Yikang Shen

发表

Unsupervised Dependency Graph Network

Jie Zhou, Alessandro Sordoni, Peng Li, 2022, ACL.

Prompting Decision Transformer for Few-Shot Policy Generalization

J. Tenenbaum, Yuchen Lu, Shun Zhang, 2022, ICML.

Phrase-aware Unsupervised Constituency Parsing

Jingbo Shang, Jiaming Shen, Xiaotao Gu, 2022, ACL.

Mixture of Attention Heads: Selecting Attention Heads Per Token

Jie Zhou, Wenge Rong, Zhang Xiong, 2022, EMNLP.

Mod-Squad: Designing Mixture of Experts As Modular Multi-Task Learners

E. Learned-Miller, Hengshuang Zhao, Chuang Gan, 2022, ArXiv.

Ordered Memory

Aaron C. Courville, Aaron Courville, Alessandro Sordoni, 2019, NeurIPS.

Explicitly Modeling Syntax in Language Models with Incremental Parsing and a Dynamic Oracle

Siva Reddy, Alessandro Sordoni, Yikang Shen, 2020, NAACL.

Explicitly Modeling Syntax in Language Model improves Generalization pdf

Aaron C. Courville, Aaron Courville, Siva Reddy, 2020, ArXiv.

Long Range Arena: A Benchmark for Efficient Transformers pdf

Liu Yang, Jinfeng Rao, Yi Tay, 2020, ICLR.

StructFormer: Joint Unsupervised Induction of Dependency and Constituency Structure from Masked Language Modeling

Aaron C. Courville, Yi Tay, Aaron Courville, 2020, ACL.

Transformer-Patcher: One Mistake worth One Neuron

Jie Zhou, Wenge Rong, Zhang Xiong, 2023, ICLR.

See, Think, Confirm: Interactive Prompting Between Vision and Language Models for Knowledge-based Visual Reasoning

Hao Zhang, Chuang Gan, Zhenfang Chen, 2023, ArXiv.

Visual Dependency Transformers: Dependency Tree Emerges from Reversed Attention

J. Tenenbaum, Lijie Fan, Chuang Gan, 2023, 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

Planning with Large Language Models for Code Generation

J. Tenenbaum, Chuang Gan, Mingyu Ding, 2023, ArXiv.

Principle-Driven Self-Alignment of Language Models from Scratch with Minimal Human Supervision

Yiming Yang, Zhiqing Sun, Chuang Gan, 2023, NeurIPS.

Hyper-Decision Transformer for Efficient Online Policy Adaptation

Yuchen Lu, Ding Zhao, Chuang Gan, 2023, ICLR.

Exploiting Syntactic Structure for Better Language Modeling: A Syntactic Distance Approach pdf

Yoshua Bengio, Timothy J. O'Donnell, Wenyu Du, 2020, ACL.

An Efficient General-Purpose Modular Vision Model via Multi-Task Heterogeneous Training

E. Learned-Miller, M. Tomizuka, W. Zhan, 2023, ArXiv.

ModuleFormer: Learning Modular Large Language Models From Uncurated Data

Chuang Gan, Zhenfang Chen, Yikang Shen, 2023, ArXiv.

Self-Instantiated Recurrent Units with Dynamic Soft Recursion

Yi Tay, Shuai Zhang, Alvin Chan, 2021, NeurIPS.

Recursive Top-Down Production for Sentence Generation with Latent Trees pdf

Aaron C. Courville, Timothy J. O'Donnell, Aaron Courville, 2020, FINDINGS.

STRUCTFORMER: JOINT UNSUPERVISED INDUCTION

Aaron C. Courville, Yi Tay, Dara Bahri, 2020 .

Learning Task Decomposition with Ordered Memory Policy Network pdf

Joshua B. Tenenbaum, Aaron C. Courville, Aaron Courville, 2021, ICLR.

Planning with Large Language Models for Code Generation

J. Tenenbaum, Chuang Gan, Mingyu Ding, 2023, ICLR.

Aligning Large Multimodal Models with Factually Augmented RLHF

Trevor Darrell, K. Keutzer, Yiming Yang, 2023, ArXiv.

ModuleFormer: Modularity Emerges from Mixture-of-Experts

Chuang Gan, Zhenfang Chen, Yikang Shen, 2023, 2306.04640.

TextPSG: Panoptic Scene Graph Generation from Textual Descriptions

Zhenfang Chen, Yikang Shen, Chengyang Zhao, 2023, 2023 IEEE/CVF International Conference on Computer Vision (ICCV).

SALMON: Self-Alignment with Principle-Following Reward Models

Zhiqing Sun, Zhenfang Chen, Yikang Shen, 2023, ArXiv.

Mod-Squad: Designing Mixtures of Experts As Modular Multi-Task Learners

E. Learned-Miller, Hengshuang Zhao, Chuang Gan, 2023, 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

Sparse Universal Transformer

Zhenfang Chen, Yikang Shen, Shawn Tan, 2023, EMNLP.