Subhabrata Mukherjee

Microsoft (United States) — United States

Computer Science · Physical Sciences

26h-index2.5kcitations125works4.42yr avg
OpenAlex↗Google Scholar↗Lab page↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Topic Modeling(78), Natural Language Processing Techniques(42), Sentiment Analysis and Opinion Mining(20), Multimodal Machine Learning Applications(19), Misinformation and Its Impacts(18)

Publications125 total

AutoViT: Achieving Real-Time Vision Transformers on Mobile via Latency-aware Coarse-to-Fine Search
International Journal of Computer Vision·2025· 3 citedOpen Access
IP03-04 PILOT VALIDATION OF SONOFLOW, A MACHINE-LEARNING SOUND-BASED UROFLOWMETRY ALGORITHM, IN A SYMPTOMATIC PATIENT POPULATION
The Journal of Urology·2025
Retrieval-Augmented Generation with Graphs (GraphRAG)
arXiv (Cornell University)·2024· 13 citedOpen Access
Hybrid LLM: Cost-Efficient and Quality-Aware Query Routing
arXiv (Cornell University)·2024· 6 citedOpen Access
High-grade prostate cancer demonstrates preferential growth in the cranio-caudal axis and provides discrimination of disease grade in an MRI parametric model
British Journal of Radiology·2024Open Access
Teaching Language Models to Hallucinate Less with Synthetic Tasks
arXiv (Cornell University)·2023· 5 citedOpen Access
Task-Based MoE for Multitask Multilingual Machine Translation
arXiv (Cornell University)·2023Open Access
SkipDecode: Autoregressive Skip Decoding with Batching and Caching for Efficient LLM Inference
arXiv (Cornell University)·2023· 7 citedOpen Access
ADMoE: Anomaly Detection with Mixture-of-Experts from Noisy Labels
Proceedings of the AAAI Conference on Artificial Intelligence·2023· 26 citedOpen Access
Adversarial Robustness of Prompt-based Few-Shot Learning for Natural Language Understanding
arXiv (Cornell University)·2023Open Access
Orca: Progressive Learning from Complex Explanation Traces of GPT-4
arXiv (Cornell University)·2023· 66 citedOpen Access
Accelerating Dataset Distillation via Model Augmentation
2023· 38 cited
GRILL: Grounded Vision-language Pre-training via Aligning Text and Image Regions
arXiv (Cornell University)·2023· 1 citedOpen Access
ReWOO: Decoupling Reasoning from Observations for Efficient Augmented Language Models
arXiv (Cornell University)·2023· 15 citedOpen Access
A Systematic Study of Knowledge Distillation for Natural Language Generation with Pseudo-Target Training
arXiv (Cornell University)·2023· 1 citedOpen Access
AutoMoE: Heterogeneous Mixture-of-Experts with Adaptive Computation for Efficient Neural Machine Translation
2023· 3 citedOpen Access
Small Character Models Match Large Word Models for Autocomplete Under Memory Constraints
2023Open Access
Robustness Challenges in Model Distillation and Pruning for Natural Language Understanding
2023· 9 citedOpen Access
Vec2Node: Self-Training with Tensor Augmentation for Text Classification with Few Labels
Lecture notes in computer science·2023· 2 cited
Adversarial Robustness of Prompt-based Few-Shot Learning for Natural Language Understanding
2023· 2 citedOpen Access
page 1 of 7Next →

Frequent Co-authors

Ahmed Hassan Awadallah(20), Gerhard Weikum(13), Kashyap Popat(6), Pushpak Bhattacharyya(5), Guo‐qing Zheng(5), Jianfeng Gao(4), Sachindra Joshi(4), Andrew Yates(3), Jannik Strötgen(3), Kai Shu(3), Huan Liu(3), Cristian Danescu-Niculescu-Mizil(2), Sahaj Agarwal(2), Yaqing Wang(2), Xiaodong Liu(2), Jing Gao(2), Yaqing Wang(2), Haoda Chu(2), Yuancheng Tu(2), Ming Wu(2)