UW NLP (@uwnlp) / X

UW NLP
@uwnlp
Nov 3
Check out this #NeurIPS2026 work on agents that build their own reasoning scaffold for each task, guided by how people meta-reason. With an 8B model, DOLORES beats all 32B baselines in over half the settings!
Kshitish Ghate
@GhateKshitish
Nov 3
New #NeurIPS2026 paper 🧵 We introduce 🌟 Deep Reasoning 🌟, an approach for building just-in-time agentic harnesses for solving diverse reasoning problems. Inspired by human cognition, we recursively decompose tasks into atomic units of formal and associative reasoning steps. We
UW NLP
@uwnlp
Oct 8
Check out this fun project by @StellaLisy on learning to explore in image generation post-training. We enjoyed annotating the monkey penguins🐒🐧!
Stella Li
@StellaLisy
Oct 8
We introduce ExploreNet🔍 for learnable exploration in diffusion RL. ExploreNet learns an adaptive exploration distribution conditioned on the current state, rewarded by the diversity of the rollouts. ➡️ Faster, more targeted learning in diffusion GRPO.
GIF
UW NLP
@uwnlp
Oct 2
KV Cache cry no more. Blog post by @RulinShao and @oscar_yinn
WAI
@waiorg
Oct 2
We recently released Context Language Models (CLMs), and got many questions on KV Cache. Our latest blog explains 1). how we measure cache-ware FLOPs 2). how to efficiently serve CLM wai-org.com/blog/clm/
Quote
Rulin Shao
@RulinShao
Oct 2
AI systems should be designed for AI. If prefix caching gets in the way of free context access, we can fix the caching. This is the idea behind our Suffix Cache Reuse (SCR) for CLR serving. Check out our blogpost for details (fun visuals included)! wai-org.com/blog/clm/
1
UW NLP
@uwnlp
Jul 29
our very own @scottgeng00 on training olmo3 & dpo
Nathan Lambert
@natolambert
Jul 29
New podcast/lecture combo -- a case study in the messy details of Olmo 3 post training & DPO with @scottgeng00. It's rare to make time for these discussions, but we cover: What it takes for a research idea to make it into a (near) frontier model. The messy side of DPO (usually
1
UW NLP
@uwnlp
Jul 23
Congrats to @hamishivi @yinn_oscar @RulinShao for their work on tmax 👐 credit to our data chef @yinn_oscar 🧑‍🍳
Prime Intellect
@PrimeIntellect
Jul 22
Scaling agentic RL environments: today we're publishing 365,000+ tasks for SWE, terminal, and search agents - 23 tasksets behind one API, one sandbox lifecycle, one command.
1

UW NLP

UW NLP’s posts