BrainLoRA adapts Qwen3-Omni to predict fMRI brain responses with 350x less compute
_akhaliq · x · 2026-10-21
BrainLoRA applies LoRA to Alibaba's Qwen3-Omni to predict fMRI responses to video, achieving top performance on the Algonauts 2025 challenge.
- Sliding-window baselines need 3,500 forward passes and 700 GPU-hours per clip; BrainLoRA's single causal pass needs 1 forward pass and 2.0 GPU-hours — a 350x compute reduction.
- Video, audio, and text are processed within one causal pass, showing PEFT's potential for scaling brain encoding.
More from Embodied
- Plato ring launches at $199 to turn near-silent speech into AI commands — TinfoilTricorn · 2026-10-21
- Dream-1 controlled 31 unseen robot types across 53 countries within 24 hours — gharik · 2026-10-21
- Stanford's T2-z lets robots probe hidden physics with a poke, lifting success from 34% to 73% — stanfordnlp · 2026-10-21
- Snap Hires Robert Downey Jr. as Chief Customer Experience Officer to Sell Specs AR Glasses Against Meta — adariostrange · 2026-10-21
- Fei-Fei Li team unveils FACT, a force-aware foundation model for robot dexterity — stanfordnlp · 2026-10-21
- Upcoming paper claims big models can handle latency-critical real-time robotics — ManlingLi_ · 2026-10-21