Cohere Labs Open Science Community hosts three public ML talks next week
Cohere_Labs · x · 2026-10-15
Cohere Labs' Open Science Community announced three public sessions for Oct 19-23:
- Late-Stage Patching Full-Attention Transformers to Gated DeltaNets (Anupam Nayak, CMU PhD student): converting pretrained full-attention transformers into efficient hybrid architectures late in training; via representation alignment, off-policy distillation, and prolonged on-policy distillation, long-context reasoning and retrieval can be recovered with only a fraction of the original pretraining budget.
- Distributionally Robust Multi-Task RL via Adaptive Task Sampling (Nicholas Edward Corrado, UW-Madison).
- Beyond EdTech: Why Pedagogy Must Lead Technology (Anshika Verma, CEO of Omnix360).
All sessions are open for registration via Luma.
More from Research
- Schmidt Sciences awards $10M to 19 AI humanities research teams — OdedRechavi · 2026-10-15
- Mistral and CERN partner to build a Large Physics Model trained on billions of simulated collisions — MistralAI · 2026-10-15
- Global Transport coupling lifts guided flow generation: ImageNet FID 2.06 to 1.91 — mmbronstein · 2026-10-15
- Your breathing gives you away: Wi-Fi signals can reveal your breath rhythm — TinfoilTricorn · 2026-10-15
- Beyond text correlation: attaching a geometry simulator to ground model reasoning — gerardsans · 2026-10-15
- Sequen CEO Zoe Weil: Ranking Models Should Optimize Purchases, Not Clicks — TWIML AI Podcast · 2026-10-15