Cross-modal alignment follows a scaling law, validated across 85 new runs
randall_balestr · x · 2026-10-30
The alignment between JEPAs and vision models follows a scaling law in the fraction of good views and samples seen. The authors registered its predictions, then ran 85 new experiments: the law predicted outcomes as accurately as rerunning with a different seed. Attached chart shows alignment vs log-scale samples across good-view fractions.
More from Research
- After 4 years growing brain cells on electrodes, startup ships 0.5¢/sec video model mischief 1 — emmanuelvivier · 2026-10-31
- Steering an "Einstein neuron" in Qwen 4B produces dramatically different answers — thursdai_pod · 2026-10-31
- Protein binder scoring head-to-head: ipDAE consistently strong, OpenDDE+ipTM surprisingly good at 80% PPV — AllThingsApx · 2026-10-31
- Turing TTS benchmark: best voice AI fools listeners only ~10% of the time — omarsar0 · 2026-10-31
- Ablation study: fine-grained MoE is the best LLM architecture change since GPT-3 — stochasticchasm · 2026-10-31
- Yann LeCun to Keynote MAIN2026 on World Models for Reasoning and Planning — karimjerbineuro · 2026-10-31