Jyo Pari
157 posts
@jyo_pari
Working on continual learning | PhD @MIT
Tokenization & Generation power Large Models. But are they really separate? Tokenization=Generation under strong observability UNITE: An end-to-end training framework where one shared Generative Encoder (GE) performs both token. & latent denoising Paper: arxiv.org/abs/2603.22283
Introducing M²RNN: Non-Linear RNNs with Matrix-Valued States for Scalable Language Modeling We bring back non-linear recurrence to language modeling and show it's been held back by small state sizes, not by non-linearity itself. 📄 Paper: arxiv.org/abs/2603.14360 💻 Code: github.com/open-lm-engine… 🤗 Models: huggingface.co/collections/op…
Being good at next word prediction is the opposite of what we want for creativity, for scientific breakthroughs.
Can language models learn useful priors without ever seeing language? We pre-pre-train transformers on neural cellular automata — fully synthetic, zero language. This improves language modeling by up to 6%, speeds up convergence by 40%, and strengthens downstream reasoning. Surprisingly, it even beats pre-pre-training on natural text! Blog: hanseungwook.github.io/blog/nca-pre-p… (1/n)
People keep saying 2026 will be the year of continual learning. But there are still major technical challenges to making it a reality. Today we take the next step towards that goal — a new on-policy learning algorithm, suitable for continual learning! (1/n)
Our latest post explores on-policy distillation, a training approach that unites the error-correcting relevance of RL with the reward density of SFT. When training it for math reasoning and as an internal chat assistant, we find that on-policy distillation can outperform other approaches for a fraction of the cost. thinkingmachines.ai/blog/on-policy…
What if scaling the context windows of frontier LLMs is much easier than it sounds? We’re excited to share our work on Recursive Language Models (RLMs). A new inference strategy where LLMs can decompose and recursively interact with input prompts of seemingly unbounded length, as a REPL environment. On the OOLONG benchmark, RLMs with GPT-5-mini outperforms GPT-5 by over 110% gains (more than double!) on 132k-token sequences and is cheaper to query on average. On the BrowseComp-Plus benchmark, RLMs with GPT-5 can take in 10M+ tokens as their “prompt” and answer highly compositional queries without degradation and even better than explicit indexing/retrieval. We link our blogpost, (still very early!) experiments, and discussion below.
I wrote this blog post that tries to go further toward design principles for neural nets and optimizers The post presents a visual intro to optimization on normed manifolds and a Muon variant for the manifold of matrices with unit condition number x.com/thinkymachines…
For agents to improve over time, they can’t afford to forget what they’ve already mastered. We found that supervised fine-tuning forgets more than RL when training on a new task! Want to find out why? 👇
