EviViT is a lightweight attachment for pretrained vision transformers that learns where to focus detail in high‑resolution images. It uses human visual‑search traces to supervise a question‑conditioned evidence density, guiding regional re‑reading and efficient visual token allocation. The method connects regional features to the global scene via a sparse, coordinate‑aware bridge, improving fine‑grained accuracy across nine host models while using fewer tokens than global‑only processing.
arXiv:2605.26380v2 Announce Type: replace-cross Abstract: Frontier multimodal large language models (MLLMs) have been reported to achieve over 90\% accuracy on fine-grained perception benchmarks. How...
arXiv:2608.29092v1 Announce Type: new Abstract: Large vision-language models (LVLMs) frequently generate content unsupported by visual inputs. Preliminary experiments show that visual evidence is pri...
arXiv:2608. 04496v1 Announce Type: cross Abstract: Visual inputs in vision-language models (VLMs) are often encoded into substantially longer token sequences than text, making visual tokens a major bottleneck for efficient inference.
arXiv:2603. 00171v3 Announce Type: replace-cross Abstract: Multimodal Large Language Models (MLLMs) are shifting towards "Thinking with Images" by actively exploring image details.
arXiv:2608.28707v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) have achieved remarkable progress in Visual Question Answering (VQA), yet they continue to struggle with quest...
arXiv:2608. 08021v1 Announce Type: cross Abstract: Vision-Language Models (VLMs) should answer from concrete image evidence rather than language priors, dataset shortcuts, or irrelevant visual context.
arXiv:2608.28698v1 Announce Type: new Abstract: Compared with typical vision-language tasks, document parsing places stronger demands on fine-grained visual perception. Existing vision-language model...
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.
arXiv:2608.21819v1 Announce Type: cross Abstract: Reliable image captioning in Vision-Language Models (VLMs) requires captions to be both precise and complete, avoiding unsupported object mentions wh...
arXiv:2608.22429v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) capable of thinking with images often rely on external tools for fine-grained perception. However, this relian...
The paper introduces Visual Retrieval Heads (VRHs), a small fraction of attention heads in vision‑language models that are causally responsible for grounding text descriptions to image regions. By recasting head‑scoring methods and evaluating across eleven VLMs and five benchmarks, the authors show that masking the top 20 VRHs can drop grounding accuracy by up to 80 percentage points, while random masking has little effect. VRHs generalize across various visual reference tasks, preserve output format while corrupting localization, and transfer causally across models sharing an LLM backbone.
arXiv:2607. 26107v1 Announce Type: cross Abstract: Dense vision-language understanding, including object localization, region recognition, and open-vocabulary semantic segmentation, requires associating language concepts with spatially grounded visual regions.