Research
Publications
-
- Date
- Title
- Revisiting Dynamic Evaluation:Online Adaptation for LLMs
- Authors
- Venue
-
- Date
- Title
- A Benchmark for Reasoning with Spatial Prepositions
- Authors
- Venue
-
- Date
- Title
- SEAHORSE: A Multilingual, Multifaceted Dataset for Summarization Evaluation
- Authors
- Venue
-
- Date
- Title
- RoboCat: A Self-Improving Foundation Agent for Robotic Manipulation
- Authors
- Venue
-
- Date
- Title
- Gaussian Process Probes (GPP) for Uncertainty-Aware Probing
- Authors
- Venue
-
- Date
- Title
- Small batch deep reinforcement learning
- Authors
- Venue
-
- Date
- Title
- RLHF and IIA: Perverse Incentives
- Authors
- Venue
-
- Date
- Title
- Unsupervised Keypoints with Stable Diffusion
- Authors
- Venue
-
- Date
- Title
- Universal Self-Consistency with Large Language Models
- Authors
- Venue
-
- Date
- Title
- SODA: Bottleneck Diffusion Models for Representation Learning
- Authors
- Venue
-
- Date
- Title
- Accelerating Neural Field Training via Langevin Monte-Carlo Sampling
- Authors
- Venue
-
- Date
- Title
- Replay Across Experiments
- Authors
- Venue
-
- Date
- Title
- Scalable AI Safety via Doubly-Efficient Debate
- Authors
- Venue
-
- Date
- Title
- No agent is an island: A social path to human-like artificial intelligence
- Authors
- Venue
-
- Date
- Title
- GraphCast: Learned Global Weather Forecasting
- Authors
- Venue
-
- Date
- Title
- Report of the 1st Workshop on Generative AI and Law
- Authors
- Venue
-
- Date
- Title
- DiLoCo: Distributed Low-Communication Training of Language Models
- Authors
- Venue
-
- Date
- Title
- Emotions and courtship help bonded pairs cooperate, but emotional agents are vulnerable to deceit
- Authors
- Venue