AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

ProLaViT: Learning Progressive Latent Visual Thoughts in Structured Latent Space

Peiming Li, Yifan Wang, Xiaotian Zhang, Zhiyuan Hu, Shiyu Li, Zheng Wei, Yang Tang

ECCV 2026 · Vision-language and multimodal › Multimodal LLMs · approach: Chain-of-thought multimodal reasoning · 1 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
replace one-step latent prediction with progressive multi-step latent chain (ablation)ProLaViT · avg of 4 benchmarksaccuracy (%): 69.28 -> 76.73 (+7.45)Improved
progressive chain instead of one-step latent prediction (ablation)ProLaViT · ChartQAaccuracy (%): 63.02 -> 78.99 (+15.97)Improved
progressive chain instead of one-step latent prediction (ablation)ProLaViT · BLINK-Jigsawaccuracy (%): 66.00 -> 76.00 (+10.00)Improved
add distance-weighted diversity loss (ablation)ProLaViT · avg of 4 benchmarksaccuracy (%): 75.14 -> 77.34Improved
add distance-weighted diversity loss (ablation)ProLaViT · BLINK-Jigsawaccuracy (%): 71.33 -> 76.00 (+4.67)Improved
add distance-weighted diversity loss (ablation)ProLaViT · ChartQAaccuracy (%): 76.18 -> 78.99 (+2.81)Improved
add margin-based diversity loss without distance weights (ablation)ProLaViT · BLINK-Jigsawaccuracy (%): 71.33 -> 67.33 (-4.00)Hurt
add margin-based diversity loss without distance weights (ablation)ProLaViT · avg of 4 benchmarksaccuracy (%): 75.14 -> 74.32Hurt
use native Qwen2.5-VL ViT teacher instead of DINOv2 (ablation)ProLaViT · avg of 4 benchmarksaccuracy (%): 75.57 -> 77.34Improved
use native ViT teacher instead of SDXL-VAE (ablation)ProLaViT · VisPuzzleaccuracy (%): 45.50 -> 74.25Improved
use canonical coarse-to-fine step order instead of random order (ablation)ProLaViT · avg of 5 benchmarksaccuracy (%): 71.16 -> 77.40 (-6.24 for random)Improved
use canonical order instead of random on CV-Bench (ablation)ProLaViT · CV-Benchaccuracy (%): 69.14 -> 77.66 (-8.52 for random)Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy