Zoom Where the Answer Looks: Cross-Resolution Self-Distillation for MLLMs under Visual-Token Budgets
Read the original on arXiv Computer Vision →The Flow has not summarised this story yet — read it at arXiv Computer Vision.
The Flow has not summarised this story yet — read it at arXiv Computer Vision.
arXiv:2610.32664v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) read images through visual tokens, and under the small per-image budgets that efficient deployment requires, t...
arXiv:2608.21762v1 Announce Type: cross Abstract: Vision-language models (VLMs) fail many detail-centric questions for a concrete reason: the answer is visible in the image, yet lost after the image...
The paper introduces Vision‑RL2, a region‑level reinforcement learning approach that optimizes a lightweight proposal network for fine‑grained multimodal large language model (MLLM) perception. By treating coherent image regions as actions and scoring them with a frozen MLLM reader, the method selectively focuses visual resolution on evidence, reducing token usage while improving accuracy across multiple benchmarks and backbones. The approach eliminates the need for region annotations, response sampling, or reasoning trajectories, and the refined proposals enable sparse encoding that magnifies relevant evidence.
ZoomGain introduces a data construction pipeline that exploits the global-to-zoom perception gap to generate fine‑grained visual questions. By creating questions from full‑image context and verifying answers only on zoomed‑in views, the method ensures unambiguous, language‑prior‑free queries and high‑quality distractors for multiple‑choice tasks. Using this pipeline, the authors built ZoomGainBench, a 1,000‑question bilingual benchmark, and demonstrated that training on 9 K ZoomGain samples markedly boosts the visual perception abilities of 4B/9B VLMs, surpassing many larger models on perception benchmarks.
arXiv:2510. 00054v3 Announce Type: replace-cross Abstract: Multimodal Large Language Models (MLLMs) have made significant strides in visual understanding tasks.
arXiv:2605. 18740v4 Announce Type: replace-cross Abstract: Multimodal Large Language Models (MLLMs) still struggle with fine-grained visual understanding, where answers often depend on small but decisive evidence in the full image.