AI news
In Line with DeepSeek-OCR: NeurIPS Paper Proposes Letting LLMs Read Long Text Like Humans
# Vision-Driven Token Compression: A Future Standard for Long-Context LLMs **Date:** 2025-11-10 12:38 Beijing  ## 📢 Overview A research team from **Nanjing University of Science and Technology**, **Central South University**, and **Nanjing Forestry University** has introduced a groundbreaking framework — **VIST*