Satwik Bhattamishra
12 papers · 2019–2025 · 7 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+8 more ↓ Show less ↑
π Interdisciplinary Bridge π Conference Polyglot (7) π Academic Marathon (6) π Renaissance Researcher (5) πΊοΈ Taxonomy Completionist (23)
π£
Hot Topic Early Bird
π
Conference Polyglot
(7)
π
Academic Marathon
(6)
π
Keyword Champion
π
Century Club
(12)
β
The Questioner
ποΈ
Keyword Collector
(58)
π₯
Unstoppable
(7)
Conferences
EMNLP (3)
ACL (2)
ICLR (2)
NAACL (2)
COLING (1)
CONLL (1)
NIPS (1)
Top co-authors
Keywords
transformer model
(3)
positional encoding
(3)
attention mechanism
(3)
transformer architecture
(3)
sequence modeling
(2)
neural network optimization
(2)
recurrent neural network
(2)
turing completeness
(2)
communication complexity
(1)
semantic parsing
(1)
natural language processing
(1)
language modeling
(1)
model evaluation
(1)
intent classification
(1)
question answering
(1)
self-attention mechanism
(1)
compositional generalization
(1)
computational complexity
(1)
sensitivity analysis
(1)
in-context learning
(1)
Papers
A Formal Framework for Understanding Length Generalization in Transformers
ICLR 2025
Separations in the Representational Capabilities of Transformers and Recurrent Architectures
NIPS 2024
Understanding In-Context Learning in Transformers and LLMs by Learning to Learn Discrete Functions
ICLR 2024
MAGNIFICo: Evaluating the In-Context Learning Ability of Large Language Models to Generalize to Novel Interpretations
EMNLP 2023
Simplicity Bias in Transformers and their Ability to Learn Sparse Boolean Functions
ACL 2023
Revisiting the Compositional Generalization Abilities of Neural Sequence Models
ACL 2022
Are NLP Models really able to Solve Simple Math Word Problems?
NAACL 2021
On the Computational Power of Transformers and Its Implications in Sequence Modeling
EMNLP 2020
On the Ability and Limitations of Transformers to Recognize Formal Languages
EMNLP 2020
On the Computational Power of Transformers and Its Implications in Sequence Modeling
CONLL 2020
On the Practical Ability of Recurrent Neural Networks to Recognize Hierarchical Languages
COLING 2020
Submodular Optimization-based Diverse Paraphrasing and its Effectiveness in Data Augmentation
NAACL 2019