MLLM-Token-Compression

[TMLR 2026] Survey: https://arxiv.org/pdf/2507.20198

Awesome LLM compression research papers and tools.

[EMNLP'23, ACL'24] To speed up LLMs' inference and enhance LLM's perceive of key information, compress the prompt and KV-Cache, which achieves up to 20x compression with minimal performance loss.