MOSS@COLM 2026 spotlights small-scale LLM research with talks by Danqi Chen and Omar Khattab
sewon__min · x · 2026-10-10
The MOSS@COLM2026 workshop takes place Oct 9 at Hilton Union Square in San Francisco (also on Zoom), asking how far LLM research can go in the under-explored small-scale regime of compute, data, and model size. Organizers argue small-scale settings yield more efficient algorithms and enable fast, controlled experiments.
Morning agenda includes:
- Danqi Chen: "Making the Case for Small Language Models," covering LMs playing and explaining chess plus lessons from years of SLM training
- Omar Khattab: "AI at the last mile"
This is the second edition of MOSS, after MOSS@ICML25.
Related event: MOSS Workshop at COLM 2026 Focuses on Small-Scale Models(2 posts)→
More from Research
- COLM 2026 announces workshop on Scientific Understanding of Foundation Models, deadline June 23 — valentina__py · 2026-10-10
- Scale AI's HSS benchmark: top model scores 53.6% on intuitive visual reasoning vs 93.1% for humans — geoffwolfe · 2026-10-10
- Elliot Glazer on when a Lean proof actually proves the math we care about — ctjlewis · 2026-10-10
- CS theorist Lance Fortnow on AI and math: don't panic, read a new proof — fortnow · 2026-10-10
- Skill Constellations: first dated copy network of 2.1M agent-skill adoptions on GitHub — UBC-O · 2026-10-10
- Physical attention bias cuts cable-simulation prediction error by 15%+ — Avihai Giuili · 2026-10-10