Rina Panigrahy‎

Roma Tre University — Italy

Computer Science · Physical Sciences

40h-index8.3kcitations146works0.22yr avg
OpenAlex↗Google Scholar↗Lab page↗

Accepting Students?

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

Research Topics

Algorithms and Data Compression(27), Complexity and Algorithms in Graphs(20), Machine Learning and Algorithms(20), Advanced Image and Video Retrieval Techniques(16), Caching and Content Delivery(16)

Publications146 total

Water-peptide interactions in presence of a ionic liquid. A structural study of a glutathione-water-BMIMI ternary solution
Journal of Molecular Liquids·2025Open Access
Universal Model Routing for Efficient LLM Inference
arXiv (Cornell University)·2025Open Access
StagFormer: Time Staggering Transformer Decoding for RunningLayers In Parallel
arXiv (Cornell University)·2025Open Access
A Implies B: Circuit Analysis in LLMs for Propositional Logical Reasoning
arXiv (Cornell University)·2024· 1 citedOpen Access
Causal Language Modeling Can Elicit Search and Reasoning Capabilities on Logic Puzzles
arXiv (Cornell University)·2024Open Access
Causal language modeling can elicit search and reasoning capabilities on logic puzzles
2024
Simple Mechanisms for Representing, Indexing and Manipulating Concepts
arXiv (Cornell University)·2023Open Access
The Power of External Memory in Increasing Predictive Model Capacity
arXiv (Cornell University)·2023Open Access
Alternating Updates for Efficient Transformers
arXiv (Cornell University)·2023Open Access
On the Benefits of Learning to Route in Mixture-of-Experts Models
2023· 8 citedOpen Access
A Unified Cascaded Encoder ASR Model for Dynamic Model Sizes
Interspeech 2022·2022· 10 cited
A Theoretical View on Sparsely Activated Networks
arXiv (Cornell University)·2022· 2 citedOpen Access
A Unified Cascaded Encoder ASR Model for Dynamic Model Sizes
arXiv (Cornell University)·2022Open Access
Provable Hierarchical Lifelong Learning with a Sketch-based Modular Architecture
arXiv (Cornell University)·2021· 2 citedOpen Access
One Network Fits All? Modular versus Monolithic Task Formulations in Neural Networks
arXiv (Cornell University)·2021Open Access
One Network Fits All? Modular versus Monolithic Task Formulations in\n Neural Networks
arXiv (Cornell University)·2021· 3 citedOpen Access
Sketch based Memory for Neural Networks
International Conference on Artificial Intelligence and Statistics·2021· 2 cited
For Manifold Learning, Deep Neural Networks can be Locality Sensitive Hash Functions
arXiv (Cornell University)·2021· 2 citedOpen Access
Learning the gravitational force law and other analytic functions
arXiv (Cornell University)·2020Open Access
On the Learnability of Random Deep Networks
Society for Industrial and Applied Mathematics eBooks·2019· 2 cited
page 1 of 8Next →

Frequent Co-authors

Moses Charikar(7), Rajeev Motwani(7), Sreenivas Gollapudi(7), Tomás Feder(6), Krishnaram Kenthapadi(6), Udi Wieder(6), Kunal Talwar(5), Gagan Aggarwal(4), Dilys Thomas(4), An Zhu(4), Atish Das Sarma(4), Eric Lehman(3), Yinglian Xie(3), Liadan O'Callaghan(3), S. Sharma(3), Vijayan Prabhakaran(2), Manoj Prabhakaran(2), Abhi Shelat(2), Michael Mitzenmacher(2), Fang Yu(2)