6 papers
Reasoning with Memory: A Temporal Granularity-Adaptive Framework for Training-Free Long Video Understanding
Linghao Meng, Qiankun Li, Junyuan Mao +7
While Multimodal Large Language Models (MLLMs) demonstrate superior generalization in fundamental video tasks, restricted context windows limit their long video understanding. To a…
SurgFed: Language-guided Multi-Task Federated Learning for Surgical Video Understanding
Zheng Fang, Ziwei Niu, Ziyue Wang +5
Surgical scene Multi-Task Federated Learning (MTFL) is essential for robot-assisted minimally invasive surgery (RAS) but remains underexplored in surgical video understanding due t…
Granulon: Awakening Pixel-Level Visual Encoders with Adaptive Multi-Granularity Semantics for MLLM
Junyuan Mao, Qiankun Li, Linghao Meng +5
Recent advances in multimodal large language models largely rely on CLIP-based visual encoders, which emphasize global semantic alignment but struggle with fine-grained visual unde…
MedVAR: Towards Scalable and Efficient Medical Image Generation via Next-scale Autoregressive Prediction
Zhicheng He, Yunpeng Zhao, Junde Wu +5
Medical image generation is pivotal in applications like data augmentation for low-resource clinical tasks and privacy-preserving data sharing. However, developing a scalable gener…
Unleashing the Power of Image-Tabular Self-Supervised Learning via Breaking Cross-Tabular Barriers
Yibing Fu, Yunpeng Zhao, Zhitao Zeng +2
Multi-modal learning integrating medical images and tabular data has significantly advanced clinical decision-making in recent years. Self-Supervised Learning (SSL) has emerged as…
Backdoor Attribution: Elucidating and Controlling Backdoor in Language Models
Miao Yu, Zhenhong Zhou, Moayad Aloqaily +5
Fine-tuned Large Language Models (LLMs) are vulnerable to backdoor attacks through data poisoning, yet the internal mechanisms governing these attacks remain a black box. Previous…