Ion Stoica
- Efficiently Scaling LLM Reasoning Programs with Certaindex
- Establishing Best Practices in Building Rigorous Agentic Benchmarks
- Faster Video Diffusion with Trainable Sparse Attention
- GSO: Challenging Software Optimization Tasks for Evaluating SWE-Agents
- 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
- Twilight: Adaptive Attention Sparsity with Hierarchical Top-$p$ Pruning
- Why Do Multi-Agent LLM Systems Fail?
- WorldModelBench: Judging Video Generation Models As World Models