Small well-performing LVLMs gain the largest benefits from test-time scaling (up to ~30% improvement), often matching or exceeding larger models, while visual tokens contribute mainly early in the reasoning chain.
Llms can generate a better answer by aggregating their own responses.arXiv preprint arXiv:2503.04104, 2025b
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2representative citing papers
Lack of exploration from conditioning on prior answers is the primary reason parallel sampling outperforms sequential sampling in large reasoning models.
citing papers explorer
-
On Test-Time Scaling for Vision-Language Models
Small well-performing LVLMs gain the largest benefits from test-time scaling (up to ~30% improvement), often matching or exceeding larger models, while visual tokens contribute mainly early in the reasoning chain.
-
Understanding Performance Gap Between Parallel and Sequential Sampling in Large Reasoning Models
Lack of exploration from conditioning on prior answers is the primary reason parallel sampling outperforms sequential sampling in large reasoning models.