collaborators

5 papers

cs.CL2026

Locale-Conditioned Few-Shot Prompting Mitigates Demonstration Regurgitation in On-Device PII Substitution with Small Language Models

Anuj Sadani, Deepak Kumar

Personally Identifiable Information (PII) redaction usually replaces detected entities with placeholder tokens such as [PERSON], destroying the downstream utility of the redacted t…

cs.CL2026

Mind the Pause: Disfluency-Aware Objective Tuning for Multilingual Speech Correction with LLMs

Deepak Kumar, Baban Gain, Asif Ekbal

Automatic Speech Recognition (ASR) transcripts often contain disfluencies, such as fillers, repetitions, and false starts, which reduce readability and hinder downstream applicatio…

cs.LG2026

CADET: Context-Conditioned Ads CTR Prediction With a Decoder-Only Transformer

David Pardoe, Neil Daftary, Miro Furtado +20

Click-through rate (CTR) prediction is fundamental to online advertising systems. While Deep Learning Recommendation Models (DLRMs) with explicit feature interactions have long dom…

cs.AR2025

GPT-OSS-20B: A Comprehensive Deployment-Centric Analysis of OpenAI's Open-Weight Mixture of Experts Model

Deepak Kumar, Divakar Yadav, Yash Patel

We present a single-GPU (H100, bf16) evaluation of GPT-OSS-20B (Mixture-of-Experts; 20.9B total, approx. 3.61B active) against dense baselines Qwen3-32B and Yi-34B across multiple…

cs.CL2025

Krutrim LLM: Multilingual Foundational Model for over a Billion People

Aditya Kallappa, Palash Kamble, Abhinav Ravi +10

India is a diverse society with unique challenges in developing AI systems, including linguistic diversity, oral traditions, data accessibility, and scalability. Existing foundatio…