Announcement_17

Several papers from our group were accepted at this year’s ICLR 2025 conference. Congratulations to our PhD student Yongxin GUO on his three first-author acceptance, and to our PhD student Futing WANG on her first first-author acceptance. We also extend the same congratulations to our PhD students Zhenglin CHENG, Peng SUN, and Yuxuan SUN, and to our internship students Xinyi SHANG, Jiamu ZHENG, and Jinwei YAO.

• Oral (1.8%) -> PathGen-1.6M: 1.6 Million Pathology Image-text Pairs Generation through Multi-agent Collaboration
• Spotlight (5.1%) -> DeFT: Decoding with Flash Tree-attention for Efficient Tree-structured LLM Inference
• ELICIT: LLM Augmentation Via External In-context Capability
• Dynamic Mixture of Experts: An Auto-Tuning Approach for Efficient Transformer Models
• GIFT: Unlocking Full Potential of Labels in Distilled Dataset at Near-zero Cost
• Enhancing Clustered Federated Learning: Integration of Strategies and Improved Methodologies
• CollabEdit: Towards Non-destructive Collaborative Knowledge Editing