collaborators

7 papers

cs.LG2026

Convex Basins in Single-Index Model Loss Landscapes: Applications to Robust Recovery under Strong Adversarial Corruption

Santanu Das, Sagnik Chatterjee, Jatin Batra

We study the problem of robustly learning Gaussian Single Index Models (SIMs) in the presence of heavy-tailed noise and a constant fraction of adversarially corrupted covariates an…

q-bio.GN2026

SCOPE: Siamese Contrastive Operon Pair Embeddings for Functional Sequence Representation and Classification

Akarsh Gupta, Kenneth Rodrigues, Sagnik Chatterjee

Identifying operons is a fundamental step in understanding prokaryotic gene regulation, as classifying genes into operons supports the reconstruction of regulatory networks, functi…

cs.SE2026

Trajectory Supervision for Continual Tool-Use Learning in LLMs

Vishnu Vardhan Reddy, Sagnik Chatterjee, Soumik Bhatta

Most language-model training data shows final artifacts, not the process that produced them. We study a tractable version of this question in tool use: when a model learns a stream…

cs.CL2026

Dual-Track CoT: Budget-Aware Stepwise Guidance for Small LMs

Sagnik Chatterjee, Atharva Patil, Sricharan Ramesh

Large Language Models (LLMs) solve many reasoning tasks via chain-of-thought (CoT) prompting, but smaller models (about 7 to 8B parameters) still struggle with multi-step reasoning…

cs.IT2026

Perfect Secret Key Generation for a class of Hypergraphical Sources

Manuj Mukherjee, Sagnik Chatterjee, Alhad Sethi

Nitinawarat and Narayan proposed a perfect secret key generation scheme for the so-called \emph{pairwise independent network (PIN) model} by exploiting the combinatorial properties…

quant-ph2026

Generalized cross-resonance scheme for maximally-entangling two-qutrit gates

Yash Saxena, Tharrmashastha Sapv, Sagnik Chatterjee +1

To utilize higher-dimensional quantum systems, in this Letter, we derive a generalized cross-resonance (GCR) scheme for realizing maximally entangling two-qutrit gates on fixed-fre…