AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

Diffusion-Based Immersive Visual Reasoning

Yifeng Zhang, Ming Jiang, Qi Zhao

ECCV 2026 · Vision-language and multimodal › Multimodal LLMs · approach: Chain-of-thought multimodal reasoning · 0 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
add LHR latent hypothesis refiner (with RGO) (ablation)DIVR · ZInD Hardaccuracy (%): 39.44 -> 41.89Improved
add LHR latent hypothesis refiner (with RGO) (ablation)DIVR · IQVAaccuracy (%): 54.24 -> 56.75Improved
add learned RGO instead of saliency viewports (ablation)DIVR with LHR · IQVAaccuracy (%): 53.46 -> 56.75Improved
add learned RGO instead of CLIP-similarity selection (ablation)DIVR with LHR · ZInD Hardaccuracy (%): 38.68 -> 41.89Improved
use dynamic CLIP viewport selection instead of static saliency (ablation)DIVR with LHR · IQVAaccuracy (%): 53.46 -> 55.14Improved
add LHR when using saliency viewports (ablation)DIVR · 360+Xaccuracy (%): 56.72 -> 57.71Hurt
increase diffusion steps from 5 to 20 (ablation)DIVR · ZInD Hardaccuracy (%): 38.46 -> 41.89Improved
increase diffusion steps from 5 to 20 (ablation)DIVR · ZInD Hardspeed (QPS): 3.57 -> 1.08Hurt
use DIVR active loop instead of saliency inputQwen2.5-VL-7B · IQVAaccuracy (%): 53.22 -> 56.75Improved
use cubemap instead of equirectangular inputQwen2.5-VL-7B · IQVAaccuracy (%): 43.54 -> 49.20Improved
use DIVR viewport selection instead of saliency viewportsDIVR · IQVA fixationNSS: 0.36 -> 0.49Improved
DIVR vs GPT-5 with saliency viewportsDIVR + Qwen2.5-VL-7B · ZInD Hardaccuracy (%): 35.64 -> 41.89Improved

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