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
- LightSuite: fast cell detection and whole-brain atlas registration on a standard workstation — hisspikeness · 2026-10-15
- Pathway CSO pitches BDH as post-Transformer architecture uniting memory, reasoning, adaptation — schwentker · 2026-10-15
- AI-designed molecular scissors cut Alzheimer's proteins — but is it really AI? — gerardsans · 2026-10-15
- EmbodiedEvo tops RoboDojo at 38.95% success by letting robots inherit failed practice — thetripathi58 · 2026-10-15
- 797GB of n-gram counts in CPU RAM let 1B models match 57% more compute — PangWeiKoh · 2026-10-15
- Google's HARNESS² evolves agent harnesses without verifiers, up to +11.5 points on WorkBuddy-Bench — dair_ai · 2026-10-15