that current transfer-based AML systems fail in complex DeFi environments because economic value migration can be structurally decoupled from explicit token transfers.

This survey provides a comprehensive, structured review of safety research in Embodied AI, analyzing attacks and defenses across the entire embodied pipeline to guide the development of safe, robust, and reliable real-world agents.

This paper presents a black-box membership inference attack (MIA) against Video Large Language Models (VideoLLMs), demonstrating that they are vulnerable by analyzing generation behavior across varying decoding temperatures.

DenoiseRL is a novel reinforcement learning framework that improves reasoning in large language models by optimizing directly from the failures and incorrect reasoning traces of weak models, eliminating the need for strong external supervision or curated datasets.

The paper introduces a multilingual benchmark (MentalMap) to test if LLMs build internal spatial world models from text, finding a universal 'L3 reasoning cliff' suggesting that text-only working memory is the primary bottleneck.

The paper addresses the 'detection-to-abstention gap' in reasoning models, where detecting insufficient information does not lead to abstention, by proposing a novel control framework that forces models to commit to an answerability judgment before solving.

TraceGraph introduces a graph-based framework to map agent decision-making across pooled trajectories, revealing hidden differences in agent behavior and improving performance by targeting known failure regions.