Note: The program is subject to change. Final details will be updated closer to the workshop date.
The program schedule for the workshop is tentatively set as follows:
| Time | Event | Speaker/Presenter |
|---|---|---|
| 09:00 - 09:15 | Opening Remarks | Wei Jiang (Workshop Chair) |
| 09:15 - 10:05 | Keynote: Model Compression for Efficient Generative AI | Jinyang Guo (Beihang University) |
| 10:05 - 10:35 | Paper Presentation: SLMQuant: Benchmarking Small Language Model Quantization for Practical Deployment | Authors |
| 10:35 - 11:05 | Paper Presentation: Efficient and Accurate Post-Training Sparsification of Large Language Models with Proximal Operators | Authors |
| 11:05 - 11:30 | Coffee Break | - |
| 11:30 - 12:15 | Challenge Report: M3VIR: A Large-Scale Multi-Modality Multi-View Synthesized Benchmark Dataset for Image Restoration and Content Creation | Yuanzhi Li |
| 12:15 - 13:30 | Lunch Break | - |
| 13:30 - 14:00 | Paper Presentation: DCEdit: Dual-Level Controlled Image Editing via Precisely Localized Semantics | Authors |
| 14:00 - 14:30 | Paper Presentation: Text-to-Image Generation Post-Training with Pixel-Space Loss | Authors |
| 14:30 - 15:20 | Keynote: Cosmos World Foundation Models for Physical AI | Jinwei Gu (Nvidia) |
| 15:20 - 16:10 | Keynote: Disentangle Appearance, Geometry, and Motion for Video Modeling and Generation | Junsong Yuan (SUNY Buffalo) |
| 16:10- 16:30 | Coffee Break | - |
| 16:30 - 17:20 | Keynote: User Simulator to Evaluate and Optimize AIGC | Junfeng He (Google) |
| 17:20 - 17:50 | Paper Presentation: BlingDiff: High-Fidelity Virtual Jewelry Try-On with Detail-Optimized Diffusionn | Authors |
| 17:50-18:15 | Award Session & Closing Remarks | Workshop Chairs |