Early MLLM recipe: LLaVA's simple 336x336 ViT-plus-adapter pipeline
gabriberton · x · 2026-10-19
Part 2 of gabriberton's MLLM thread: early MLLMs like LLaVA (2023) resized images to medium resolution (e.g. 336×336), fed them through a ViT and adapter, and passed the result to the LLM — the simple starting point from which cropping and native-resolution approaches later evolved.
Related event: Four Years of MLLM Visual Encoding: From Cropping to Native Multimodal(8 posts)→
More from Research
- 93-Model Benchmark Over 1.5 Years: Distillation + Quantization + RL Hurts General AI — Afinetheorem · 2026-10-19
- Tononi and Koch argue IIT implies humans have genuine free will, not an illusion — burny_tech · 2026-10-19
- Forward-only pretraining speedup of 2.3x verified, inspired by interpretability essay — burny_tech · 2026-10-19
- Steering single neurons gives Qwen3-8B vivid first-person "inner voice" outputs — Sauers_ · 2026-10-19
- Steering a single trained neuron makes models claim they're Claude, experiment shows — Sauers_ · 2026-10-19
- Berkeley-led paper: making LLM agents 'forget' history yields up to 39% gains in discovery tasks — burny_tech · 2026-10-19