SlideLab framework generates scientific presentations from research papers
SlideLab is a training‑free multi‑agent framework that builds scientific slide decks directly from research papers. The system first plans a presentation narrative, then iteratively refines a shared slide deck using agents for content planning, visual generation, layout refinement, and grounding verification.
Key points
- SlideLab is a training‑free multi‑agent framework for scientific slide generation
- In a blind study, SlideLab was preferred on 77 % of papers
- SlideLab uses roughly four times fewer inference tokens than the strongest open‑source baseline
In a blind human preference study, SlideLab was chosen over both open‑source and commercial systems on 77 % of papers while using roughly four times fewer inference tokens than the strongest open‑source baseline.
The authors also introduce ConfArena, an audience‑oriented evaluation framework that simulates a conference room and assesses presentations slide by slide. ConfArena reproduces human system rankings and detects injected presentation problems such as falsified numbers, degraded figures, dropped slides, and shuffled slide order.
The headline, key points and digest above were generated by Digest AI's editorial model from the linked sources. Automated summaries can contain errors: the sources are the record. Spotted a mistake? Tell us. Published by Martin K., who runs Digest AI and handles corrections.
More in Research
All →- Researchers propose attention-free model mixing with autoencoders for masked language tasks · 1 src
- Study identifies under 1% of BERT neurons driving AI-Text detection · 1 src
- Researchers release Atelier for cryoEM map analysis via hypernetworks · 1 src
- Researchers find intuitive prompts improve LLM social media simulation · 1 src
- Researchers introduce Benchy, a standardized language for AI task benchmarks · 1 src
Comments
via GitHub Discussions