Publications

Research in NLP, LLM systems, computer vision, and reinforcement learning.

Papers

RAMP: Reinforcement Adaptive Mixed Precision Quantization for Efficient On-Device LLM Inference

Arpit Singh Gautam, Saurabh Jha

arXiv preprint · Submitted Mar 18, 2026

arXiv
The Energy of Falsehood: Generative Calibration of Fact Verification via Diffusion Models

Arpit Singh Gautam, Kailash Talreja, Saurabh Jha

FEVER: Ninth Workshop on Fact Extraction and VERification @ EACL 2026

ACL Anthology
Faithful Theory of Mind Distillation: Why Preference Based Refinement Improves Imitation

Arpit Singh Gautam, Saurabh Jha

Advancing AI through Theory of Mind Workshop @ AAAI 2026
CogniSQL-R1-Zero: Lightweight Reinforced Reasoning for Efficient SQL Generation

Kushal Gajjar, Harshit Sikchi, Arpit Singh Gautam, Marc Hammons, Saurabh Jha

arXiv preprint — paper + 2 datasets public · SOTA on BIRD benchmark, outperforming 236B+ models

arXiv
Enhancing Lymphoma Detection Using Multi-Layer Hybrid Neural Networks

Arpit Singh Gautam, Satyam Kumar, Nishad Khade, Vivek Bhardwaj

Oral Presentation — 16th ICCCNT, IIT Indore (2025)
Real-Time QUIC Traffic Classification Using LightGBM with SHAP+LIME Explainability

Arpit Singh Gautam, Rajesh Kumar et al.

16th ICCCNT, IIT Indore (2025)