41 citations · 104 across the 19 of their papers we have counts for
5 papers · 1 filter
What's in an embedding? Would a rose by any embedding smell as sweet?
Venkat Venkatasubramanian
Large Language Models (LLMs) are often criticized for lacking true "understanding" and the ability to "reason" with their knowledge, being seen merely as autocomplete systems. We b…
Arbitrage equilibrium and the emergence of universal microstructure in deep neural networks
Venkat Venkatasubramanian, N Sanjeevrajan, Manasi Khandekar +2
Despite the stunning progress recently in large-scale deep neural network applications, our understanding of their microstructure, 'energy' functions, and optimal design remains in…
Quo Vadis ChatGPT? From Large Language Models to Large Knowledge Models
Venkat Venkatasubramanian, Arijit Chakraborty
The startling success of ChatGPT and other large language models (LLMs) using transformer-based generative neural network architecture in applications such as natural language proc…
Arbitrage equilibria in active matter systems
Venkat Venkatasubramanian, Abhishek Sivaram, N. Sanjeevrajan +1
The motility-induced phase separation (MIPS) phenomenon in active matter has been of great interest for the past decade or so. A central conceptual puzzle is that this behavior, wh…
Density and Affinity Dependent Social Segregation and Arbitrage Equilibrium in a Multi-class Schelling Game
Venkat Venkatasubramanian, Jessica Shi, Leo Goldman +2
Contrary to the widely believed hypothesis that larger, denser cities promote socioeconomic mixing, a recent study (Nilforoshan et al. 2023) reports the opposite behavior, i.e. mor…