CF
Chelsea Finn
cs.LGcs.AIcs.ROcs.CVstat.MLcs.CLcs.NEcs.CYcs.MAcs.SY
On Valency
published · living versionsW_87fa8gnp·v1 · currentpublished
Unsupervised Learning for Physical Interaction through Video Prediction
with Ian Goodfellow, Sergey Levine
1 version
Preprints & journals
312 papers in the corpus · 2015–2026Librarian Agents: Training LLMs to Curate Long-Context Workspaces that Anticipate Future Queries2610.22273v1 · Anikait Singh, Teresa Zhang, Yoonho Lee et al.2026 · 0 citationsarXiv
Generative Value Classifier2610.22497v1 · Alexander Swerdlow, Perry Dong, Chelsea Finn2026 · 0 citationsarXiv
Mulligan: Performance-Guided Data Collection for Efficient On-Robot Learning2610.05882v1 · Lars Ankile, Perry Dong, Rohan Bhowmik et al.2026 · 0 citationsarXiv
ScholarCatalyst: A Benchmark for Retrieving Papers That Inspire New Research2610.02202v1 · Sohyeon Kim, Yoonho Lee, Bo Liu et al.2026 · 0 citationsarXiv
Reinforcement Learning for Real-Time Vision-Language-Action Policies2609.18207v1 · Perry Dong, Kuo-Han Hung, Dorsa Sadigh et al.2026 · 0 citationsarXiv
WHALE: A Simple Recipe for Joint Harness-Weight Optimization2609.00196v1 · Haechan Kim, Yoonho Lee, Gisang Lee et al.2026 · 0 citationsarXiv
Q-Learning With World Models2608.17163v1 · Perry Dong, Yueru Jia, Chelsea Finn et al.2026 · 0 citationsarXiv
Pre-training Visual Dexterity in Simulation2608.15917v2 · Sarthak Kamat, Adam Rashid, Satvik Sharma et al.2026 · 0 citationsarXiv
SpeedTuning: Speeding Up Policy Execution with Lightweight Reinforcement Learning2608.09138v2 · David D. Yuan, Tony Z. Zhao, Kaylee Burns et al.2026 · 0 citations2025 IEEE International Conference on Robotics and Automation (ICRA), pp. 1184-1192, 2025
Do You Really Need to Pretrain Q-Functions for Online RL Fine-Tuning?2607.27203v2 · Perry Dong, Ron Polonsky, Dorsa Sadigh et al.2026 · 0 citationsarXiv
LLM-as-a-Verifier: A General-Purpose Verification Framework2607.05391v2 · Jacky Kwok, Shulu Li, Pranav Atreya et al.2026 · 0 citationsarXiv
Freeform Preference Learning for Robotic Manipulation2606.32027v3 · Marcel Torne, Anubha Mahajan, Abhijnya Bhat et al.2026 · 0 citationsarXiv
SPIRAL: Learning to Search and Aggregate2606.23595v2 · Jubayer Ibn Hamid, Ifdita Hasan Orney, Michael Y. Li et al.2026 · 0 citationsarXiv
Improving Robotic Generalist Policies via Flow Reversal Steering2606.13675v2 · Andy Tang, William Chen, Andrew Wagenmaker et al.2026 · 0 citationsarXiv
CHORUS: Decentralized Multi-Embodiment Collaboration with One VLA Policy2606.12352v1 · Ria Doshi, Tian Gao, Annie Chen et al.2026 · 0 citationsarXiv
DIRECT: When and Where Should You Allocate Test-Time Compute in Embodied Planners?2606.12402v2 · Jadelynn Dao, Milan Ganai, Yasmina Abukhadra et al.2026 · 0 citationsarXiv
Ego-Pi: VLA Fine-Tuning for Ego-Centric Human and Robot Data2606.08107v1 · Ji Woong Kim, Ke Wang, Zipeng Fu et al.2026 · 0 citationsarXiv
EXPO-FT: Sample-Efficient Reinforcement Learning Finetuning for Vision-Language-Action Models2605.25477v2 · Perry Dong, Kuo-Han Hung, Tian Gao et al.2026 · 0 citationsarXiv
Long-Horizon Q-Learning: Accurate Value Learning via n-Step Inequalities2605.05812v2 · Armaan A. Abraham, Lucy Xiaoyang Shi, Chelsea Finn2026 · 0 citationsarXiv
Open-H-Embodiment: A Large-Scale Dataset for Enabling Foundation Models in Medical Robotics2604.21017v3 · Juo-Tung Chen, Jesse Haworth, Xinhao Chen et al.2026 · 1 citationarXiv
FASTER: Value-Guided Sampling for Fast RL2604.19730v1 · Perry Dong, Alexander Swerdlow, Dorsa Sadigh et al.2026 · 0 citationsarXiv
Poly-EPO: Training Exploratory Reasoning Models2604.17654v3 · Ifdita Hasan Orney, Jubayer Ibn Hamid, Shreya S Ramanujam et al.2026 · 0 citationsarXiv
: a Steerable Generalist Robotic Foundation Model with Emergent Capabilities2604.15483v2 · Physical Intelligence, Bo Ai, Ali Amin et al.2026 · 0 citationsarXiv
GIANTS: Generative Insight Anticipation from Scientific Literature2604.09793v1 · Joy He-Yueya, Anikait Singh, Ge Gao et al.2026 · 0 citationsarXiv
