Session
Intelligent Systems for Physical & Structured Worlds
DescriptionThis session covers methodologies for EDA (chip placement, timing prediction), 3D vision, robotics, GNNs for circuit graphs, and structured spatial reasoning.
Event Type
Research Manuscript
TimeWednesday, July 293:30pm - 5:30pm PDT
LocationMtg Room 101A
AI
AI2-II. AI/ML Algorithms and Models
Presentations
| 3:30pm - 3:42pm PDT | Adagscale: Viewpoint-Adaptive Gaussian Scaling in 3D Gaussian Splatting to Reduce Gaussian-Tile Pairs | |
| 3:42pm - 3:54pm PDT | Flowplace: Flow Matching for Chip Placement | |
| 3:54pm - 4:06pm PDT | How Can Reinforcement Learning Achieve Expert-Level Placement? | |
| 4:06pm - 4:18pm PDT | ENACT: Ensemble Neural Fields for Reactive Robot Control | |
| 4:18pm - 4:30pm PDT | Excavating Consistency Across Editing Steps for Effective Multi-Step Image Editing | |
| 4:30pm - 4:42pm PDT | GSR-GNN: Training Acceleration and Memory-Saving Framework of Deep GNNs on Circuit Graph | |
| 4:42pm - 4:54pm PDT | PBA-rGAT-Edge: Arc-Level Path-Based Timing Prediction with Scalable Residual Edge-Aware Graph Attention | |
| 4:54pm - 5:06pm PDT | Operator-Level Acceleration for Sparse 3D Object Detection | |
| 5:06pm - 5:18pm PDT | TRACE: Learning to Compute on Circuit Graphs | |
| 5:18pm - 5:30pm PDT | Flashfps: Efficient Farthest Point Sampling for Large-Scale Point Clouds via Pruning and Caching |