2 citations · 2 across the 11 of their papers we have counts for
12 papers
Context-Gated Associative Retrieval: From Theory to Transformers
Moulik Choraria, Argyrios Gerogiannis, Vidhata Jayaraman +2
Hopfield networks and their generalizations have established deep connections among biological associative memories, statistical physics, and transformers. Yet most models treat re…
Know Thy Reasoner: Not All Language Models Explore Alike
Moulik Choraria, Argyrios Gerogiannis, Anirban Das +4
Compute scaling for LLM reasoning trades off exploring solution approaches (\emph{breadth}) against refining promising ones (\emph{depth}), yet why a given trade-off works, and why…
Watermarking Discrete Diffusion Language Models
Avi Bagchi, Akhil Bhimaraju, Moulik Choraria +2
Watermarking has emerged as a promising technique to track AI-generated content and differentiate it from authentic human creations. While prior work extensively studies watermarki…
Skip-It? Theoretical Conditions for Layer Skipping in Vision-Language Models
Max Hartman, Vidhata Jayaraman, Moulik Choraria +2
Vision-language models achieve incredible performance across a wide range of tasks, but their large size makes inference costly. Recent work has shown that multimodal processing co…
DeepInsert: Early Layer Bypass for Efficient and Performant Multimodal Understanding
Moulik Choraria, Xinbo Wu, Akhil Bhimaraju +5
Hyperscaling of data and parameter count in LLMs is yielding diminishing improvement when weighed against training costs, underlining a growing need for more efficient finetuning a…
Semantically Grounded QFormer for Efficient Vision Language Understanding
Moulik Choraria, Xinbo Wu, Sourya Basu +5
General purpose Vision Language Models (VLMs) have received tremendous interest in recent years, owing to their ability to learn rich vision-language correlations as well as their…
Transformers are Universal Predictors
Sourya Basu, Moulik Choraria, Lav R. Varshney
We find limits to the Transformer architecture for language modeling and show it has a universal prediction property in an information-theoretic sense. We further analyze performan…
Learning Optimal Features via Partial Invariance
Moulik Choraria, Ibtihal Ferwana, Ankur Mani +1
Learning models that are robust to distribution shifts is a key concern in the context of their real-life applicability. Invariant Risk Minimization (IRM) is a popular framework th…
The Spectral Bias of Polynomial Neural Networks
Moulik Choraria, Leello Tadesse Dadi, Grigorios Chrysos +2
Polynomial neural networks (PNNs) have been recently shown to be particularly effective at image generation and face recognition, where high-frequency information is critical. Prev…
Balancing Fairness and Robustness via Partial Invariance
Moulik Choraria, Ibtihal Ferwana, Ankur Mani +1
The Invariant Risk Minimization (IRM) framework aims to learn invariant features from a set of environments for solving the out-of-distribution (OOD) generalization problem. The un…
Design of false data injection attack on distributed process estimation
Moulik Choraria, Arpan Chattopadhyay, Urbashi Mitra +1
Herein, design of false data injection attack on a distributed cyber-physical system is considered. A stochastic process with linear dynamics and Gaussian noise is measured by mult…
Optimal deception attack on networked vehicular cyber physical systems
Moulik Choraria, Arpan Chattopadhyay, Urbashi Mitra +1
Herein, design of false data injection attack on a distributed cyber-physical system is considered. A stochastic process with linear dynamics and Gaussian noise is measured by mult…