Visual Document Indexing Throughput Jumps 20x
tomaarsen · x · 2026-07-08
On an H100, V-SPLADE's document-side indexing throughput reaches 20.19 pages/sec, compared to just 0.83 pages/sec for Qwen3-VL captioning and 0.90 pages/sec for Tesseract OCR, demonstrating its potential to significantly replace traditional OCR/caption pipelines.
More from Research
- LTX 2.3 LoRA demo changes a video’s camera angle — CQDSN · 2026-07-21
- OpenForecaster uses daily news to improve language-model forecasting — Cohere_Labs · 2026-07-21
- SenseTime unveils U1 Pro and open-sources a 50M-sample vision dataset at WAIC 2026 — 机器之心 · 2026-07-21
- Baseten study finds new facts in LLM weights are fragile unless trained from many restatements — alex_verem · 2026-07-21
- Kimi K3 and Fable 5 now look much closer than the old open-vs-closed gap — FinanceYF5 · 2026-07-21
- uv-scripts/ocr returns to the top of Hugging Face datasets with a JSON model picker — vanstriendaniel · 2026-07-21