Ayan Sengupta
10 papers · 2020–2025 · 6 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+3 more ↓ Show less ↑
π§ Keyword Pioneer π Conference Polyglot (6) π Academic Marathon (5) π Interdisciplinary Bridge πΊοΈ Taxonomy Completionist (24)
π
Cross-Pollinator
(14)
π₯
Unstoppable
(6)
π
Century Club
(10)
Conferences
EMNLP (3)
ACL (2)
ICLR (2)
ICML (1)
IJCAI (1)
IJCNLP (1)
Top co-authors
Keywords
pre-trained language model
(2)
transfer learning
(2)
sequence modeling
(1)
adversarial learning
(1)
self-attention mechanism
(1)
binary classification
(1)
manifold learning
(1)
natural language processing
(1)
text classification
(1)
knowledge distillation
(1)
machine translation
(1)
language modeling
(1)
multi-agent learning
(1)
distance preservation
(1)
lipschitz continuity
(1)
regularization technique
(1)
mixture of expert
(1)
utility function
(1)
gated mechanism
(1)
noisy datum
(1)
Papers
You Only Prune Once: Designing Calibration-Free Model Compression With Policy Learning
ICLR 2025
Position: Enough of Scaling LLMs! Lets Focus on Downscaling
ICML 2025
On the Generalization vs Fidelity Paradox in Knowledge Distillation
ACL 2025
A Good Learner can Teach Better: Teacher-Student Collaborative Knowledge Distillation
ICLR 2024
Manifold-Preserving Transformers are Effective for Short-Long Range Encoding
EMNLP 2023
Transfer Learning Based Adaptive Automated Negotiating Agent Framework
IJCAI 2022
HIT - A Hierarchically Fused Deep Attention Network for Robust Code-mixed Language Representation
IJCNLP 2021
Gated Transformer for Robust De-noised Sequence-to-Sequence Modelling
EMNLP 2021
HIT - A Hierarchically Fused Deep Attention Network for Robust Code-mixed Language Representation
ACL 2021
DATAMAFIA at WNUT-2020 Task 2: A Study of Pre-trained Language Models along with Regularization Techniques for Downstream Tasks
EMNLP 2020