The NeurIPS Call for Papers is now live. Abstracts are due May 11th AoE, with full papers due May 15th AoE. neurips.cc/Conferences/...
Please read about key changes to Dataset and Benchmarks submissions this year in our blog post: blog.neurips.cc/2025/03/10/n...
To repeat, we train RINS on less data to match the same compute flops, which is why this is a stronger result than “sample efficiency”, and one should not just expect it to work. E.g. it does NOT help in image classification but RINS works in language and multimodal. Why? (3/n)🤔
🔥Excited to introduce RINS - a technique that boosts model performance by recursively applying early layers during inference without increasing model size or training compute flops! Not only does it significantly improve LMs, but also multimodal systems like SigLIP.
(1/N)