NSF funds SAGE: AI video understanding to democratize personal coaching
amypavel · x · 2026-10-15
Researchers Lorenzo Torresani (Khoury College), Kristen Grauman (UT Austin) and Amy Pavel (UC Berkeley) received a three-year NSF grant to build SAGE (Skill Assessment and Guidance Engine), an AI personal coach. Users record themselves (e.g., a golf swing) and SAGE analyzes the video to give technique feedback, aiming to democratize access to expert coaching. Torresani notes a capability gap: today's AI describes actions well but struggles with subtle execution differences separating experts from beginners — the project's core challenge, alongside a lack of established training datasets.
More from Research
- DuplexJev Cuts Autoregressive Decoding for Voice Agents, Answering 80 Speech Decisions in 0.1s — adventists-ai · 2026-10-15
- LLM-to-Flow Distillation Adapts Scientific Generators to Natural-Language Discovery Goals — rbhar90 · 2026-10-15
- ETH's Uncertainty-Aware World Model Makes Offline RL Work on Real Robots — breadli428 · 2026-10-15
- 167,356 simulated shop-days: paper shows eval world design writes the model behavior it scores — liminal_bardo · 2026-10-15
- Multilingual NLP roadmap: researcher maps open problems from data selection to LID across 350+ languages — StellaLisy · 2026-10-15
- Beyond RAG: Injecting Tensor Memory Cartridges Into Layer-3 of a Frozen LLM — Nearby_Indication474 · 2026-10-15