lossless compression
- 70% Size, 100% Accuracy: Lossless LLM Compression for Efficient GPU Inference via Dynamic-Length Float (DFloat11)
- Better Language Model Inversion by Compactly Representing Next-Token Distributions
- Compress & Cache: Vision token compression for efficient generation and retrieval
- Large Language Models for Lossless Image Compression: Next-Pixel Prediction in Language Space is All You Need
- MoRIC: A Modular Region-based Implicit Codec for Image Compression