Sketch, Don't Paint: Allocating Test-Time Compute in Generative Visual Reasoning
Event overview(model summary, not the source's own text)
Sketch, Don't Paint: Allocating Test-Time Compute in Generative Visual Reasoning — 3 reports from 2 sources so far.
How this story unfolded
Left: what it concluded — the key points the model distilled from the reports below, each one listing the reports it rests on. Right: what happened — ordered by time, each with a short summary so you can follow the thread without clicking through. The numbered links work both ways: tap a source under a point to jump to that report, tap the cited-by chip on a report to jump back to the point.
Key points0 items Model summary · ordered by when the evidence was published
- Only a handful of reports so far — the model has not distilled any key points yet.
ReportsBy publish time · newer further down
- November 18, 2026 · Wed
- Start
Sketch, Don't Paint: Allocating Test-Time Compute in Generative Visual Reasoning
Original summary arXiv:2611.21812v1 Announce Type: new Abstract: Multimodal models increasingly reason by synthesizing pixels, sketching maze paths within interleaved chains of thought or rolling o
arXiv cs.CV Original ↗ - November 19, 2026 · Thu
- +1d 0h
Keep the Reasoning, Read the Image: On-Demand Visual KV for Multi-Turn Reasoning VLMs
Original summary arXiv:2611.23769v1 Announce Type: new Abstract: Reasoning vision-language models (VLMs) think for thousands of tokens before they answer, and retention policies keep the KV cache a
arXiv cs.CV Original ↗ - November 20, 2026 · Fri
- +2d 0h
When and How Much to Imagine: Adaptive Test-Time Scaling with World Models for Visual Spatial Reasoning
Original summary arXiv:2602.08236v3 Announce Type: replace-cross Abstract: Despite rapid progress in MLLMs, visual spatial reasoning remains unreliable when correct answers depend on how a scene wo