FoAViS is a foveated active vision system that samples visual input using a log‑polar foveation and stores information in a 2D spatial memory. The system’s fixation policy is trained concurrently with tasks such as classification and semantic segmentation, allowing the same memory to be read out globally or densely without architectural changes. Learned fixation policies outperform non‑learned heuristics, improving task performance and producing scanpaths that resemble human gaze behavior.
arXiv:2602. 14834v2 Announce Type: replace-cross Abstract: Human eye movements in visual recognition reflect a balance between foveal sampling and peripheral context.
arXiv:2507. 15833v3 Announce Type: replace-cross Abstract: Human vision is a highly active process driven by gaze, which directs attention to task-relevant regions through foveation, dramatically reducing visual processing.
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:2609.05517v1 Announce Type: cross Abstract: Human observers prioritize visual information according to task goals. Most computational models of naturalistic viewing are gaze-trained for free vi...
arXiv:2606. 14703v1 Announce Type: cross Abstract: How a vision-language model internally solves the task of describing an image is far from obvious.
arXiv:2610.03710v1 Announce Type: cross Abstract: Inspired by human vision, we introduce a framework using active gaze to enable fine-grained bimanual manipulation with only a single stereo camera. E...
arXiv:2606. 02735v1 Announce Type: cross Abstract: Generalization remains a central bottleneck for vision-language-action (VLA) models: under distractors, appearance shifts, and semantically similar tasks, the policy must often infer local execution details from coarse instructions while also deciding which parts of the image matter for control.
arXiv:2608. 16514v1 Announce Type: cross Abstract: Human visual search is serial: the fovea must land on a candidate to confirm it, and those landings form a scanpath.
Gaze Attention is a new mechanism for multimodal large language models that selectively focuses on relevant visual regions during each generation step, rather than attending to all visual tokens. By grouping tokens into spatial regions and using learnable context tokens to retain global information, it reduces attention computation and visual key‑value entries by up to 90%. Experiments on 13 image and 6 video benchmarks show that Gaze Attention matches or outperforms dense‑attention baselines while using fewer visual resources.
arXiv:2608. 11367v1 Announce Type: cross Abstract: Estimating human gaze targets from images in-the-wild is an important and formidable task.
arXiv:2211.11062v2 Announce Type: replace Abstract: Gaze following aims to predict where a person is looking in a scene, by predicting the target location, or indicating that the target is located ou...
Estimating human gaze targets from images in-the-wild is an important and formidable task. Existing approaches primarily employ brittle, multi-stage pipelines that require explicit inputs, like head bounding boxes and human pose, in order to identify the subject of gaze analysis.