6 papers
HarnessCompass: Guiding Automatic Harness Evolution toward Generalizable and Effective Agent Harnesses
Luan Zhang, Ruochen Zhou, Dandan Song +9
Harness design plays a critical role in agent performance by shaping how large language models (LLMs) perceive, reason over, and act within executable environments. Recent work has…
What Makes Synthetic Data Effective in Image Segmentation
Jinjin Zhang, Xiefan Guo, Yizhou Jin +2
Driven by rapid advances in large-scale generative models, synthetic data has emerged as a promising solution for visual understanding. While modern diffusion models achieve remark…
Reasoning-Driven Anomaly Detection and Localization with Image-Level Supervision
Yizhou Jin, Yuezhu Feng, Jinjin Zhang +3
Multimodal large language models (MLLMs) have recently demonstrated remarkable reasoning and perceptual abilities for anomaly detection. However, most approaches remain confined to…
ActiShade: Activating Overshadowed Knowledge to Guide Multi-Hop Reasoning in Large Language Models
Huipeng Ma, Luan Zhang, Dandan Song +10
In multi-hop reasoning, multi-round retrieval-augmented generation (RAG) methods typically rely on LLM-generated content as the retrieval query. However, these approaches are inher…
ONER: Online Experience Replay for Incremental Anomaly Detection
Yizhou Jin, Jiahui Zhu, Guodong Wang +5
Incremental anomaly detection aims to sequentially identify defects in industrial product lines but suffers from catastrophic forgetting, primarily due to knowledge overwriting dur…
Towards Training-free Anomaly Detection with Vision and Language Foundation Models
Jinjin Zhang, Guodong Wang, Yizhou Jin +1
Anomaly detection is valuable for real-world applications, such as industrial quality inspection. However, most approaches focus on detecting local structural anomalies while negle…