beam-search

Tag

Cards List
#beam-search

Can gzip be a language model?

Lobsters Hottest · 2026-06-16 Cached

This article explores using the gzip compression algorithm as a language model, demonstrating that compression algorithms can generate text by scoring candidate continuations based on compressed length, using beam search to produce output.

0 favorites 0 likes
#beam-search

ThinkBooster: A Unified Framework for Seamless Test-Time Scaling of LLM Reasoning

arXiv cs.CL · 2026-06-08 Cached

ThinkBooster is a unified framework for test-time compute scaling of LLM reasoning, providing a modular Python library, a performance-efficiency benchmark, an OpenAI-compatible proxy service, and a visual debugger. Empirical results on math and coding tasks demonstrate practical gains with quality-cost trade-offs.

0 favorites 0 likes
#beam-search

(1D) Ordered Tokens Enable Efficient Test-Time Search

Hugging Face Daily Papers · 2026-04-16 Cached

This paper investigates how 1D coarse-to-fine token structures in autoregressive models improve test-time search efficiency compared to classical 2D grid tokenization. The authors show that such ordered tokens enable better test-time scaling and even training-free text-to-image generation when guided by image-text verifiers.

0 favorites 0 likes
← Back to home

Submit Feedback