collaborators

10 papers

cs.MA2026

You Can't Escape Your Own Activations : Evaluation Awareness and Multi-Agent Monitoring

Aritra Das, Jaee Ponde, Mihir More +1

LLM agents are increasingly deployed in multi-agent systems, where they can collude while keeping their actions benign. Output monitors designed to detect such collusions can be fo…

cs.LG2026

On the Indistinguishability of Human v/s AI Generated Text

Jaee Ponde, Aritra Das, Mihir More +1

The rapid improvement of LLMs has made distinguishing AI-generated text from human writing a pressing problem. This challenge is further amplified by paraphrasing tools designed to…

cs.CC2026

Parameterized Complexity of -Lipschitz Constants for Input Convex Neural Networks and -Norm Maximization over Zonotopes

Aritra Das, Vincent Froese, Moritz Grillo +6

Lipschitz constants are a standard way to quantify the sensitivity of neural networks to small input perturbations, but computing them is difficult even for shallow ReLU networks.…

cs.LG2026

The Query Knows What to Forget: A Second Erase Direction for Linear Attention

Dhruman Gupta, Aritra Das, Debayan Gupta

Linear attention keeps a state of fixed size. At long context, many stored items share this state, and interference between them degrades retrieval. Gated DeltaNet-2 (GDN-2), like…

cs.AI2026

Linearized 2-Simplicial Attention

Aritra Das, Dhruman Gupta, Debayan Gupta

We present a linearized form of 2-simplicial attention by rewriting the trilinear score as an inner product between a composite query and a key, so that the sum over one token axis…

cs.LG2026

A Rate Separation for Agnostic Direct Sums

Mihir More, Aritra Das, Debayan Gupta

Hanneke, Moran, and Waknine \cite{HannekeMoranWaknine2024} asked how the agnostic PAC learning curve of the direct sum depends on the single-instance learning curve $\epsagn(…