# Lossless Tensor Compression as Program Synthesis

arXiv: https://arxiv.org/abs/2608.02162 · HTML: https://mlsanity.com/paper/2608.02162/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 33 references that are in the map.
- First posted on arXiv 3 Aug 2026.

## Builds on (most cited first, 17 of 17)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration](https://mlsanity.com/paper/2306.00978/) (2023)
- [GLM-5: from Vibe Coding to Agentic Engineering](https://mlsanity.com/paper/2602.15763/) (2026)
- [TF-Coder: Program Synthesis for Tensor Manipulations](https://mlsanity.com/paper/2003.09040/) (2020)
- [NeuZip: Memory-Efficient Training and Inference with Dynamic Compression of Neural Networks](https://mlsanity.com/paper/2410.20650/) (2024)
- [ZipNN: Lossless Compression for AI Models](https://mlsanity.com/paper/2411.05239/) (2024)
- [Huff-LLM: End-to-End Lossless Compression for Efficient LLM Inference](https://mlsanity.com/paper/2502.00922/) (2025)
- [ZipServ: Fast and Memory-Efficient LLM Inference with Hardware-Aware Lossless Compression](https://mlsanity.com/paper/2603.17435/) (2026)
- [The KoLMogorov Test: Compression by Code Generation](https://mlsanity.com/paper/2503.13992/) (2025)
- [ZipLLM: Efficient LLM Storage via Model-Aware Synergistic Data Deduplication and Compression](https://mlsanity.com/paper/2505.06252/) (2025)
- [To Compress or Not? Pushing the Frontier of Lossless GenAI Model Weights Compression with Exponent Concentration](https://mlsanity.com/paper/2510.02676/) (2025)
- [ZipMoE: Efficient On-Device MoE Serving via Lossless Compression and Cache-Affinity Scheduling](https://mlsanity.com/paper/2601.21198/) (2026)
- [ENEC: A Lossless AI Model Compression Method Enabling Fast Inference on Ascend NPUs](https://mlsanity.com/paper/2604.03298/) (2026)
- [Floating-Point Data Transformation for Lossless Compression](https://mlsanity.com/paper/2506.18062/) (2025)
- [Approaching Shannon Bound with Lossless LLM Weight Compression](https://mlsanity.com/paper/2606.15789/) (2026)
- [OpenZL: A Graph-Based Model for Compression](https://mlsanity.com/paper/2510.03203/) (2025)

## Built on by (most cited first, 1 of 1)

- [ULPack: Reference-Conditioned Lossless Compression of Checkpoint Trajectories](https://mlsanity.com/paper/2610.14184/) (2026)

## Abstract (arXiv)

Model checkpoints are growing in both number and size, which makes archival, transfer, and deployment increasingly costly. General-purpose compressors can reduce storage requirements but ignore tensor structure, whereas existing tensor-specific compressors rely on fixed and format-specific pipelines. We present Brevis, which formulates lossless tensor compression as program synthesis. We design a typed domain-specific language (DSL) that captures recurring tensor structures, such as repeated regions and floating-point fields, through a set of reversible operators. Given a tensor, Brevis synthesizes a self-contained DSL program that reconstructs it bit-exactly. A checkpoint-specific production prior, learned from a small representative sample of tensors, guides a bounded A* search to synthesize compact programs, which can later be executed directly for bit-exact decompression. On 10 public checkpoints spanning language, audio, and image generation models, Brevis reduces 2.13 TB of checkpoint data to 1.41 TB, a 33.93% storage reduction. It produces archives up to 30.87% smaller than those of four general-purpose compressors, including zstd and gzip, and smaller archives than the tensor-specific compressors ZipNN and DFloat11. Under a practical concurrency configuration, Brevis achieves 3.60 GB/s compression and 6.61 GB/s decompression while preserving every source byte.