Egocentric visual grounding requires high-resolution inputs to localize small objects. However, scaling Multimodal Large Language Models to this domain is constrained by the excessive cost of visual token processing.
arXiv:2605. 13178v2 Announce Type: replace-cross Abstract: In large vision-language models, visual tokens typically constitute the majority of input tokens, leading to substantial computational overhead.
Recent advancements in Multimodal Large Language Models (MLLMs) have evolved from static perception to interleaved visual-language reasoning, often referred to as ``thinking with images''. A basic operation in this reasoning process is to zoom in on regions of interest (often represented with bounding boxes) to acquire finer visual details.
arXiv:2607. 06915v1 Announce Type: cross Abstract: Scaling down the resolution of input images can greatly reduce the computational overhead of convolutional neural networks (CNNs), which is promising for edge AI.
arXiv:2606. 12412v1 Announce Type: cross Abstract: Vision-language models (VLMs) project images into hundreds to thousands of visual tokens, making decoder inference expensive in both attention computation and KV-cache memory.
Vision-language-action (VLA) models enable robot navigation from natural language and visual goals, but remain susceptible to perceptual distractions and ambiguous scene interpretations. This paper presents the first empirical evaluation of visual grounding for VLA navigation policies.
arXiv:2512. 23020v3 Announce Type: replace-cross Abstract: 3D visual grounding aims to locate objects based on natural language descriptions in 3D scenes.
arXiv:2607. 03595v1 Announce Type: cross Abstract: Affordance grounding aims to localize image regions that support a specific action, serving as a core capability for physical intelligence and embodied perception.
Image-goal visual navigation is a fundamental capability for embodied agents. Existing navigation policies efficiently predict waypoint trajectories but lack visual foresight, while navigation world models can anticipate future observations but often require costly planning rollouts.
arXiv:2607. 05798v1 Announce Type: cross Abstract: Recent advancements in Multimodal Large Language Models (MLLMs) have evolved from static perception to interleaved visual-language reasoning, often referred to as ``thinking with images''.
arXiv:2602. 15875v2 Announce Type: replace-cross Abstract: Current Visual-Language Navigation (VLN) methodologies face a trade-off between semantic understanding and control precision.
arXiv:2510. 00054v3 Announce Type: replace-cross Abstract: Multimodal Large Language Models (MLLMs) have made significant strides in visual understanding tasks.
arXiv:2608. 03244v1 Announce Type: new Abstract: Image-goal visual navigation is a fundamental capability for embodied agents.