Strong New RAG Solution for Mixed Corpora
tomaarsen · x · 2026-07-17
This is a major release tailored for mixed-corpus RAG, specifically optimized for scenarios blending PDFs, scanned pages, and plain text.
Key details from the post include:
- A workflow designed for team-based retrieval-augmented generation over mixed corpora
- A training scale of 213K training groups for only a single epoch
- By contrast, competitors often use millions of samples or rely on distillation from larger teacher models, suggesting significant room for improvement in this recipe
- Although trained on English data, it performs well in French on ViDoRe V3, even surpassing English in three domains
Overall, this reads more like a research-backed RAG solution/study rather than mere marketing.
Related event: LightOn-rerank Targets Mixed-Corpus RAG With Multimodal Rerankers(10 posts)→
More from Research
- UK AISI: under $80 of fine-tuning fully restores filtered bio capabilities in open-weight models — connoraxiotes · 2026-10-27
- RFD4-Proteina runs on an RTX 3060: protein design from $0.001 per design — AllThingsApx · 2026-10-27
- University of Freiburg's Generative Intelligence Lab recruiting funded PhDs via ELLIS, apply by Oct 31 — yuyinzhou_cs · 2026-10-27
- Nature Physics: reprogrammable refractive index enables arbitrary multimode wave control for ML — MarioKrenn6240 · 2026-10-27
- Wakaru open-sources ontologize: labeling datasets from model activations — amplifiedamp · 2026-10-27
- EMNLP Oral paper traces multilingual representations in LLMs with cross-layer transcoders — ZhijingJin · 2026-10-27