ELLIS x UniReps talk Oct 21: universal steering of AI models and steering fields
ClementineDomi6 · x · 2026-10-19
The ELLIS x UniReps speaker series hosts an event on October 21 at 16:00 CEST on why distinct learning processes yield similar representations and how far they can be unified. Keynote by Adit Radhakrishnan (MIT, Broad Institute of MIT and Harvard): "Toward universal steering of AI models". Flash talk by Simone Facchiano (Sapienza University of Rome): "Steering Fields: Adaptive Vector Fields for Safe Image Generation and Beyond". Join via Zoom or Discord.
More from Research
- Ropedia W0 shows 10k hours of human video yields a robot learning scaling law — liuziwei7 · 2026-10-20
- UCSD's CarryOn boosts agent OSWorld score 43.9→49.7 while cutting tokens 52% — mark_k · 2026-10-20
- Stanford lab launches Collaborative Intelligence Benchmark; OpenAI models found best teammates — james_y_zou · 2026-10-20
- Building an all-in-one infant EEG/MRI resource for ages 1-72 months — Dr_Alex_Crimi · 2026-10-20
- LidarVerse: one real-time LiDAR world model for reconstruction, forecasting and generation — ZGojcic · 2026-10-20
- Open-Source logos-theodolite Visualizes Layer-by-Layer LLM Internals — New_Alps_5655 · 2026-10-20