4 citations · 7 across the 10 of their papers we have counts for
11 papers
Beyond the Need for Speed: Energy-Aware Code Generation via Simulation-Guided Reinforcement Learning
Saurabhsingh Rajput, Tushar Sharma
Code models strictly prioritize functional correctness, leaving software energy efficiency as an unoptimized byproduct. Training models to generate energy-efficient code requires r…
Hierarchical Fault Detection and Diagnosis for Transformer Architectures
Sigma Jahan, Saurabh Singh Rajput, Tushar Sharma +1
Transformers now underpin critical AI systems across industry and research. Yet their faults can silently alter model behavior without runtime errors, and existing techniques offer…
Watts This Smell: A Comprehensive Taxonomy of Software Energy Smells
Mohammadjavad Mehditabar, Saurabhsingh Rajput, Tushar Sharma
As software proliferates across domains, its aggregate energy footprint has become a major concern. To reduce software's growing environmental footprint, developers need to identif…
CodeGreen: Towards Improving Precision and Portability in Software Energy Measurement
Saurabhsingh Rajput, Tushar Sharma
Accurate software energy measurement is critical for optimizing energy, yet existing profilers force a trade-off between measurement accuracy and overhead due to tight coupling wit…
Energy Flow Graph: Modeling Software Energy Consumption
Saurabhsingh Rajput, Tushar Sharma
The growing energy demands of computational systems necessitate a fundamental shift from performance-centric design to one that treats energy consumption as one of the primary desi…
Hierarchical Evaluation of Software Design Capabilities of Large Language Models of Code
Mootez Saad, Boqi Chen, José Antonio Hernández López +2
Large language models (LLMs) are being increasingly adopted in the software engineering domain, yet the robustness of their grasp on core software design concepts remains unclear.…
On the Effect of Token Merging on Pre-trained Models for Code
Mootez Saad, Hao Li, Tushar Sharma +1
Tokenization is a fundamental component of language models for code. It involves breaking down the input into units that are later passed to the language model stack to learn high-…
Tu(r)ning AI Green: Exploring Energy Efficiency Cascading with Orthogonal Optimizations
Saurabhsingh Rajput, Mootez Saad, Tushar Sharma
AI's exponential growth intensifies computational demands and energy challenges. While practitioners employ various optimization techniques, that we refer as "knobs" in this paper,…
SENAI: Towards Software Engineering Native Generative Artificial Intelligence
Mootez Saad, José Antonio Hernández López, Boqi Chen +3
Large Language Models have significantly advanced the field of code generation, demonstrating the ability to produce functionally correct code snippets. However, advancements in ge…
ALPINE: An adaptive language-agnostic pruning method for language models for code
Mootez Saad, José Antonio Hernández López, Boqi Chen +2
Language models of code have demonstrated state-of-the-art performance across various software engineering and source code analysis tasks. However, their demanding computational re…
On Inter-dataset Code Duplication and Data Leakage in Large Language Models
José Antonio Hernández López, Boqi Chen, Mootez Saaz +2
Motivation. Large language models (LLMs) have exhibited remarkable proficiency in diverse software engineering (SE) tasks. Handling such tasks typically involves acquiring foundati…