AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

Vision-as-Inverse-Graphics Agent via Interleaved Multimodal Reasoning

Shaofeng Yin, Jiaxin Ge, Zora Wang, Xiuyu Li, Chenyang Wang, Michael Black, Trevor Darrell, Angjoo Kanazawa, Haiwen Feng

ECCV 2026 · Vision-language and multimodal › Multimodal LLMs · approach: Multimodal LLM benchmarks · 53 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
increase best-of-N search budget from 1 to 4 (ablation)VIGA · BlenderBench Task 1VLM score: 1.44 -> 3.25Improved
add sliding-window multimodal memory (ablation)VIGA · qualitative sequential generationcontext retentionImproved
bound memory with a sliding window instead of unconstrained history (ablation)VIGA · long-horizon generationgeneration qualityImproved
use VIGA code-render-inspect loop instead of one-shotQwen3-8B · SlideBenchExecution: 0.10 -> 0.54Improved
use VIGA instead of one-shotClaude-3.5 · SlideBenchExecution: 0.93 -> 0.90Hurt
use VIGA instead of BlenderAlchemy at best-of-1GPT-4o · BlenderBench Task 1VLM score: 1.75 -> 1.44Hurt
use VIGA instead of BlenderAlchemy at best-of-4GPT-4o · BlenderBench Task 2Photometric loss: 1.95 -> 2.94Hurt
use VIGA instead of one-shotQwen3-8B · BlenderGym Blend ShapePhotometric loss: 7.76 -> 13.51Hurt
use VIGA instead of one-shotGemini-2.5-Pro · BlenderGym Blend ShapePhotometric loss: 7.01 -> 7.62Hurt
use VIGA instead of one-shotGemini-2.5-Pro · BlenderBench Task 2Photometric loss: 10.14 -> 1.99Improved
use VIGA with Qwen3-VL-8B instead of BlenderAlchemy (best-of-1)Qwen3-VL-8B · BlenderBenchaverage relative improvement: +312.20%Improved
use VIGA instead of one-shot and BlenderAlchemy on BlenderGymVIGA · BlenderGymaverage improvement: +35.32%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