Profiles2022-2026
Ruisi Cai
The University of Texas at Austin
7Papers
0Last author
25Unique co-authors
3First author
0Solo
First and last author come from byline position, which some venues assign alphabetically.
Recent papers7
- ∇-Reasoner: LLM Reasoning via Test-Time Gradient Descent in Latent SpaceAuthor 2 of 7ICLR 2026 · 5 citations
- Steepest Descent Density Control for Compact 3D Gaussian SplattingAuthor 7 of 12CVPR 2025
- Understanding and Mitigating Bottlenecks of State Space Models through the Lens of Recency and Over-smoothingAuthor 2 of 7ICLR 2025
- Read-ME: Refactorizing LLMs as Router-Decoupled Mixture of Experts with System Co-DesignAuthor 1 of 7NeurIPS 2024 · 21 citations
- LoCoCo: Dropping In Convolutions for Long Context CompressionAuthor 1 of 4ICML 2024 · 17 citations
- H2O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language ModelsAuthor 6 of 12NeurIPS 2023 · 1,003 citations
- Randomized Channel Shuffling: Minimal-Overhead Backdoor Attack Detection without Clean DatasetsAuthor 1 of 5NeurIPS 2022 · 21 citations
