Artificial Intelligence

Interpretable Adaptive Sampling for LLM Test-Time Scaling
An interpretable adaptive sampling method that dynamically allocates inference-time compute for efficient LLM test-time scaling.
Mobina Kashaniyan, Ali Jannesari
Posted Aug 4, 2026 Preprint, Artificial Intelligence, Large Language Models
PDF DOI PDF arXiv Google Scholar Research Summary
Interpretable Adaptive Sampling for LLM Test-Time Scaling and Test-Time Compute
Interpretable adaptive sampling for LLM test-time scaling and test-time compute. A fuzzy controller uses prompt complexity and model confidence to dynamically allocate inference-time compute for efficient LLM reasoning.
Mobina Kashaniyan
Posted Aug 4, 2026 Large Language Models, Artificial Intelligence, LLM Reasoning, Test-Time Scaling, Research Summary
Dependency-Aware Auto-Scaling for Serverless Computing and Cloud Resource Management
Dependency-aware auto-scaling for serverless computing, Function-as-a-Service, cloud resource management, workload forecasting, cold-start mitigation, and cost-efficient resource allocation using multi-expert consensus.
Mobina Kashaniyan
Posted Jul 2, 2026 Cloud Computing, Serverless Computing, Distributed Systems, Artificial Intelligence, Research Summary
LLM-Driven AutoML and AI Agents for Multilingual Handwritten OCR
LLM-driven AutoML and AI agents for multilingual handwritten text recognition, cross-lingual OCR, and closed-loop neural architecture search across Arabic, Persian, and English handwriting.
Mobina Kashaniyan
Posted Jul 2, 2026 Artificial Intelligence, AI Agents, Computer Vision, Machine Learning, Document AI, Automated Machine Learning, Research Summary

© 2026 Mobina Kashaniyan.