Lattice AI Research

Research focus

Code Generation & Program Synthesis (2)Inference & Quantization (1)Training Efficiency & Optimization (1)Interpretability & Mechanistic Interp (1)

Frequent co-authors

Ajmain Inqiad Alam (1)Palash Roy (1)Chanchal K. Roy (1)Kevin A. Schneider (1)

Papers (2)

Apr 28, 2026

Ajmain Inqiad Alam +43w ago

Carbon-Taxed Transformers: A Green Compression Pipeline for Overgrown Language Models

Slash your LLM's carbon footprint by up to 81% without sacrificing performance using a compression pipeline inspired by carbon taxation.

Ajmain Inqiad Alam, Palash Roy, Chanchal K. Roy +2

Code Generation & Program Synthesis Inference & Quantization Training Efficiency & Optimization

Feb 25, 2026

Saumendu Roy +3Feb 25, 2026·also University of Saskatchewan

XMENTOR: A Rank-Aware Aggregation Approach for Human-Centered Explainable AI in Just-in-Time Software Defect Prediction

Conflicting explanations from multiple XAI methods can be unified into a single, coherent view that developers overwhelmingly prefer for debugging and code review.

Saumendu Roy, Banani Roy, Chanchal Roy +1

Code Generation & Program Synthesis Interpretability & Mechanistic Interp

Search

Banani Roy

Publication activitypapers/week, last 8 weeks

Research focus

Frequent co-authors

Papers (2)