Tianjun Zhang

发表

NovelD: A Simple yet Effective Exploration Criterion

K. Keutzer, Joseph E. Gonzalez, Huazhe Xu, 2021, NeurIPS.

Learning Self-Supervised Representations of Code Functionality

P. Abbeel, I. Stoica, Joseph Gonzalez, 2021 .

Contrastive Learning as Goal-Conditioned Reinforcement Learning

S. Levine, R. Salakhutdinov, Benjamin Eysenbach, 2022, ArXiv.

Graph Backup: Data Efficient Backup Exploiting Markovian Transitions

Edward Grefenstette, Tim Rocktaschel, Tianjun Zhang, 2022, ArXiv.

Making Linear MDPs Practical via Contrastive Representation Learning

D. Schuurmans, Joseph E. Gonzalez, Bo Dai, 2022, ICML.

Efficient Planning in a Compact Latent Action Space

Michael Janner, Edward Grefenstette, Tim Rocktaschel, 2022, International Conference on Learning Representations.

Spectral Decomposition Representation for Reinforcement Learning

D. Schuurmans, Joseph E. Gonzalez, Bo Dai, 2022, ArXiv.

Multi-objective Optimization by Learning Space Partitions

Tianjun Zhang, Yuandong Tian, Tian Guo, 2021, ICLR.

Contrastive Learning as Goal-Conditioned Reinforcement Learning

S. Levine, R. Salakhutdinov, Benjamin Eysenbach, 2022, ArXiv.

Masked Layer Distillation: Fast and Robust Training Through Knowledge Transfer Normalization

K. Keutzer, Paras Jain, Tianjun Zhang, 2021 .

Multitask Vision-Language Prompt Tuning

Trevor Darrell, K. Keutzer, Sheng Shen, 2022, IEEE Workshop/Winter Conference on Applications of Computer Vision.

Latent Variable Representation for Reinforcement Learning

D. Schuurmans, Sujay Sanghavi, Bo Dai, 2022, 2212.08765.

TEMPERA: Test-Time Prompting via Reinforcement Learning

D. Schuurmans, Xuezhi Wang, Joseph Gonzalez, 2022, ArXiv.

Multi-Agent Collaboration via Reward Attribution Decomposition pdf

Yuandong Tian, Kurt Keutzer, Joseph E. Gonzalez, 2020, ArXiv.

Learning Space Partitions for Path Planning pdf

Dan Klein, Joseph E. Gonzalez, Tianjun Zhang, 2021, NeurIPS.

ANODEV2: A Coupled Neural ODE Evolution Framework pdf

Kurt Keutzer, Joseph Gonzalez, George Biros, 2019, ArXiv.

MADE: Exploration via Maximizing Deviation from Explored Regions pdf

Stuart J. Russell, Jiantao Jiao, Tianjun Zhang, 2021, NeurIPS.

Contrastive Code Representation Learning pdf

Joseph E. Gonzalez, Pieter Abbeel, Paras Jain, 2020, EMNLP.

Latent Variable Representation for Reinforcement Learning

D. Schuurmans, Sujay Sanghavi, Bo Dai, 2022, ICLR.

Spectral Decomposition Representation for Reinforcement Learning

D. Schuurmans, Joseph E. Gonzalez, Bo Dai, 2022, ICLR.

A Free Lunch from the Noise: Provable and Practical Exploration for Representation Learning

Csaba Szepesvari, Bo Dai, Tianjun Zhang, 2021, UAI.

GenAx: A Genome Sequencing Accelerator

David Blaauw, Reetuparna Das, Satish Narayanasamy, 2018, 2018 ACM/IEEE 45th Annual International Symposium on Computer Architecture (ISCA).

Contrastive Learning as Goal-Conditioned Reinforcement Learning

S. Levine, R. Salakhutdinov, Benjamin Eysenbach, 2022, NeurIPS.

The Wisdom of Hindsight Makes Language Models Better Instruction Followers

P. Abbeel, Joseph Gonzalez, Fangchen Liu, 2023, ICML.

CLUT-Net: Learning Adaptively Compressed Representations of 3DLUTs for Lightweight Image Enhancement

Tianjun Zhang, Lin Zhang, Huiyu Zeng, 2022, ACM Multimedia.

Efficient Planning in a Compact Latent Action Space

Michael Janner, Edward Grefenstette, Tim Rocktaschel, 2022, ICLR.

Gorilla: Large Language Model Connected with Massive APIs

Shishir G. Patil, Joseph E. Gonzalez, Joseph E. Gonzalez, 2023, ArXiv.

A 2.46M reads/s Genome Sequencing Accelerator using a 625 Processing-Element Array

David Blaauw, Reetuparna Das, Satish Narayanasamy, 2020, 2020 IEEE Custom Integrated Circuits Conference (CICC).

Synetgy: Algorithm-hardware Co-design for ConvNet Accelerators on Embedded FPGAs

Luciano Lavagno, Kurt Keutzer, Yifan Yang, 2018, FPGA.

C-Planning: An Automatic Curriculum for Learning Goal-Reaching Tasks pdf

Sergey Levine, Ruslan Salakhutdinov, Tianjun Zhang, 2021, ICLR.

S PECTRAL D ECOMPOSITION R EPRESENTATION FOR R EINFORCEMENT L EARNING

D. Schuurmans, Joseph E. Gonzalez, Bo Dai, 2023 .

L ATENT V ARIABLE R EPRESENTATION FOR R EINFORCE - MENT L EARNING

D. Schuurmans, Sujay Sanghavi, Bo Dai, 2023 .

ANODEV2: A Coupled Neural ODE Framework

Kurt Keutzer, Joseph E. Gonzalez, George Biros, 2019, NeurIPS.

TEMPERA: Test-Time Prompting via Reinforcement Learning

D. Schuurmans, Joseph E. Gonzalez, Denny Zhou, 2022, ICLR.

TEMPERA: T EST -T IME P ROMPT E DITING VIA R EIN - FORCEMENT L EARNING

D. Schuurmans, Joseph E. Gonzalez, Denny Zhou, 2023 .

Multi-objective Optimization by Learning Space Partition

Tianjun Zhang, Yuandong Tian, Kevin Yang, 2022, International Conference on Learning Representations.

AgentBench: Evaluating LLMs as Agents

Minlie Huang, Yuxiao Dong, Yifan Xu, 2023, ArXiv.

BeBold: Exploration Beyond the Boundary of Explored Regions pdf

Kurt Keutzer, Joseph E. Gonzalez, Huazhe Xu, 2020, ArXiv.

Mitigating Metastable Failures in Distributed Systems with Offline Reinforcement Learning

Francis Y. Yan, G. Suh, Christina Delimitrou, 2023, Tiny Papers @ ICLR.

LLM-Assisted Code Cleaning For Training Accurate Code Generators

Wei-Lin Chiang, Tianjun Zhang, I. Stoica, 2023, ArXiv.

Energy-based Predictive Representations for Partially Observed Reinforcement Learning

D. Schuurmans, Joseph E. Gonzalez, Bo Dai, 2023, UAI.

LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code

Tianjun Zhang, Naman Jain, Koushik Sen, 2024, ArXiv.

RAFT: Adapting Language Model to Domain Specific RAG

M. Zaharia, Tianjun Zhang, Naman Jain, 2024, ArXiv.

In-Context Principle Learning from Mistakes

Aman Madaan, Tianjun Zhang, Uri Alon, 2024, ArXiv.