conftrace_

run-length encoding

2 papers

Explore in graph

Also known as

RLE

Co-occurring keywords · papers mentioning both

training speedup (1) semantic descriptor (1) token reduction (1) token compression (1) model efficiency (1) vision-language task (1) multimodal large language model (1) video transformer (1) efficient inference (1) text generation (1)

Papers

Text4Seg: Reimagining Image Segmentation as Text Generation ICLR 2025 Don't Look Twice: Faster Video Transformers with Run-Length Tokenization NeurIPS 2024