Publications
Explore a selection of our recent research on some of the most complex and interesting challenges in AI.
240 publications
-
- 10 December 2023
- Improving neural network representations using human similarity judgments
-
- 9 December 2023
- Distributional Bellman Operators over Mean-embeddings
-
- 8 December 2023
- POMRL: No-Regret Learning-to-Plan with IncreasingHorizons
-
- 7 December 2023
- Revisiting Dynamic Evaluation:Online Adaptation for LLMs
-
- 6 December 2023
- A Benchmark for Reasoning with Spatial Prepositions
-
- 6 December 2023
- Generative agent-based modeling with actions grounded in physical, social, or digital space using Concordia
-
- 6 December 2023
- SEAHORSE: A Multilingual, Multifaceted Dataset for Summarization Evaluation
-
- 6 December 2023
- MingOfficial: A Ming Official Career Dataset and a Historical Context-Aware Representation Learning Framework
-
- 5 December 2023
- RoboCat: A Self-Improving Foundation Agent for Robotic Manipulation
-
- 5 December 2023
- Gaussian Process Probes (GPP) for Uncertainty-Aware Probing
-
- 4 December 2023
- Small batch deep reinforcement learning
-
- 2 December 2023
- RLHF and IIA: Perverse Incentives
-
- 29 November 2023
- Universal Self-Consistency with Large Language Models
-
- 29 November 2023
- SODA: Bottleneck Diffusion Models for Representation Learning
-
- 29 November 2023
- Unsupervised Keypoints with Stable Diffusion
-
- 29 November 2023
- Accelerating Neural Field Training via Langevin Monte-Carlo Sampling
-
- 27 November 2023
- Replay Across Experiments
-
- 23 November 2023
- Scalable AI Safety via Doubly-Efficient Debate
-
- 17 November 2023
- No agent is an island: A social path to human-like artificial intelligence
-
- 14 November 2023
- GraphCast: Learned Global Weather Forecasting
-
- 14 November 2023
- Report of the 1st Workshop on Generative AI and Law
-
- 14 November 2023
- DiLoCo: Distributed Low-Communication Training of Language Models
-
- 10 November 2023
- Emotions and courtship help bonded pairs cooperate, but emotional agents are vulnerable to deceit
-
- 8 November 2023
- Role Play with Large Language Models
-
- 6 November 2023
- Finding Increasingly Large Extremal Graphs with AlphaZero and Tabu Search
-
- 3 November 2023
- RT-Trajectory: Robotic Task Generalization via Hindsight Trajectory Sketches
-
- 3 November 2023
- Grammar Prompting for Domain-Specific Language Generation with Large Language Models
-
- 2 November 2023
- Optimistic Natural Policy Gradient: a Simple Efficient Policy Optimization Framework for Online RL
-
- 2 November 2023
- Optimistic Meta-Gradients
-
- 1 November 2023
- RoboVQA: Multimodal Long-Horizon Reasoning for Robotics