Subhabrata Mukherjee

发表

PARAMETER-EFFICIENT TUNING OF LARGE LANGUAGE MODELS

Xiaodong Liu, Jianfeng Gao, A. Awadallah, 2022 .

AdaMix: Mixture-of-Adapter for Parameter-efficient Tuning of Large Language Models

Xiaodong Liu, Jianfeng Gao, A. Awadallah, 2022, arXiv.org.

LiST: Lite Prompted Self-training Makes Parameter-efficient Few-shot Learners

Xiaodong Liu, Jianfeng Gao, A. Awadallah, 2021, NAACL-HLT.

Vec2Node: Self-Training with Tensor Augmentation for Text Classification with Few Labels

E. Papalexakis, Subhabrata Mukherjee, S. Abdali, 2022, ECML/PKDD.

AdaMix: Mixture-of-Adaptations for Parameter-efficient Model Tuning

Xiaodong Liu, Jianfeng Gao, Jing Gao, 2022, Conference on Empirical Methods in Natural Language Processing.

LiteTransformerSearch: Training-free Neural Architecture Search for Efficient Language Models

Sébastien Bubeck, Debadeepta Dey, F. Koushanfar, 2022, NeurIPS.

OpenTag

Subhabrata Mukherjee, Feifei Li, Guineng Zheng, 2018, Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining.

AutoMoE: Neural Architecture Search for Efficient Sparsely Activated Transformers

Sébastien Bubeck, L. Lakshmanan, Xiaodong Liu, 2022, ArXiv.

ADMoE: Anomaly Detection with Mixture-of-Experts from Noisy Labels

Yue Zhao, R. McCann, Guoqing Zheng, 2022, 2208.11290.

Small Character Models Match Large Word Models for Autocomplete Under Memory Constraints

Debadeepta Dey, S. Shah, L. Lakshmanan, 2022, ArXiv.

Accelerating Dataset Distillation via Model Augmentation

Lei Zhang, J Zhang, Y. Li, 2022, ArXiv.

AdaMix: Mixture-of-Adaptations for Parameter-efficient Model Tuning

Xiaodong Liu, Jianfeng Gao, Jing Gao, 2022, EMNLP.

Sparsely Activated Mixture-of-Experts are Robust Multi-Task Learners

Jianfeng Gao, Damien Jose, A. Awadallah, 2022, ArXiv.

LiteTransformerSearch: Training-free On-device Search for Efficient Autoregressive Language Models

Sébastien Bubeck, Debadeepta Dey, F. Koushanfar, 2022, ArXiv.

A Systematic Study of Knowledge Distillation for Natural Language Generation with Pseudo-Target Training

Roi Reichart, Nitay Calderon, Subhabrata Mukherjee, 2023, ArXiv.

Robustness Challenges in Model Distillation and Pruning for Natural Language Understanding

Mengnan Du, Yu Cheng, Xia Hu, 2021, EACL.

What do Compressed Large Language Models Forget? Robustness Challenges in Model Compression pdf

Milad Shokouhi, Yu Cheng, Mengnan Du, 2021, ArXiv.

Accelerating Dataset Distillation via Model Augmentation

Lei Zhang, J Zhang, Y. Li, 2022, 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

CLUES: Few-Shot Learning Evaluation in Natural Language Understanding pdf

Hao Cheng, Jianfeng Gao, Saghar Hosseini, 2021, NeurIPS Datasets and Benchmarks.

Meta Self-training for Few-shot Neural Sequence Labeling

Yuancheng Tu, Haoda Chu, Subhabrata Mukherjee, 2021, KDD.

Fairness via Representation Neutralization pdf

Xia Hu, Mengnan Du, Subhabrata Mukherjee, 2021, NeurIPS.

CLUES: Few-Shot Learning Evaluation in NLU

Hao Cheng, Saghar Hosseini, Xiaodong Liu, 2021 .

LiST: Lite Self-training Makes Efficient Few-shot Learners pdf

Jianfeng Gao, Jing Gao, Subhabrata Mukherjee, 2021, ArXiv.

ReWOO: Decoupling Reasoning from Observations for Efficient Augmented Language Models

Zhiyuan Peng, Binfeng Xu, Subhabrata Mukherjee, 2023, ArXiv.

AutoMoE: Heterogeneous Mixture-of-Experts with Adaptive Computation for Efficient Neural Machine Translation

Sébastien Bubeck, L. Lakshmanan, Xiaodong Liu, 2022, 2210.07535.

Orca: Progressive Learning from Complex Explanation Traces of GPT-4

H. Palangi, Arindam Mitra, A. Awadallah, 2023, ArXiv.

ADMoE: Anomaly Detection with Mixture-of-Experts from Noisy Labels

Yue Zhao, R. McCann, Guoqing Zheng, 2022, AAAI.

A Systematic Study of Knowledge Distillation for Natural Language Generation with Pseudo-Target Training

Roi Reichart, Nitay Calderon, Subhabrata Mukherjee, 2023, ACL.

AutoDistil: Few-shot Task-agnostic Neural Architecture Search for Distilling Large Language Models

Debadeepta Dey, Wenhui Wang, Xiaodong Liu, 2022, ArXiv.

Few-shot Task-agnostic Neural Architecture Search for Distilling Large Language Models

Debadeepta Dey, Wenhui Wang, Xiaodong Liu, 2022, NeurIPS.

Adversarial Robustness of Prompt-based Few-Shot Learning for Natural Language Understanding

Srijan Kumar, Gaurav Verma, Subhabrata Mukherjee, 2023, ACL.

Small Character Models Match Large Word Models for Autocomplete Under Memory Constraints

Debadeepta Dey, S. Shah, L. Lakshmanan, 2022, SUSTAINLP.

Self-training with Few-shot Rationalization pdf

Alessandro Sordoni, Meghana Moorthy Bhat, Subhabrata Mukherjee, 2021, EMNLP.

Teaching Language Models to Hallucinate Less with Synthetic Tasks

A. Awadallah, Subhabrata Mukherjee, Ece Kamar, 2023, ArXiv.

SkipDecode: Autoregressive Skip Decoding with Batching and Caching for Efficient LLM Inference

Luciano Del Corro, Allison Del Giorno, Ting Yu, 2023, ArXiv.