2.3k citations · 7.8k across the 98 of their papers we have counts for
14 papers · 1 filter
Base Models Can Reason By Taking a Cue From Training Data
Sophie L. Wang, Amil Dravid, Rulin Shao +3
In this paper, we study how training data creates associations between the tokens at the start of a base model's response and the reasoning behavior that follows. First, we demonst…
Neuron Populations Exhibit Divergent Selectivity with Scale
Amil Dravid, Yasaman Bahri, Alexei A. Efros +1
We investigate whether neuron populations within neural networks evolve predictably with scale, extending scaling laws beyond macroscopic observables such as loss. To probe this qu…
Prioritized Generative Replay
Renhao Wang, Kevin Frans, Pieter Abbeel +2
Sample-efficient online reinforcement learning often uses replay buffers to store experience for reuse when updating the value function. However, uniform replay is inefficient, sin…
Internet Explorer: Targeted Representation Learning on the Open Web
Alexander C. Li, Ellis Brown, Alexei A. Efros +1
Modern vision models typically rely on fine-tuning general-purpose models pre-trained on large, static datasets. These general-purpose models only capture the knowledge within thei…
Understanding Collapse in Non-Contrastive Siamese Representation Learning
Alexander C. Li, Alexei A. Efros, Deepak Pathak
Contrastive methods have led a recent surge in the performance of self-supervised representation learning (SSL). Recent methods like BYOL or SimSiam purportedly distill these contr…
Learning to Learn with Generative Models of Neural Network Checkpoints
William Peebles, Ilija Radosavovic, Tim Brooks +2
We explore a data-driven approach for learning to optimize neural networks. We construct a dataset of neural network checkpoints and train a generative model on the parameters. In…
Self-Supervised Policy Adaptation during Deployment
Nicklas Hansen, Rishabh Jangir, Yu Sun +5
In most real world scenarios, a policy trained by reinforcement learning in one environment needs to be deployed in another, potentially quite different environment. However, gener…
Unsupervised Domain Adaptation through Self-Supervision
Yu Sun, Eric Tzeng, Trevor Darrell +1
This paper addresses unsupervised domain adaptation, the setting where labeled training data is available on a source domain, but the goal is to have good performance on a target d…
Test-Time Training with Self-Supervision for Generalization under Distribution Shifts
Yu Sun, Xiaolong Wang, Zhuang Liu +3
In this paper, we propose Test-Time Training, a general approach for improving the performance of predictive models when training and test data come from different distributions. W…
Learning to Control Self-Assembling Morphologies: A Study of Generalization via Modularity
Deepak Pathak, Chris Lu, Trevor Darrell +2
Contemporary sensorimotor learning approaches typically start with an existing complex agent (e.g., a robotic arm), which they learn to control. In contrast, this paper investigate…
Dataset Distillation
Tongzhou Wang, Jun-Yan Zhu, Antonio Torralba +1
Model distillation aims to distill the knowledge of a complex model into a simpler one. In this paper, we consider an alternative formulation called dataset distillation: we keep t…
Large-Scale Study of Curiosity-Driven Learning
Yuri Burda, Harri Edwards, Deepak Pathak +3
Reinforcement learning algorithms rely on carefully engineering environment rewards that are extrinsic to the agent. However, annotating each environment with hand-designed, dense…
Zero-Shot Visual Imitation
Deepak Pathak, Parsa Mahmoudieh, Guanghao Luo +7
The current dominant paradigm for imitation learning relies on strong supervision of expert actions to learn both 'what' and 'how' to imitate. We pursue an alternative paradigm whe…
Curiosity-driven Exploration by Self-supervised Prediction
Deepak Pathak, Pulkit Agrawal, Alexei A. Efros +1
In many real-world scenarios, rewards extrinsic to the agent are extremely sparse, or absent altogether. In such cases, curiosity can serve as an intrinsic reward signal to enable…