Yutong (Kelly) He

Diffusion planners are great for offline RL. But they need many steps to work well! Way too slow for real-time decision making! Presenting RACTD at #ICLR2026: reward-aware distillation that plans in ONE step 🇧🇷 Today (4/23) P4-#4618 3:15-5:45 PM arxiv.org/abs/2506.07822 1/

As LLMs saturate benchmarks, evaluating their five-nines reliability is crucial, but prohibitively expensive. We cut the inference cost by 5-20x on average (up to 156×) by exploiting a key insight: LLM failures are not random. 🧵[1/n]

One of the things I’m most excited about this year is building agents that can work productively for hours, days, or weeks. Coding agents are starting to become very competent at this, but what about computer use agents? Our new benchmark, Odysseys (co-led with @JangLawrenceK) is a set of 200 new tasks derived from real world browsing behavior that measure long horizon web navigation capabilities (potentially up to hours of web browsing work). Interestingly, we find that frontier CUAs are already surprisingly good at working productively for up to an hour on these tasks, but there’s a lot of work to be done in making them even more efficient. Like every other AI researcher, my real dream is to open a cafe once we solve ASI. So, here’s Opus 4.6 doing some market research for me ("I want to do market research on the most popular cafes in Singapore. Analyse the menus of the top 10 cafes in Singapore (by Google reviews/ratings), and make sure we include at least 1 from the North/South/East/West/Central regions of Singapore. Keep the relevant pages of each cafe open, and summarise their pricing, menu offerings, unique selling points, making sure to reference which tab is opened for each cafe. For each cafe, also help me figure out how long it would take to get to it from Tampines MRT, and include this in your final summary."). I was very impressed to see Opus 4.6 complete this task after working for 52 mins, satisfying all 7 rubrics that corresponded to this task. It provided a very nice markdown summary at the end that gave me all the information I asked for!

Foresight will be the defining frontier on the path to AGI. I am excited to start Sooth Labs with my amazing co-founders: Yaser Sheikh @subail, Chuck Hoover @chuckjhoover, David LaRose, and Shih-En Wei. Deeply grateful to Aydin Senkut @asenkut and Feyza Haskaraman @FHaskaraman at @felicis for leading the round, alongside an exceptional group of partners. bloomberg.com/news/articles/…

Joint work with the amazing @x_duan9296 (the best master's student at CMU), @FahimTajwar10, @rsalakhu, @zicokolter, and Jeff Schneider. Come chat with us today at 3:15 PM! Paper: arxiv.org/abs/2506.07822 Code: github.com/Ddduanxt/RACTD

RACTD improves over previous SOTA by 9.7% on D4RL Gym-MuJoCo and outperforms Diffuser on long-horizon Maze2D planning All with a SINGLE denoising step, achieving up to 142x speedup over diffusion counterparts 🚀🚀🚀

Diffusion planners are great for offline RL. But they need many steps to work well! Way too slow for real-time decision making! Presenting RACTD at #ICLR2026: reward-aware distillation that plans in ONE step 🇧🇷 Today (4/23) P4-#4618 3:15-5:45 PM arxiv.org/abs/2506.07822 1/

How can visual planning agents 𝙨𝙚𝙡𝙛-𝙞𝙢𝙥𝙧𝙤𝙫𝙚 from their own collected experience? We present 𝗦𝗜𝗟𝗩𝗥🩶, a framework that combines offline data with online experience for concurrent zero-shot generalization and sample-efficient self-improvement capabilities!#ICLR2026

💎

F2D2 is accepted at #ICLR2026 ! To celebrate, we have added a new JAX codebase & new results w/ Lagrangian self-distillation in camera-ready! Check them out on our project page: kellyyutonghe.github.io/f2d2/ P.S. I will present F2D2 Apr 23 10:30 AM – 1:00 PM P3-#1911, see yall in Rio🇧🇷

🐍

@nmboffi 🕶️

@electronickale Welcome to the dark side

5 days into my trip to the Bay Area I’ve already upgraded my Claude subscription to max 🙂

@yus167 not 🐋 if it's for agi 🤖

@electronickale 🐋

Train Beyond Language. We bet on the visual world as the critical next step alongside and beyond language modeling. So, we studied building foundation models from scratch with vision. We share our exploration: visual representations, data, world modeling, architecture, and scaling behavior! [1/9]

Super grateful to be invited for the talk and very excited to meet with everyone next month!

Video Editing is great - but what if you want to apply an effect to your input video described by another video?? Introducing RefVFX, the first method that takes in both an input video and a reference effect video for generative video editing!

Flow map language model on openwebtext scale!