EMNLP paper DemoICL: learning novel procedural knowledge from in-context video demos
liuziwei7 · x · 2026-08-26
A new EMNLP paper, DemoICL, tackles demo-driven video in-context learning: learning dynamic, novel procedural knowledge from in-context video demonstrations, going beyond static internal knowledge. The authors note they're excited to see demo-driven in-context learning take off. Both paper and code are available.
Related event: Demo-ICL Paper on Video In-Context Learning Accepted by EMNLP 2026(2 posts)→
More from Research
- Knowledge editing experiments may mislead interpretability conclusions — yoavgo · 2026-08-26
- Figma acquires Lica to explore AI taste and visual design — omooretweets · 2026-08-26
- Recovering encrypted LLM reasoning traces leaks sensitive data — dl_weekly · 2026-08-26
- Study: Giving AI Agents Memory of Past Work Mostly Makes Them Worse — alex_verem · 2026-08-26
- Yoav Goldberg: Interpretability core is understanding mechanisms, not just methods — yoavgo · 2026-08-26
- Yoav Goldberg: interpretability that serves steering is just steering research with a handicap — yoavgo · 2026-08-26