IBM releases Palette: 20B small model generates slides
Understand this story
IBM Research released Palette, which fine-tunes a 20B-parameter open-weight model with synthetic data to generate presentations according to IBM Design Language. During training, designers write JSON briefs and a coder writes pptxgenjs code, with two LoRA roles dividing the work to complete slide generation. IBM says this method tests the hypothesis that a small open-weight model trained on synthetic data in its own design language and checked by validation tools can compete with frontier systems while preserving ownership of the results. This statement is IBM's description of the method's goal; the report does not provide measured results comparing it with frontier systems.
AI overview based on source reports · Updated 3 days ago
Coverage timeline
Follow the coverage to explore different perspectives.
- Hugging Face BlogPalette: teaching a small model to build decks in your design language
Palette fine-tunes a 20B open-weight model with LoRA to build slide decks in two roles—a designer that writes a structured JSON brief and a coder that writes pptxgenjs code per slide—trained on roughly 1,000 synthetic decks (~10,000 slides) generated by a large open teacher and filtered by a checker. On PresentBench it ranks first on Economics and Education, third on Talk, and second across the three-domain mean (59.7 vs. NotebookLM's 60.8). A check-and-repair harness that keeps a rewrite only when the checker confirms improvement adds 3.5 points on average across 131 decks.
Activity for this story
- Current comparable activity
- 3
- Peak comparable activity
- 10Nov 4 02:00
- Change in the past 24 hours
- -51%
Trends compare the same fully observed participants, which may cover fewer participants than current activity. Move the pointer or tap the chart to inspect hourly activity; use the left and right arrow keys with a keyboard.