← 研踪 PaperTrailarXiv:2610.32664 · v2
Zoom Where the Answer Looks: Cross-Resolution Self-Distillation for MLLMs under Visual-Token Budgets
首次提交 2026-10-23 22:07
版本更新 2026-11-13 16:29
雷达观测 2026-11-16 10:40
摘要
Under the small per-view visual-token budgets of efficient deployment, the fine text of documents, charts and infographics becomes illegible to multimodal large language models (MLLMs). Zooming in recovers it, but the region must be chosen before the model answers. Existing methods decode an answer or a box first, at the cost of generation, or read the attention available before answering, which localizes the evidence only in top layers whose depth varies with model size. Learned region proposers instead distill the attention of the model's answers, but on the same budgeted view. Yet this attention is precise only on a view the model can read: on Qwen3-VL-4B, a window around its peak covers 83% of the evidence on a high-resolution view but 54% on the budgeted view. Since answers and high-resolution views are available during training, we introduce LookZoom, a zooming method that trains a dedicated look token by cross-resolution self-distillation of the answer's attention: with the MLLM frozen, the token learns to attend on the budgeted view, before any answer, where the model's own correct answers attend on a high-resolution view. The region around its attention peak is the window to zoom into, and reinforcement learning then trains the MLLM to answer from both views. With 98 visual tokens per view on five text-rich benchmarks, LookZoom surpasses attention-guided zooming by 20-24 points and grounding-based zooming and learned crop routing by 12-15 points on Qwen3-VL at three scales, and it outperforms learned region proposers at every budget from 98 to 392 tokens. On Qwen3-VL, the look token alone, with the MLLM frozen, already surpasses every baseline that leaves the language model unchanged, and the recipe carries over to InternVL3.5 and Qwen2.5-VL.
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。
v2 · 2026-11-13 16:29 · 最新观测版本
Zoom Where the Answer Looks: Cross-Resolution Self-Distillation for MLLMs under Visual-Token Budgets
Under the small per-view visual-token budgets of efficient deployment, the fine text of documents, charts and infographics becomes illegible to multimodal large language models (MLLMs). Zooming in recovers it, but the region must be chosen before the model answers. Existing methods decode an answer or a box first, at the cost of generation, or read the attention available before answering, which localizes the evidence only in top layers whose depth varies with model size. Learned region proposers instead distill the attention of the model's answers, but on the same budgeted view. Yet this attention is precise only on a view the model can read: on Qwen3-VL-4B, a window around its peak covers 83% of the evidence on a high-resolution view but 54% on the budgeted view. Since answers and high-resolution views are available during training, we introduce LookZoom, a zooming method that trains a dedicated look token by cross-resolution self-distillation of the answer's attention: with the MLLM frozen, the token learns to attend on the budgeted view, before any answer, where the model's own correct answers attend on a high-resolution view. The region around its attention peak is the window to zoom into, and reinforcement learning then trains the MLLM to answer from both views. With 98 visual tokens per view on five text-rich benchmarks, LookZoom surpasses attention-guided zooming by 20-24 points and grounding-based zooming and learned crop routing by 12-15 points on Qwen3-VL at three scales, and it outperforms learned region proposers at every budget from 98 to 392 tokens. On Qwen3-VL, the look token alone, with the MLLM frozen, already surpasses every baseline that leaves the language model unchanged, and the recipe carries over to InternVL3.5 and Qwen2.5-VL.
查看此版本解读 →查看此版本原文 ↗