61 citations · 77 across the 14 of their papers we have counts for
14 papers
OpenClawBench: Benchmarking Process-side Anomalies in Real-world Agent Execution Trajectories
Yibing Liu, Yangze Liu, Xiaolong Yin +4
Task success can hide process anomalies in real-world agent executions. An agent may pass the final task oracle while still accumulating unresolved ambiguity, unsafe external write…
From Text to Forecasts: Bridging Modality Gap with Temporal Evolution Semantic Space
Lehui Li, Yuyao Wang, Jisheng Yan +5
Incorporating textual information into time-series forecasting holds promise for addressing event-driven non-stationarity; however, a fundamental modality gap hinders effective fus…
Agentic Unlearning: When LLM Agent Meets Machine Unlearning
Bin Wang, Fan Wang, Pingping Wang +5
In this paper, we introduce \textbf{agentic unlearning} which removes specified information from both model parameters and persistent memory in agents with closed-loop interaction.…
DVLA-RL: Dual-Level Vision-Language Alignment with Reinforcement Learning Gating for Few-Shot Learning
Wenhao Li, Xianjing Meng, Qiangchang Wang +3
Few-shot learning (FSL) aims to generalize to novel categories with only a few samples. Recent approaches incorporate large language models (LLMs) to enrich visual representations…
TrajAD: Trajectory Anomaly Detection for Trustworthy LLM Agents
Yibing Liu, Chong Zhang, Zhongyi Han +5
We address the problem of runtime trajectory anomaly detection, a critical capability for enabling trustworthy LLM agents. Current safety measures predominantly focus on static inp…
G-OSR: A Comprehensive Benchmark for Graph Open-Set Recognition
Yicong Dong, Rundong He, Guangyao Chen +4
Graph Neural Networks (GNNs) have achieved significant success in machine learning, with wide applications in social networks, bioinformatics, knowledge graphs, and other fields. M…
Unveiling the Superior Paradigm: A Comparative Study of Source-Free Domain Adaptation and Unsupervised Domain Adaptation
Fan Wang, Zhongyi Han, Xingbo Liu +2
In domain adaptation, there are two popular paradigms: Unsupervised Domain Adaptation (UDA), which aligns distributions using source data, and Source-Free Domain Adaptation (SFDA),…
CLIP-driven Outliers Synthesis for few-shot OOD detection
Hao Sun, Rundong He, Zhongyi Han +3
Few-shot OOD detection focuses on recognizing out-of-distribution (OOD) images that belong to classes unseen during training, with the use of only a small number of labeled in-dist…
How Well Does GPT-4V(ision) Adapt to Distribution Shifts? A Preliminary Investigation
Zhongyi Han, Guanglin Zhou, Rundong He +7
In machine learning, generalization against distribution shifts -- where deployment conditions diverge from the training scenarios -- is crucial, particularly in fields like climat…
Topological Structure Learning for Weakly-Supervised Out-of-Distribution Detection
Rundong He, Rongxue Li, Zhongyi Han +1
Out-of-distribution (OOD) detection is the key to deploying models safely in the open world. For OOD detection, collecting sufficient in-distribution (ID) labeled data is usually m…
Active Source Free Domain Adaptation
Fan Wang, Zhongyi Han, Zhiyan Zhang +1
Source free domain adaptation (SFDA) aims to transfer a trained source model to the unlabeled target domain without accessing the source data. However, the SFDA setting faces an ef…
Learning to Rectify for Robust Learning with Noisy Labels
Haoliang Sun, Chenhui Guo, Qi Wei +2
Label noise significantly degrades the generalization ability of deep models in applications. Effective strategies and approaches, \textit{e.g.} re-weighting, or loss correction, a…
Learning Transferable Parameters for Unsupervised Domain Adaptation
Zhongyi Han, Haoliang Sun, Yilong Yin
Unsupervised domain adaptation (UDA) enables a learning machine to adapt from a labeled source domain to an unlabeled domain under the distribution shift. Thanks to the strong repr…
Unifying Neural Learning and Symbolic Reasoning for Spinal Medical Report Generation
Zhongyi Han, Benzheng Wei, Yilong Yin +1
Automated medical report generation in spine radiology, i.e., given spinal medical images and directly create radiologist-level diagnosis reports to support clinical decision makin…