Publications (16)
Engagement and Disclosures in LLM-Powered Cognitive Behavioral Therapy Exercises: A Factorial Design Comparing the Influence of a Robot vs. Chatbot Over Time
Mina Kian, Mingyu Zong, Katrin Fischer +10
Gemini: A Family of Highly Capable Multimodal Models
Gemini Team, Rohan Anil, Sebastian Borgeaud +1340
When MAML Can Adapt Fast and How to Assist When It Cannot
Sébastien M. R. Arnold, Shariq Iqbal, Fei Sha
Reducing the variance in online optimization by transporting past gradients
Sébastien M. R. Arnold, Pierre-Antoine Manzagol, Reza Babanezhad +2
Analyzing the Variance of Policy Gradient Estimators for the Linear-Quadratic Regulator
James A. Preiss, Sébastien M. R. Arnold, Chen-Yu Wei +1
Embedding Adaptation is Still Needed for Few-Shot Learning
Sébastien M. R. Arnold, Fei Sha
Graders should cheat: privileged information enables expert-level automated evaluations
Jin Peng Zhou, Sébastien M. R. Arnold, Nan Ding +3
Accelerating SGD for Distributed Deep-Learning Using Approximated Hessian Matrix
Sébastien M. R. Arnold, Chunming Wang
Can Long-Context Language Models Subsume Retrieval, RAG, SQL, and More?
Jinhyuk Lee, Anthony Chen, Zhuyun Dai +16
Shapechanger: Environments for Transfer Learning
Sébastien M. R. Arnold, Tsam Kiu Pun, Théo-Tim J. Denisart +1
learn2learn: A Library for Meta-Learning Research
Sébastien M. R. Arnold, Praateek Mahajan, Debajyoti Datta +2
RoboCLIP: One Demonstration is Enough to Learn Robot Policies
Sumedh A Sontakke, Jesse Zhang, Sébastien M. R. Arnold +5
A Domain-Agnostic Approach for Characterization of Lifelong Learning Systems
Megan M. Baker, Alexander New, Mario Aguilar-Simon +44
Gemma 2: Improving Open Language Models at a Practical Size
Gemma Team, Morgane Riviere, Shreya Pathak +195
Policy-Induced Self-Supervision Improves Representation Finetuning in Visual RL
Sébastien M. R. Arnold, Fei Sha
Uniform Sampling over Episode Difficulty
Sébastien M. R. Arnold, Guneet S. Dhillon, Avinash Ravichandran +1