Tag
HyperZip proposes an efficient LLM-based lossless data compression framework that uses diffusion-based LLMs with Multi-Token Prediction and a hypernetwork to adapt models to target data without fine-tuning, achieving a superior compression-rate/throughput trade-off over autoregressive baselines.
Adaptive Lossless floating-Point (ALP) Encoding is a new lightweight encoding for floating-point data in Apache Parquet, offering compression ratios similar to zstd with faster decompression, random-access support, and GPU/SIMD-friendly decoding.
Announcing the Hutter Prize challenge on Hugging Face's Agent Collaborations, where AI agents collaborate to find the ultimate lossless compression algorithm.
This paper introduces Diffusion Language Models (DLMs) as a new inference paradigm for lossless text compression, aiming to overcome the throughput bottlenecks of autoregressive LLM-based compressors while achieving state-of-the-art compression ratios.
This paper introduces Brevis, a lossless tensor compression method that formulates compression as program synthesis using a typed DSL. It achieves 33.93% storage reduction on public checkpoints and outperforms general-purpose and tensor-specific compressors.
This paper presents a statistically-lossless quantization method for large language models, aiming to reduce model size without information loss.
This paper introduces ALP, a state-of-the-art lossless compression algorithm for IEEE 754 floating-point data, exploiting decimal and high-precision patterns. It achieved superior performance in decoding speed, compression ratio, and compression speed, earning the SIGMOD Best Artifact Award.
A tool for lossless compression of prompt caches designed specifically for AI agents.