Kurt Keutzer
- Angles Don’t Lie: Unlocking Training‑Efficient RL Through the Model’s Own Signals
- DrivingRecon: Large 4D Gaussian Reconstruction Model For Autonomous Driving
- Multipole Attention for Efficient Long Context Reasoning
- Radial Attention: $\mathcal O(n \log n)$ Sparse Attention for Long Video Generation
- Sparse VideoGen2: Accelerate Video Generation with Sparse Attention via Semantic-Aware Permutation
- Why Do Multi-Agent LLM Systems Fail?