pith. sign in

arXiv preprint arXiv:2402.18700 , year=

2 Pith papers cite this work. Polarity classification is still indexing.

2 Pith papers citing it

fields

cs.AI 1 cs.CL 1

years

2026 2

clear filters

representative citing papers

End-to-End Context Compression at Scale

cs.CL · 2026-06-08 · unverdicted · novelty 6.0

LCLMs are scaled 0.6B-encoder 4B-decoder compressors pre-trained on over 350B tokens that improve the Pareto frontier for general-task performance, compression speed, and peak memory in long-context language model inference.

citing papers explorer

Showing 2 of 2 citing papers after filters.

  • Post Reasoning: Improving the Performance of Non-Thinking Models at No Cost cs.AI · 2026-05-07 · conditional · none · ref 85

    Post-Reasoning boosts LLM accuracy by reversing the usual answer-after-reasoning order, delivering mean relative gains of 17.37% across 117 model-benchmark pairs with zero extra cost.

  • End-to-End Context Compression at Scale cs.CL · 2026-06-08 · unverdicted · none · ref 13

    LCLMs are scaled 0.6B-encoder 4B-decoder compressors pre-trained on over 350B tokens that improve the Pareto frontier for general-task performance, compression speed, and peak memory in long-context language model inference.