World Action Verifier: Self-Improving World Models via Forward-Inverse Asymmetry2604.01985v2 · Yuejiang Liu, Fan Feng, Lingjing Kong et al.2026 · 0 citationsarXiv
Meta-Harness: End-to-End Optimization of Model Harnesses2603.28052v1 · Yoonho Lee, Roshen Nair, Qizheng Zhang et al.2026 · 2 citationsarXiv
Data Analogies Enable Efficient Cross-Embodiment Transfer2603.06450v2 · Jonathan Yang, Chelsea Finn, Dorsa Sadigh2026 · 0 citationsarXiv
MEM: Multi-Scale Embodied Memory for Vision Language Action Models2603.03596v2 · Marcel Torne, Karl Pertsch, Homer Walke et al.2026 · 0 citationsarXiv
RoboMME: Benchmarking and Understanding Memory for Robotic Generalist Policies2603.04639v3 · Yinpei Dai, Hongze Fu, Jayjun Lee et al.2026 · 0 citationsarXiv
VLAW: Iterative Co-Improvement of Vision-Language-Action Policy and World Model2602.12063v2 · Yanjiang Guo, Tony Lee, Lucy Xiaoyang Shi et al.2026 · 0 citationsarXiv
Scaling Verification Can Be More Effective than Scaling Policy Learning for Vision-Language-Action Alignment2602.12281v2 · Jacky Kwok, Xilun Zhang, Mengdi Xu et al.2026 · 0 citationsarXiv
SteerVLA: Steering Vision-Language-Action Models in Long-Tail Driving Scenarios2602.08440v2 · Tian Gao, Celine Tan, Catherine Glossop et al.2026 · 0 citationsarXiv
TQL: Scaling Q-Functions with Transformers by Preventing Attention Collapse2602.01439v1 · Perry Dong, Kuo-Han Hung, Alexander Swerdlow et al.2026 · 0 citationsarXiv
Cosmos Policy: Fine-Tuning Video Models for Visuomotor Control and Planning2601.16163v1 · Moo Jin Kim, Yihuai Gao, Tsung-Yi Lin et al.2026 · 0 citationsarXiv
RoboReward: General-Purpose Vision-Language Reward Models for Robotics2601.00675v2 · Tony Lee, Andrew Wagenmaker, Karl Pertsch et al.2026 · 0 citationsarXiv
Emergence of Human to Robot Transfer in Vision-Language-Action Models2512.22414v1 · Simar Kareer, Karl Pertsch, James Darpinian et al.2025 · 2 citationsarXiv
PolaRiS: Scalable Real-to-Sim Evaluations for Generalist Robot Policies2512.16881v2 · Arhan Jain, Mingtong Zhang, Kanav Arora et al.2025 · 2 citationsarXiv
Posterior Behavioral Cloning: Pretraining BC Policies for Efficient RL Finetuning2512.16911v1 · Andrew Wagenmaker, Perry Dong, Raymond Tsao et al.2025 · 0 citationsarXiv
Invariance Co-training for Robot Visual Generalization2512.05230v1 · Jonathan Yang, Chelsea Finn, Dorsa Sadigh2025 · 0 citationsarXiv
: a VLA That Learns From Experience2511.14759v2 · Physical Intelligence, Ali Amin, Raichelle Aniceto et al.2025 · 0 citationsarXiv
Feedback Descent: Open-Ended Text Optimization via Pairwise Comparison2511.07919v2 · Yoonho Lee, Joseph Boen, Chelsea Finn2025 · 0 citationsarXiv
MemER: Scaling Up Memory for Robot Control via Experience Retrieval2510.20328v1 · Ajay Sridhar, Jennifer Pan, Satvik Sharma et al.2025 · 0 citationsarXiv
SutureBot: A Precision Framework & Benchmark For Autonomous End-to-End Suturing2510.20965v1 · Jesse Haworth, Juo-Tung Chen, Nigel Nelson et al.2025 · 1 citationarXiv
Ctrl-World: A Controllable Generative World Model for Robot Manipulation2510.10125v3 · Yanjiang Guo, Lucy Xiaoyang Shi, Jianyu Chen et al.2025 · 0 citationsarXiv
Value Flows2510.07650v4 · Perry Dong, Chongyi Zheng, Chelsea Finn et al.2025 · 0 citationsarXiv
RLAD: Training LLMs to Discover Abstractions for Solving Reasoning Problems2510.02263v1 · Yuxiao Qu, Anikait Singh, Yoonho Lee et al.2025 · 0 citationsarXiv
Polychromic Objectives for Reinforcement Learning2509.25424v6 · Jubayer Ibn Hamid, Ifdita Hasan Orney, Ellen Xu et al.2025 · 0 citationsarXiv
Self-Guided Action Diffusion2508.12189v1 · Rhea Malhotra, Yuejiang Liu, Chelsea Finn2025 · 0 citationsarXiv
EXPO: Stable Reinforcement Learning with Expressive Policies2507.07986v3 · Perry Dong, Qiyang Li, Dorsa Sadigh et al.2025 · 0 citationsarXiv
SRT-H: A hierarchical framework for autonomous surgery via language-conditioned imitation learning.40632876 · Kim, Ji Woong Brian, Chen, Juo-Tung, Hansen, Pascal et al.2025 · 113 citationsScience robotics. 2025;10(104):eadt5254
Career total: 370 works. 312 are in this corpus.Showing the 50 most recent.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.