| 09:00 AM | Opening Remarks |
| 09:10 AM | Paper Presentation (Information Consistent Pruning: How to Efficiently Search for Sparse Networks?) |
| 09:25 AM | Paper Presentation (Efficient LLM Inference with I/O-Aware Partial KV Cache Recomputation) |
| 09:40 AM | Paper Presentation (The Impact of Model Scaling on Seen and Unseen Language Performance) |
| 09:55 AM | Paper Presentation (PickLLM: Context-Aware RL-Assisted Large Language Model Routing) |
| 10:10 AM | Break |
| 10:40 AM | Keynote Talk by Dr. Danfeng Qin, Google DeepMind |
| 11:20 AM | Paper Presentation (Differentiated Aggregation to Improve Generalization in Federated Learning) |
| 11:35 AM | Paper Presentation (ssProp: Energy-Efficient Training for Convolutional Neural Networks with Scheduled Sparse Back Propagation) |
| 11:50 AM | Break |
| 01:30 PM | Keynote Talk by Dr. Priyadarshini Panda, Yale University |
| 02:10 PM | Keynote Talk by Dr. Yanzhi Wang, Northeastern University |
| 02:50 PM | Paper Presentation (Knowledge Distillation with Training Wheels) |
| 03:05 PM | Paper Presentation (ZNorm: Z-Score Gradient Normalization Accelerating Skip-Connected Network Training without Architectural Modification) |
| 03:20 PM | Paper Presentation (Efficient Image Similarity Search with Quadtrees) |
| 03:35 PM | Closing Remarks |
All times are in Philadelphia local time.
Contact Info
E-mail: seas25 AT googlegroups.com