Yang Yu

The paper characterizes logging code security issues and benchmarks LLMs, finding that while LLMs can moderately detect these issues, they struggle significantly with reliably generating correct code repairs.

ClawdGo is a novel framework that provides endogenous security awareness training for autonomous AI agents, enabling them to recognize and reason about internal threats without modifying the underlying model.

The paper establishes the first theoretical framework for analyzing the learnability of Test-Time Adaptation (TTA) under non-stationary data streams by introducing Recovery Complexity, which quantifies the long-term reliability of TTA.

The paper introduces TaskWeave, a hierarchical agentic framework that successfully simulates long-horizon organizational dynamics by treating coordination as a memory-centered problem, demonstrating that structured memory is key to reliable LLM-based simulations.

The paper introduces ChartWalker, a framework for generating challenging cross-modal analytical tasks using charts, with a hierarchical knowledge graph construction method and structure-aware sampling algorithm.

The paper introduces MADB, a large-scale dataset and benchmark for music aesthetic assessment with 9,999 tracks annotated by 30 trained annotators across 10 perceptual dimensions.

This paper introduces the REAL-TSE Challenge, a satellite challenge on target speaker extraction from real conversational recordings, and describes its task definition, datasets, evaluation protocol, and submitted systems.

A closed-loop evolutionary algorithm is proposed to guide a large language model in generating complete and executable physics-informed neural network configurations, using measured training outcomes to determine subsequent search decisions.