collaborators

7 papers

cs.AI2026

Why Does CLAUDE.md Keep Growing? Catastrophic Remembering in Agentic Coding

Kushal Chakrabarti

Agentic coding READMEs like CLAUDE.md grow without bound in real repositories, stopping only when the repository retires or someone rewrites the file wholesale. We trace this to im…

cs.LG2026

Reliability Scales Inversely: Hallucinations Snowball Faster in Bigger Language Models

Kushal Chakrabarti

Bigger language models are less reliable. Across three families, three benchmarks and six rungs, including in-the-wild chat logs, scaling closes the start-of-response knowledge gap…

math.OC2026

Quantized Stochastic Primal-Dual Methods for Distributed Optimization under Relaxed Global Geometry

Susmit Sarkar, Abhinav Raghuvanshi, Kushal Chakrabarti +1

We study distributed optimization with stochastic gradients and finite-bit communication modeled by random (unbiased) quantization. We propose q-PDGD, a quantized stochastic primal…

cs.LG2026

Enhancing Robustness of Federated Learning via Server Learning

Van Sy Mai, Kushal Chakrabarti, Richard J. La +1

This paper explores the use of server learning for enhancing the robustness of federated learning against malicious attacks even when clients' training data are not independent and…

cs.AI2026

Multi-Head Attention Is a Multi-Player Game

Kushal Chakrabarti, Nirmal Balachundar

Modern transformer attention is internally multi-agent -- heads compete and coordinate -- yet we train it as if it were a monolithic optimizer. We formalize this gap: cross-entropy…

cs.CL2025

Neural Diversity Regularizes Hallucinations in Language Models

Kushal Chakrabarti, Nirmal Balachundhar

Language models continue to hallucinate despite increases in parameters, compute, and data. We propose neural diversity -- decorrelated parallel representations -- as a principled…