Lei Xie

LibScan is an automated framework that detects eight categories of smart contract library misuse by combining LLM-based semantic reasoning with rule-based analysis, achieving 85.15% accuracy on real-world contracts.

InfoMerge is a novel, training-free method that significantly compresses visual tokens for Video-LLMs by estimating temporal redundancy and allocating tokens based on content richness, achieving high efficiency with minimal performance loss.

The paper argues that current embodied planning benchmarks prioritize superficial language prediction over true physical reasoning, introducing new benchmarks and a large-scale dataset to demonstrate that physically grounded causal reasoning is necessary for reliable autonomous agents.

The paper introduces GigaSpeechBench, a comprehensive multilingual and multidimensional ASR & AST benchmark with 680 hours of human-annotated speech, featuring 12 low-resource languages, 6 Chinese dialects, 6 English accents, dense terminology, older adult and child speech, and human-annotated translations.

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.