Conference Paper

Sample Count Is Not Enough: Candidate-Generation Strategy Shapes the Energy and Performance of LLM Test-Time Scaling
arXiv:2609.19499 — For self-consistency, candidate count N is not enough. At fixed N, how samples are batched can change LLM test-time scaling energy and latency by several times on A100 GPUs.
Mobina Kashaniyan, Ali Jannesari
Posted Nov 1, 2026 Conference Paper, Workshop Paper, Preprint, Large Language Models, High-Performance Computing, Energy Efficiency
PDF DOI PDF arXiv DOI Google Scholar Research Summary Local PDF
PerfMamba: Performance Analysis and Pruning of Selective State Space Models
PerfMamba analyzes the runtime behavior, resource utilization, memory access patterns, scaling properties, and pruning opportunities of Mamba-1 and Mamba-2 selective state space models.
Abdullah Al Asif, Mobina Kashaniyan, Sixing Yu, Juan Pablo Muñoz, Ali Jannesari
Posted Jan 1, 2026 Conference Paper, Efficient AI, High-Performance Computing
PDF PDF arXiv Research Summary
LLM-Driven AutoML for Cross-Lingual Handwritten OCR: Closed-Loop Neural Architecture Search with GPT-5, GPT-4o, and Claude Sonnet 4
A fully automated LLM-driven AutoML framework for cross-lingual handwritten OCR using closed-loop neural architecture search with GPT-5, GPT-4o, and Claude Sonnet 4 across Arabic, English, and Persian scripts.
Mobina Kashaniyan, Amirhossein Ghassemi, Nasser Mozayani
Posted Oct 28, 2025 Conference Paper
PDF DOI PDF IEEE Xplore arXiv Google Scholar Research Summary

© 2026 Mobina Kashaniyan.