FAIR Vet Recalls BERT-Era Experiment: Frozen Encoders Plus One Linear Layer Aligned Vision and Text
ylecun · x · 2026-10-10
In a thread with Yann LeCun, former FAIR researcher Thomas Scialom recalls running the same alignment idea back in the BERT days: frozen visual encoder + frozen BERT with a single linear layer between them — and it worked remarkably well. He credits FAIR's zero-shot cross-lingual alignment work as the direct inspiration for the intuition.
More from Research
- PopVax's AI-designed fridge-stable RNA vaccine enters Phase I human trial — SeyoneC · 2026-10-11
- Stanford paper simulates AI eval ecosystem with LLM agents: holdout design tradeoffs — sanmikoyejo · 2026-10-11
- First AI Measurement Science workshop at COLM 2026 targets rigorous AI evaluation — sanmikoyejo · 2026-10-11
- Nat Lambert advises Mercor on RL data: evals science is the next frontier — natolambert · 2026-10-11
- Open-source LLM simulator separates structural effects from LLM quirks in benchmark markets — sanmikoyejo · 2026-10-11
- Simulation platform tests how evaluator independence and mandatory disclosure reshape AI markets — sanmikoyejo · 2026-10-11