best-of-n
- Bag of Tricks for Inference-time Computation of LLM Reasoning
- Latent Chain-of-Thought for Visual Reasoning
- Majority of the Bests: Improving Best-of-N via Bootstrapping
- Quality-Driven Curation of Remote Sensing Vision-Language Data via Learned Scoring Models
- Value-Guided Search for Efficient Chain-of-Thought Reasoning