Fine-tuned fake knowledge collapses in one epoch, pre-trained knowledge fades far slower
_vztu · x · 2026-10-17
Thread entry 4 (pitfall 2): most benchmarks inject fake identities via fine-tuning then unlearn them; that knowledge collapses within one epoch, while real pre-trained knowledge (faces, landmarks) fades far more slowly on both LLaVA-1.5 and Qwen3-VL.
More from Research
- SAE features are only partially compositional, new paper finds — OpenSAE · 2026-10-17
- Contact-UAN: MIT's residual world model fixes humanoid sim-to-real with 6.5 minutes of data — kevin_zakka · 2026-10-17
- ROS 2 LiDAR localization runs 390 m outdoors on handheld Livox MID-360 — rsasaki0109 · 2026-10-17
- New paper asks how seriously to take AI welfare, with constraints from consciousness epistemology — birchlse · 2026-10-17
- GPT-6 Astra fastest-rising method on Papers with Code, 27 papers in 30 days — NielsRogge · 2026-10-17
- Embodied Astra tops RoboMME at 92.1% — beating humans by just keeping full visual history in context — hankyang94 · 2026-10-17