@chelseabfinn
Asst Prof of CS & EE @Stanford Co-founder of Physical Intelligence @physical_int PhD from @Berkeley_EECS, EECS BS from @MIT
Scientific discovery is one of the most exciting applications of LLMs, but we lack data & evals on the scientific process. ScholarCatalyst captures which prior papers can advance new research on a problem, rather than citations or topical relevance. Strikingly, even frontier models struggle to identify which prior research is helpful -- lots of room for future work! Paper, Code, Data: t.co/fynHV2sx1S
Sohyeon Kim @ COLM@ohmyksh·AI can increasingly make progress on open problems like Navier-Stokes. Yet defining a new problem still relies on human research taste. Introducing ScholarCatalyst, a benchmark built from AI researchers’ firsthand accounts of what inspired their work.
New blog post with @perryadong on what we need for robots to be broadly useful in the real world. t.co/jxsNeMUhFg Reliability is the one of the biggest open challenges in AI right now. Current models work out okay if a person will be reviewing the outputs (eg drafting code), but it will become more of a bottleneck as we want systems to act with more autonomy and more trust.
Perry Dong@perryadong·What will be the “RLHF” moment for robotics? What will it take to get robotics to where LLMs are today and beyond? New blog post with @chelseabfinn sharing some thoughts on the state of RL for frontier robotics models and what's missing 👇 Blog: pd-perry.github.io/posts/post-tra…
RL for dynamic tasks requires handling latency. Building on EXPO-FT, we let the base VLA operate on older images while a small edit policy operates in real time. Outperforms RTC by a significant margin, across the board. Paper: pd-perry.github.io/real-time-expo…
Perry Dong@perryadong·Introducing Real-Time EXPO-FT – Fast and Reliable RL for Real-Time VLA Policies! Real-Time EXPO-FT unlocks π0.5 on challenging dynamic tasks, such as balancing a ball on a plate and striking a ball into the goal (1/6)
Project led by @perryadong and @khhung906 with @DorsaSadigh at @StanfordAILab. Plus some related recent work from friends at Berkeley/Siemens:
E Harrison@ehharrison4·Asynchronous VLA inference reduces inference delay, but breaks the Markovian assumption necessary for RL fine-tuning. How can we enable RL fine-tuning of VLAs with async inference? We introduce ARLI: Asynchronous RL with Intermediate Information! …rl-intermediate-information.github.io (1/n)
A video from a Pi robot deployed at Dandelion Chocolate, fully autonomous w/ no interventions. 🤖 Deploying robots has taught us surprising lessons about the gap between proof-of-concept (i.e. building one box) and real-world utility (productively building boxes for hours). I expected that the hard part is building the box, since it’s the most dexterous, but that wasn't what we found. Counterintuitively, the hardest part was reliably stacking the boxes. Our original table-mounted robot had poor visibility of the stack without special separately-mounted cameras. Plus, stacking requires more generalization (each box is placed in a different location), and an imprecisely-placed box can lead the entire stack to collapse many boxes later. We recently switched this deployment over to a mobile robot, and it's fun to watch the robot being completely self sufficient for multiple hours. 🙂 Data and feedback from real world use-cases like these are quite valuable for the π pre-trained model as we scale!
Congrats to @zipengfu, @chenwang_j, and co on the release!
Reward AI@RewardAI_·Introducing OM-1, our first robot foundation model, zero-shot generalizing to any robot: table-top arms, industrial arms and humanoids. - learned directly from human manipulation data - no teleop/robot data - close to human-level dexterity and efficiency - multi-robot collab
One of the most important aspects of scientific discovery is deciding where to draw insights from. While LLMs are promising tools for science, we lack datasets & evaluations for this step. Help contribute to a public dataset for exactly this: tinyurl.com/45b9ykae
Sohyeon Kim@ohmyksh·We’re asking the research community to help us build a benchmark for research taste. Scientific discovery starts with a fundamental step: which prior work is worth building on? We want to capture this undocumented layer through our collective knowledge. Please sign up: t.co/T4vfwQnHUY ↓
Pretraining a Q-function often doesn’t actually help RL finetuning, compared to initializing Q from scratch. We find that pretraining Q-functions on data from diverse policies is critical to see improvements from pretraining. Paper: arxiv.org/abs/2607.27203 x.com/perryadong/sta…
I'm giving a talk tomorrow at ICML on emergent physical generalization, including π0.7 🤖 3:15 pm @ SCALE workshop in Ballroom 201 scale-icml-2026.github.io
I'm giving a talk on how we can move beyond the scalar reward bottleneck for both robotics & LLMs. ICML RLxF workshop tomorrow at 1:30 pm. x.com/shaohua0116/st…
We’ve been approaching reward supervision for robots the wrong way. I think freeform preferences are part of the answer. A short 🧵
Long term, we need reward models to capture all aspects of performance, like success, outcome quality, and speed. This also includes task-specific axes like: - was the PB spread evenly? - was the apple slightly bruised while bagging it? - was the furniture bumped or scratched?
LLM RL optimizes for sequential reasoning We also optimize over the reasoning strategy, incl parallel trains of thought, aggregation of parallel traces, & sequential reasoning This allows the model to better explore & allocate compute at test time t.co/DkTSllkmvp
Can we translate a rough sense for what to do + VLA prior into successful behavior? Flow reversal steering: 1) runs the VLA's flow ODE backwards to back out noise that's closest to coarse traj 2) runs flow forwards to get closest good behavior Paper: t.co/FUDqDEpeJq
How does test-time scaling impact robots? We find that larger models, more thinking, and more context help significantly for some prompts but not others. Like LLMs, we can also train a router to for a better performance/latency tradeoff! Paper: jadee-dao.github.io/direct/ x.com/_jadelynn/stat…
Can robot foundation models collaborate with themself? We finetune a VLA to be able to control any robot in a team. - matches or outperforms training separate models or a single centralized model for all robots - readily scales to large teams Paper: t.co/yqdSOQ7ead
Scaling RL to long horizons remains a major challenge. Long-horizon Q-learning (LQL) prevents compounding bootstrapping errors by bounding the difference in value over long horizons. It shows large gains over 1-step TD and n-step returns! Paper: arxiv.org/abs/2605.05812 x.com/armaanabraham/…
How can VLAs achieve 95+% reliability? Using RL post-training with EXPO-FT: - π0.5 improves to 30/30 success on all 8 tasks tested - uses only 19 min of RL data on average Paper & videos: pd-perry.github.io/expo-ft/ x.com/perryadong/sta…
EXPO-FT builds on EXPO (arxiv.org/abs/2507.07986) The first idea of EXPO is to train a small Gaussian policy, to edit the VLA's actions. We also continuously distill successful trajectories into the base VLA.
