Project AELLA – Open LLMs for structuring 100M research papers
We're releasing Project AELLA - an open-science initiative to make scientific knowledge more accessible through AI-generated structured summaries of research papers. Blog: https://inference.net/blog/project-aella Visualizer: https://aella.inference.net Models: https://huggingface.co/inference-net/Aella-Qwen3-14B, https://huggingface.co/inference-net/Aella-Nemotron-12B Highlights: - Released 100K research paper summaries in standardized JSON format with interactive visualization. - Fine-tuned open models (Qwen 3 14B &…
What it does
In the maker’s words, at launch
We're releasing Project AELLA - an open-science initiative to make scientific knowledge more accessible through AI-generated structured summaries of research papers. Blog: https://inference.net/blog/project-aella Visualizer: https://aella.inference.net Models: https://huggingface.co/inference-net/Aella-Qwen3-14B, https://huggingface.co/inference-net/Aella-Nemotron-12B Highlights: - Released 100K research paper summaries in standardized JSON format with interactive visualization. - Fine-tuned open models (Qwen 3 14B & Nemotron 12B) that match GPT-5/Claude 4.5 performance at 98% lower cost (~$100K vs $5M to process 100M papers) - Built on distributed "idle compute" infrastructure - think SETI@Home for LLM workloads Goal: Process ~100M papers total, then link to OpenAlex metadata and convert to copyright-respecting "Knowledge Units" The models are open, evaluation framework is transparent, and we're making the summaries publicly available. This builds on Project Alexandria's legal/technical foundation for extracting factual knowledge while respecting copyright. Technical deep-dive in the post covers our training pipeline, dual evaluation methods (LLM-as-judge + QA dataset), and economic comparison showing 50x cost reduction vs closed models. Happy to answer questions about the training approach, evaluation methodology, or infrastructure!
Does the same job
all alternatives →
- ULUsing LLMs and >1k 4090s to visualize 100k scientific research articlesOct 2025 · twitter.com · ▲5
- PAPaperQA2, Agentic RAG for Science2024 · github.com · ▲8
We're excited to release PaperQA2, an open source RAG library specialized to work with the scientific literature. We've seen some really compelling results with it (https://paper.wikicrow.ai), like superhuman performance at question answering and summarization when compared with expert scientists. PaperQA2 is a major overhaul of our prior PaperQA system, it includes automatically obtained rich metadata for each paper, a CLI to work with local papers directly, a local full-text search engine for keywords searches over PDF files, a state-of-the-art algorithm for LLM-based re-ranking…
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 27d ago · cactuscompute.com
Launched alongside, November 2025
the whole month →
- IB
Life & fun · Nov 2025 · bitsnpieces.dev
- BBoing▲782
Life & fun · Nov 2025 · boing.greg.technology