5 papers
The Joint Effect of Quantization and Sampling Temperature on LLM Safety Alignment: A Factorial Analysis
Hari Prasad, Ritam Pal
Modern LLM deployments often combine quantization with higher sampling temperatures to reduce cost, latency, or repetition, yet safety evaluations usually treat these as fixed impl…
LLM Inference at the Edge: Mobile, NPU, and GPU Performance Efficiency Trade-offs Under Sustained Load
Pranay Tummalapalli, Sahil Arayakandy, Ritam Pal +1
Deploying large language models on-device for always-on personal agents demands sustained inference from hardware tightly constrained in power, thermal envelope, and memory. We ben…
Identifying fatigue crack initiation through analytical calculation of temporal compliance calibrated with Computed Tomography
Ritam Pal, Amrita Basak
Fatigue failure is ubiquitous in engineering applications. While the total fatigue life is critical to understanding a component's operational life, for safety, regulatory complian…
Surface roughness-informed fatigue life prediction of L-PBF Hastelloy X at elevated temperature
Ritam Pal, Brandon Kemerling, Daniel Ryan +2
Additive manufacturing, especially laser powder bed fusion (L-PBF), is widely used for fabricating metal parts with intricate geometries. However, parts produced via L-PBF suffer f…
A novel approach to preventing SARS-CoV-2 transmission in classrooms: An OpenFOAM based CFD Study
Anish Pal, Riddhideep Biswas, Ritam Pal +2
The education sector has suffered a catastrophic setback due to ongoing COVID-pandemic, with classrooms being closed indefinitely. The current study aims to solve the existing dile…