Xinyang Geng

发表

Rewriting History with Inverse RL: Hindsight Inference for Policy Improvement pdf

Sergey Levine, Ruslan Salakhutdinov, Xinyang Geng, 2020, NeurIPS.

Deep reinforcement learning for tensegrity robot locomotion

Sergey Levine, Pieter Abbeel, Vytas SunSpiral, 2016, 2017 IEEE International Conference on Robotics and Automation (ICRA).

Automatic Goal Generation for Reinforcement Learning Agents pdf

Pieter Abbeel, David Held, Xinyang Geng, 2017, ICML.

Variable-Shot Adaptation for Online Meta-Learning pdf

Sergey Levine, Chelsea Finn, Tianhe Yu, 2020, ArXiv.

Real-time user-guided image colorization with learned deep priors

Alexei A. Efros, Jun-Yan Zhu, Richard Zhang, 2017, ACM Trans. Graph..

Design-Bench: Benchmarks for Data-Driven Offline Model-Based Optimization

S. Levine, Aviral Kumar, Xinyang Geng, 2022, ICML.

Conservative Objective Models for Effective Offline Model-Based Optimization

Sergey Levine, Aviral Kumar, Brandon Trabucco, 2021, ICML.

Dynamical Distance Learning for Semi-Supervised and Unsupervised Skill Discovery

S. Levine, Tuomas Haarnoja, Xinyang Geng, 2019, ICLR.

Consistent Meta-Reinforcement Learning via Model Identification and Experience Relabeling

Sergey Levine, Chelsea Finn, Xinyang Geng, 2019 .

Multimodal Masked Autoencoders Learn Transferable Representations

S. Levine, P. Abbeel, Xinyang Geng, 2022, ArXiv.

FCM: Forgetful Causal Masking Makes Causal Language Models Better Zero-Shot Learners

S. Levine, P. Abbeel, Igor Mordatch, 2022, ArXiv.

Offline Q-Learning on Diverse Multi-Task Data Both Scales And Generalizes

S. Levine, Rishabh Agarwal, G. Tucker, 2022, ArXiv.

Towards Better Few-Shot and Finetuning Performance with Forgetful Causal Language Models

S. Levine, P. Abbeel, Igor Mordatch, 2022, 2210.13432.

Pretraining strategies for effective promoter-driven gene expression prediction

Aniketh Janardhan Reddy, Nilah M. Ioannidis, Amy X. Lu, 2023, bioRxiv.

Meta-Reinforcement Learning Robust to Distributional Shift via Model Identification and Experience Relabeling pdf

Sergey Levine, Chelsea Finn, Xinyang Geng, 2020, ArXiv.

Solidification of uranium tailings using alkali-activated slag mixed with natural zeolite

Xinyang Geng, Cheng Chen, Shijiao Yang, 2022, Nuclear Engineering and Technology.

The False Promise of Imitating Proprietary LLMs

S. Levine, P. Abbeel, Xinyang Geng, 2023, ArXiv.

Offline Q-Learning on Diverse Multi-Task Data Both Scales And Generalizes

S. Levine, Rishabh Agarwal, G. Tucker, 2022, ICLR.

Multistage Cable Routing Through Hierarchical Imitation Learning

S. Levine, S. Schaal, Jianlan Luo, 2023, IEEE Transactions on Robotics.

Dynamical Distance Learning for Unsupervised and Semi-Supervised Skill Discovery pdf

Sergey Levine, Xinyang Geng, Tuomas Haarnoja, 2019, ArXiv.

Action-Quantized Offline Reinforcement Learning for Robotic Skill Learning

Aviral Kumar, Xinyang Geng, Sergey Levine, 2023, CoRL.

Sequential Modeling Enables Scalable Learning for Large Vision Models

Xinyang Geng, Amir Bar, Alexei A. Efros, 2023, ArXiv.

RL on Incorrect Synthetic Data Scales the Efficiency of LLM Math Reasoning by Eight-Fold

Amrith Rajagopal Setlur, Xinyang Geng, Saurabh Garg, 2024, ArXiv.

Strategies for effectively modelling promoter-driven gene expression using transfer learning

Aniketh Janardhan Reddy, Nilah M. Ioannidis, Amy X. Lu, 2023, bioRxiv.

Conservative Objective Models for Biological Sequence Design

Aniketh Janardhan Reddy, Nilah M. Ioannidis, Xinyang Geng, 2023 .