inference-time-sampling

Tag

Cards List
#inference-time-sampling

Explore Broadly, Reason Sharply: Push Small Models toward the Frontier via Sampling

Hugging Face Daily Papers ↗ · 2026-09-29 Cached

The paper introduces Parallel Power Tempering (PPT), an inference-time sampling method that uses multiple parallel tempering chains at different sharpening levels to resolve the exploration-exploitation trade-off in power-sharpened LLM sampling, outperforming RL post-training and approaching frontier-model reasoning performance.

0 favorites 0 likes
← Back to home

Submit Feedback