← 研踪 PaperTrailarXiv:2611.21812 · v1
Sketch, Don't Paint: Allocating Test-Time Compute in Generative Visual Reasoning
首次提交 2026-11-17 03:25
版本更新 2026-11-17 03:25
雷达观测 2026-11-18 19:44
摘要
Multimodal models increasingly reason by synthesizing pixels, sketching maze paths within interleaved chains of thought or rolling out video solutions frame by frame. Each visual thought runs the full diffusion schedule inherited from photorealistic synthesis, so iterative denoising dominates inference cost. We study how to allocate test-time compute along two axes: when to render visual thoughts rather than thinking in text or answering directly, and how many denoising steps each thought requires. Controlled interventions that vary only how the thought is rendered uncover three regimes. Causal thoughts carry the plan and become legible early: an 8-step sketch nearly matches a 50-step render in accuracy, commits to the same plan as often as two independent full renders agree, and in video models mostly fails by stalling short of the goal, so the rollout abstains. Decorative thoughts can be omitted without loss, whereas harmful thoughts lower accuracy. Because the regime depends on both model and task, always drawing is suboptimal. Across 14 model-benchmark pairs of three interleaved reasoners, answering directly, without any thinking, wins 9 pairs, and choosing among direct, text-only, and visual tiers from ten labeled examples per pair raises mean accuracy from 60.7% (always drawing) to 65.1%. Where drawing pays, we propose sketch-and-vote, which samples 8-step sketches (a step count chosen without labels) from independent noises until one answer reaches three votes. With this one setting, sketch-and-vote beats full rendering with fewer denoising steps on an image reasoner and two video reasoners, by 8.6 points on VSP spatial planning and by 9.6 and 22.1 points on mazes.
作者备注:11 pages, 5 figures, 3 tables
观测到的版本
相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。
v1 · 2026-11-17 03:25 · 最新观测版本
Sketch, Don't Paint: Allocating Test-Time Compute in Generative Visual Reasoning
Multimodal models increasingly reason by synthesizing pixels, sketching maze paths within interleaved chains of thought or rolling out video solutions frame by frame. Each visual thought runs the full diffusion schedule inherited from photorealistic synthesis, so iterative denoising dominates inference cost. We study how to allocate test-time compute along two axes: when to render visual thoughts rather than thinking in text or answering directly, and how many denoising steps each thought requires. Controlled interventions that vary only how the thought is rendered uncover three regimes. Causal thoughts carry the plan and become legible early: an 8-step sketch nearly matches a 50-step render in accuracy, commits to the same plan as often as two independent full renders agree, and in video models mostly fails by stalling short of the goal, so the rollout abstains. Decorative thoughts can be omitted without loss, whereas harmful thoughts lower accuracy. Because the regime depends on both model and task, always drawing is suboptimal. Across 14 model-benchmark pairs of three interleaved reasoners, answering directly, without any thinking, wins 9 pairs, and choosing among direct, text-only, and visual tiers from ten labeled examples per pair raises mean accuracy from 60.7% (always drawing) to 65.1%. Where drawing pays, we propose sketch-and-vote, which samples 8-step sketches (a step count chosen without labels) from independent noises until one answer reaches three votes. With this one setting, sketch-and-vote beats full rendering with fewer denoising steps on an image reasoner and two video reasoners, by 8.6 points on VSP spatial planning and by 9.6 and 22.1 points on mazes.
查看此版本解读 →查看此版本原文 ↗