109M text-JEPA beats zero-shot results of LLMs up to 8B: 64% vs 56% on ImageNet100
randall_balestr · x · 2026-10-30
Another key result from the PRH thread: on Phillip Isola's latest pair-free benchmark, the 109M text-JEPA beats every reported zero-shot result from LLMs up to 8B — 64% vs 56% accuracy on ImageNet100 — without ever using image-text pairs. The attached table shows the full comparison.
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