activity
20242026
collaborators

9 papers

cs.CV2026

Memory-Supported Synergistic Adaptation for Training-Free Test-Time Medical Image Segmentation

Lingrui Li, Nan Pu, Dong Zhao +4

Test-time adaptation (TTA) aims to mitigate distribution shifts by adapting models with unlabeled target data at inference time. While TTA with vision-language models (VLMs) has sh…

cs.CV2026

Technical Report for the ICRA 2026 GOOSE 2D Fine-Grained Semantic Segmentation Challenge: Pretraining-Diverse Ensemble of Foundation Vision Encoders for Robust Outdoor Scene Understanding

Boyan Wang, Yongxi Huang, Wenjing Li +4

This report presents our solution for the ICRA 2026 GOOSE 2D Fine-Grained Semantic Segmentation Challenge, which requires parsing unstructured outdoor scenes from four camera platf…

cs.CV2026

EvoComp: Learning Visual Token Compression for Multimodal Large Language Models via Semantic-Guided Evolutionary Labeling

Jiafei Song, Fengwei Zhou, Jin Qu +7

Recent Multimodal Large Language Models (MLLMs) have demonstrated strong performance on vision-language understanding tasks, yet their inference efficiency is often hampered by the…

cs.LG2026

The Devil Is in Gradient Entanglement: Energy-Aware Gradient Coordinator for Robust Generalized Category Discovery

Haiyang Zheng, Nan Pu, Yaqi Cai +4

Generalized Category Discovery (GCD) leverages labeled data to categorize unlabeled samples from known or unknown classes. Most previous methods jointly optimize supervised and uns…

cs.CV2025

Open-World Deepfake Attribution via Confidence-Aware Asymmetric Learning

Haiyang Zheng, Nan Pu, Wenjing Li +3

The proliferation of synthetic facial imagery has intensified the need for robust Open-World DeepFake Attribution (OW-DFA), which aims to attribute both known and unknown forgeries…

cs.CV2025

Generalized Fine-Grained Category Discovery with Multi-Granularity Conceptual Experts

Haiyang Zheng, Nan Pu, Wenjing Li +2

Generalized Category Discovery (GCD) is an open-world problem that clusters unlabeled data by leveraging knowledge from partially labeled categories. A key challenge is that unlabe…