6 papers
Advantage Collapse in Group Relative Policy Optimization: Diagnosis and Mitigation
Xixiang He, Qiyao Sun, Ao Cheng +5
Group Relative Policy Optimization (GRPO), a prominent algorithm within the Reinforcement Learning from Verifiable Rewards (RLVR) framework, has achieved strong results in improvin…
MoASE++: Mixture of Activation Sparsity Experts with Domain-Adaptive On-policy Distillation for Continual Test Time Adaptation
Ronyu Zhang, Aosong Cheng, Gaole Dai +8
Continual test-time adaptation adapts a source-pretrained model to non-stationary, unlabeled target streams while retaining past competence, yet texture-biased backbones risk error…
Key-Embedded Privacy for Decentralized AI in Biomedical Omics
Rongyu Zhang, Hongyu Dong, Gaole Dai +13
The rapid adoption of data-driven methods in biomedicine has intensified concerns over privacy, governance, and regulation, limiting raw data sharing and hindering the assembly of…
Beyond Text-Visual Attention: Exploiting Visual Cues for Effective Token Pruning in VLMs
Qizhe Zhang, Aosong Cheng, Ming Lu +6
Large vision-language models (LVLMs) generally contain significantly more visual tokens than their textual counterparts, resulting in a considerable computational burden. Recent ef…
MMTrail: A Multimodal Trailer Video Dataset with Language and Music Descriptions
Xiaowei Chi, Yatian Wang, Aosong Cheng +16
Massive multi-modality datasets play a significant role in facilitating the success of large video-language models. However, current video-language datasets primarily provide text…
Decomposing the Neurons: Activation Sparsity via Mixture of Experts for Continual Test Time Adaptation
Rongyu Zhang, Aosong Cheng, Yulin Luo +8
Continual Test-Time Adaptation (CTTA), which aims to adapt the pre-trained model to ever-evolving target domains, emerges as an important task for vision models. As current vision…