collaborators

5 papers

cs.CV2026

Addressing Overthinking in Large Vision-Language Models via Gated Perception-Reasoning Optimization

Xingjian Diao, Zheyuan Liu, Chunhui Zhang +6

Large Vision-Language Models (LVLMs) have exhibited strong reasoning capabilities through chain-of-thought mechanisms that generate step-by-step rationales. However, such slow-thin…

cs.SE2026

Terminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line Interfaces

Mike A. Merrill, Alexander G. Shaw, Nicholas Carlini +82

AI agents may soon become capable of autonomously completing valuable, long-horizon tasks in diverse domains. Current benchmarks either do not measure real-world tasks, or are not…

cs.CL2025

Judging the Judges: A Systematic Study of Position Bias in LLM-as-a-Judge

Lin Shi, Chiyu Ma, Wenhua Liang +3

LLM-as-a-Judge has emerged as a promising alternative to human evaluators across various tasks, yet inherent biases - particularly position bias, the tendency to favor solutions ba…

cs.AI2025

Judging with Many Minds: Do More Perspectives Mean Less Prejudice? On Bias Amplifications and Resistance in Multi-Agent Based LLM-as-Judge

Chiyu Ma, Enpei Zhang, Yilun Zhao +7

LLM-as-Judge has emerged as a scalable alternative to human evaluation, enabling large language models (LLMs) to provide reward signals in trainings. While recent work has explored…

cs.CL2025

Vulnerability of Text-to-Image Models to Prompt Template Stealing: A Differential Evolution Approach

Yurong Wu, Fangwen Mu, Qiuhong Zhang +8

Prompt trading has emerged as a significant intellectual property concern in recent years, where vendors entice users by showcasing sample images before selling prompt templates th…