arXiv:2604. 02343v2 Announce Type: replace-cross Abstract: We study the compression of LLM-generated text across lossless and lossy regimes, characterizing a compression-compute frontier where more compression is possible at the cost of more compute.
arXiv:2608. 11249v1 Announce Type: cross Abstract: We study the problem of lossless text compression, motivated by the rapid growth in the collection and storage of digital textual data - including plain text, source code, and structured formats such as XML - and by recent advances in neural language model-based compression.
arXiv:2607. 24192v1 Announce Type: cross Abstract: We study the problem of lossless compression of source code, motivated by the storage demands of large-scale software archives, such as Software Heritage (https://www.
arXiv:2607. 18280v1 Announce Type: cross Abstract: Large language models (LLMs) are often compressed through static parameter pruning or dynamic token-level computation, yet aggressive sparsification can trigger rapid performance degradation beyond an essential sparsity boundary.
arXiv:2608.00311v2 Announce Type: replace Abstract: Long-context inference with large language models (LLMs) is costly: self-attention during prefill scales quadratically with sequence length, and th...
arXiv:2609.07966v1 Announce Type: new Abstract: Key--value (KV) cache compression is an effective way to reduce the memory overhead of large language model (LLM) inference, particularly for long-cont...
The paper investigates prompt minimization, aiming to reduce prompts to their smallest, most information-dense form without losing output fidelity. It argues that shorter prompts lower computational overhead and inference latency, especially when large contexts are unnecessarily included, and that longer prompts can harm LLM reasoning and accuracy. The authors propose three frameworks to identify minimal prompts and show that these often produce outputs comparable to longer versions, highlighting redundancy in the input space and opening new avenues for efficient prompt engineering.
arXiv:2410. 06458v2 Announce Type: replace-cross Abstract: Instruction following is a key capability for LLMs.
arXiv:2609.22100v1 Announce Type: cross Abstract: Retrieval-augmented generation (RAG) improves language models with retrieved evidence, but processing many long passages is costly and can introduce...
arXiv:2606. 09659v1 Announce Type: cross Abstract: Long-context language model inference is bottlenecked by memory, as the KV cache grows with context length.
Long-context language model inference is bottlenecked by memory, as the KV cache grows with context length. Recent techniques to compress the KV cache fall short: they either degrade model quality substantially or require considerable time and compute to compress a single long prompt.
arXiv:2609.25537v1 Announce Type: new Abstract: Large language model (LLM) inference is constrained by the quadratic scaling of self-attention and the linear scaling of the KV cache, increasing laten...
arXiv:2607. 06519v1 Announce Type: new Abstract: Long-context LLM inference is increasingly limited by the memory and bandwidth cost of KV caches, yet aggressive compression can remove the layer-specific evidence needed for retrieval and multi-step reasoning.