142 citations · 356 across the 20 of their papers we have counts for
20 papers
Towards Embodiment Scaling Laws in Robot Locomotion
Bo Ai, Liu Dai, Nico Bohlinger +7
Cross-embodiment generalization underpins the vision of building generalist embodied agents for any robot, yet its enabling factors remain poorly understood. We investigate embodim…
Rewarding Progress: Scaling Automated Process Verifiers for LLM Reasoning
Amrith Setlur, Chirag Nagpal, Adam Fisch +6
A promising approach for improving reasoning in large language models is to use process reward models (PRMs). PRMs provide feedback at each step of a multi-step reasoning trace, po…
RL on Incorrect Synthetic Data Scales the Efficiency of LLM Math Reasoning by Eight-Fold
Amrith Setlur, Saurabh Garg, Xinyang Geng +3
Training on model-generated synthetic data is a promising approach for finetuning LLMs, but it remains unclear when it helps or hurts. In this paper, we investigate this question f…
Sequential Modeling Enables Scalable Learning for Large Vision Models
Yutong Bai, Xinyang Geng, Karttikeya Mangalam +5
We introduce a novel sequential modeling approach which enables learning a Large Vision Model (LVM) without making use of any linguistic data. To do this, we define a common format…
Action-Quantized Offline Reinforcement Learning for Robotic Skill Learning
Jianlan Luo, Perry Dong, Jeffrey Wu +3
The offline reinforcement learning (RL) paradigm provides a general recipe to convert static behavior datasets into policies that can perform better than the policy that collected…
Latent Conservative Objective Models for Data-Driven Crystal Structure Prediction
Han Qi, Xinyang Geng, Stefano Rando +3
In computational chemistry, crystal structure prediction (CSP) is an optimization problem that involves discovering the lowest energy stable crystal structure for a given chemical…
Multi-Stage Cable Routing through Hierarchical Imitation Learning
Jianlan Luo, Charles Xu, Xinyang Geng +5
We study the problem of learning to perform multi-stage robotic manipulation tasks, with applications to cable routing, where the robot must route a cable through a series of clips…
The False Promise of Imitating Proprietary LLMs
Arnav Gudibande, Eric Wallace, Charlie Snell +5
An emerging method to cheaply improve a weaker language model is to finetune it on outputs from a stronger model, such as a proprietary system like ChatGPT (e.g., Alpaca, Self-Inst…
Offline Q-Learning on Diverse Multi-Task Data Both Scales And Generalizes
Aviral Kumar, Rishabh Agarwal, Xinyang Geng +2
The potential of offline reinforcement learning (RL) is that high-capacity models trained on large, heterogeneous datasets can lead to agents that generalize broadly, analogously t…
Towards Better Few-Shot and Finetuning Performance with Forgetful Causal Language Models
Hao Liu, Xinyang Geng, Lisa Lee +4
Large language models (LLM) trained using the next-token-prediction objective, such as GPT3 and PaLM, have revolutionized natural language processing in recent years by showing imp…
Multimodal Masked Autoencoders Learn Transferable Representations
Xinyang Geng, Hao Liu, Lisa Lee +3
Building scalable models to learn from diverse, multimodal data remains an open challenge. For vision-language data, the dominant approaches are based on contrastive learning objec…
Design-Bench: Benchmarks for Data-Driven Offline Model-Based Optimization
Brandon Trabucco, Xinyang Geng, Aviral Kumar +1
Black-box model-based optimization (MBO) problems, where the goal is to find a design input that maximizes an unknown objective function, are ubiquitous in a wide range of domains,…
Conservative Objective Models for Effective Offline Model-Based Optimization
Brandon Trabucco, Aviral Kumar, Xinyang Geng +1
Computational design problems arise in a number of settings, from synthetic biology to computer architectures. In this paper, we aim to solve data-driven model-based optimization (…
Variable-Shot Adaptation for Online Meta-Learning
Tianhe Yu, Xinyang Geng, Chelsea Finn +1
Few-shot meta-learning methods consider the problem of learning new tasks from a small, fixed number of examples, by meta-learning across static data from a set of previous tasks.…
Meta-Reinforcement Learning Robust to Distributional Shift via Model Identification and Experience Relabeling
Russell Mendonca, Xinyang Geng, Chelsea Finn +1
Reinforcement learning algorithms can acquire policies for complex tasks autonomously. However, the number of samples required to learn a diverse set of skills can be prohibitively…
Rewriting History with Inverse RL: Hindsight Inference for Policy Improvement
Benjamin Eysenbach, Xinyang Geng, Sergey Levine +1
Multi-task reinforcement learning (RL) aims to simultaneously learn policies for solving many tasks. Several prior works have found that relabeling past experience with different r…
Dynamical Distance Learning for Semi-Supervised and Unsupervised Skill Discovery
Kristian Hartikainen, Xinyang Geng, Tuomas Haarnoja +1
Reinforcement learning requires manual specification of a reward function to learn a task. While in principle this reward function only needs to specify the task goal, in practice…
Real-Time User-Guided Image Colorization with Learned Deep Priors
Richard Zhang, Jun-Yan Zhu, Phillip Isola +4
We propose a deep learning approach for user-guided image colorization. The system directly maps a grayscale image, along with sparse, local user "hints" to an output colorization…
Automatic Goal Generation for Reinforcement Learning Agents
Carlos Florensa, David Held, Xinyang Geng +1
Reinforcement learning is a powerful technique to train an agent to perform a task. However, an agent that is trained using reinforcement learning is only capable of achieving the…
Deep Reinforcement Learning for Tensegrity Robot Locomotion
Marvin Zhang, Xinyang Geng, Jonathan Bruce +5
Tensegrity robots, composed of rigid rods connected by elastic cables, have a number of unique properties that make them appealing for use as planetary exploration rovers. However,…