Home
Research
Publications
Education
Research Experience
Projects
Teaching
Skills
Contact
Online Cost Learning
ATEST / RATTS: Adaptive Resource-Aware Test-Time Scaling for LLM Inference (arXiv:2610.25519)
ATEST (RATTS) makes self-consistency resource-aware. The same four-sample self-consistency query can use 4.1× more energy when the GPU is busy. ATEST-Online answers every query within budget. arXiv:2610.25519.
Mobina Kashaniyan
Posted Oct 18, 2026
Large Language Models
,
High-Performance Computing
,
Energy Efficiency
,
Test-Time Scaling
,
Research Summary