Sample Count Is Not Enough: Candidate-Generation Strategy Shapes the Energy and Performance of LLM Test-Time Scaling
Paper • 2609.19499 • Published • 2
Mobina
iammobina
AI & ML interests
None yet
Recent Activity
submitted a paper about 15 hours ago
Sample Count Is Not Enough: Candidate-Generation Strategy Shapes the Energy and Performance of LLM Test-Time Scaling authored a paper about 18 hours ago
Sample Count Is Not Enough: Candidate-Generation Strategy Shapes the Energy and Performance of LLM Test-Time Scaling authored a paper about 18 hours ago
LLM-Driven AutoML for Cross-Lingual Handwritten OCR: Closed-Loop Neural Architecture Search with GPT-5, GPT-4o, and Claude Sonnet 4Organizations
None yet
submitted a
paper to Daily Papers about 15 hours ago
authored 5
papers about 18 hours ago
Sample Count Is Not Enough: Candidate-Generation Strategy Shapes the Energy and Performance of LLM Test-Time Scaling
Paper • 2609.19499 • Published • 2
LLM-Driven AutoML for Cross-Lingual Handwritten OCR: Closed-Loop Neural Architecture Search with GPT-5, GPT-4o, and Claude Sonnet 4
Paper • 2607.15509 • Published
An Auto-Scaling Approach for Serverless Environments Based on a Multi-Expert Consensus Mechanism
Paper • 2607.15511 • Published
PerfMamba: Performance Analysis and Pruning of Selective State Space Models
Paper • 2511.22849 • Published
Interpretable Adaptive Sampling for LLM Test-Time Scaling
Paper • 2608.03961 • Published