collaborators

6 papers

cs.LG2026

DECAF: De-Clustering for Adaptive Representational Unlearning

Anjie Le, Can Peng, Hongcheng Guo +1

Machine unlearning, which aims to remove the influence of specific training data from a trained model, is a key requirement for privacy, accountability, and adaptive deployment. We…

cs.CV2026

From Failure to Feedback: Group Revision Unlocks Hard Cases in Object-Level Grounding

Yuyuan Liu, Yiping Ji, Anjie Le +6

Finetuning Large Vision-Language Models with reinforcement learning has emerged as a promising approach to enhance their capability in object-level grounding. However, existing met…

cs.CV2026

POUR: A Provably Optimal Method for Unlearning Representations via Neural Collapse

Anjie Le, Can Peng, Yuyuan Liu +1

In computer vision, machine unlearning aims to remove the influence of specific visual concepts or training images without retraining from scratch. Studies show that existing appro…

cs.CV2026

U2-BENCH: Benchmarking Large Vision-Language Models on Ultrasound Understanding

Anjie Le, Henan Liu, Yue Wang +18

Ultrasound is a widely-used imaging modality critical to global healthcare, yet its interpretation remains challenging due to its varying image quality on operators, noises, and an…

cs.CL2025

SNS-Bench-VL: Benchmarking Multimodal Large Language Models in Social Networking Services

Hongcheng Guo, Zheyong Xie, Shaosheng Cao +5

With the increasing integration of visual and textual content in Social Networking Services (SNS), evaluating the multimodal capabilities of Large Language Models (LLMs) is crucial…

cs.SE2025

Lemur: Log Parsing with Entropy Sampling and Chain-of-Thought Merging

Wei Zhang, Xiangyuan Guan, Lu Yunhong +5

Logs produced by extensive software systems are integral to monitoring system behaviors. Advanced log analysis facilitates the detection, alerting, and diagnosis of system faults.…