arXiv subjects

Annabelle Michael Carrell

Publications and source records attributed to Annabelle Michael Carrell.

3 recordsLinked to original sources

arXiv2026

Haiku to Opus in Just 10 bits: LLMs Unlock Large Compression Gains

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. For lossless compression, domain-adapted LoRA adapters can improve LLM-based arithmetic coding by 2x over compression with the base LLM alone. For lossy compression, prompting a model for a succinct rewrite then applying arithmetic coding can achieve compression ratios of approximately 0.03, a 2x improvement over compressing the original response. We further introduce Question-Asking compression (QA), an interactive lossy protocol inspired by the game 'Twenty Questions'. A small model iteratively refines its response by asking yes/no questions to a stronger model, transferring exactly one bit per answer. On 8 benchmarks spanning math, science, and code, 10 binary questions recover 23% to 72% of the capability gap between a small and large model on standard benchmarks and 7% to 38% on harder benchmarks, achieving compression ratios of 0.0006 to 0.004. This is over 100x smaller than prior LLM-based compression (Deletang et al., 2024), suggesting that interactive protocols can transfer knowledge far more efficiently than transmitting full responses.

cs.LG↗

arXiv2026

Express Language Modeling

We introduce a new tool, Express, for converting a non-causal attention approximation into a causal approximation with matching approximation guarantees. When combined with the state-of-the-art Thinformer approximation, Express improves upon the best known causal attention guarantees, delivering $\log^{3/2}(n)/s$ approximation error with only $O(s)$ memory and $O(s^2 \log^2(n))$ compression overhead for a sequence of length $n$. We pair these developments with an efficient I/O-aware Triton implementation, demonstrate substantial speedups over FlashAttention 2, and use Express to overcome four resource bottlenecks in the language modeling pipeline: long-context prefill, KV cache compression, long-form memory-constrained decoding, and long-form compute-constrained decoding.

cs.LG↗

arXiv2026

Low-Rank Thinning

The goal in thinning is to summarize a dataset using a small set of representative points. Remarkably, sub-Gaussian thinning algorithms like Kernel Halving and Compress can match the quality of uniform subsampling while substantially reducing the number of summary points. However, existing guarantees cover only a restricted range of distributions and kernel-based quality measures and suffer from pessimistic dimension dependence. To address these deficiencies, we introduce a new low-rank analysis of sub-Gaussian thinning that applies to any distribution and any kernel, guaranteeing high-quality compression whenever the kernel or data matrix is approximately low-rank. To demonstrate the broad applicability of the techniques, we design practical sub-Gaussian thinning approaches that improve upon the best known guarantees for approximating attention in transformers, accelerating stochastic gradient training through reordering, and distinguishing distributions in near-linear time.

stat.ML↗