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.
arXiv:2609.36875v1 Announce Type: new Abstract: Accurate instance segmentation in dynamic scenes is important for downstream applications such as robotics and autonomous driving. Existing Segment Any...
arXiv:2607. 14497v2 Announce Type: replace Abstract: Egocentric Visual Question Answering (VQA) has attracted widespread attention as an important task for enabling Multimodal Large Language Models (MLLMs) to interact with the real world.
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.
The paper introduces O$^2$-VG, a unified framework for oriented object visual grounding in remote sensing images, comprising three complementary models: O$^2$-VG-Trans, a cross‑modality transformer; O$^2$-VG-Uni, which predicts universal oriented proposals; and O$^2$-VG-VLM, an autoregressive vision‑language model that generates oriented bounding boxes. It also presents DIOR‑R‑SVG, a new dataset containing image, expression, and oriented box triplets for training and evaluation. The framework demonstrates superior performance across multiple benchmarks and is supported by publicly available code.
TempoGround is a vision‑language model–native framework for streaming visual grounding that detects cross‑frame object correspondence and explicitly models object presence states. It uses a curriculum prediction mechanism to resolve 2D instance association, predict object entry, continuation, or exit, decode 2D boxes, and lift them to 3D camera‑frame boxes. The approach is further refined with Streaming Grounding Reinforcement, which optimizes grounding, identity, and consistency rewards, and achieves significant improvements on multiple streaming visual grounding benchmarks.
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.
RankGround is a two‑stage framework for GUI grounding that uses a single Vision‑Language Model call per query. It introduces GroundRanker, a lightweight multimodal reranker that selects the most promising crop from a dense candidate set, trained with a two‑stage curriculum on ranking supervision data derived from existing grounding datasets. Experiments show RankGround outperforms strong baselines, achieving 1.4× faster inference and a 5.5% average improvement in localization accuracy over the second‑best method across all backbones and screen scales.
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.
IVSGround introduces a lightweight view selector that learns to choose the most informative camera views for vision‑language model (VLM) based 3D visual grounding, replacing heuristic view selection. The selector is trained via a two‑stage rejection sampling process that uses feedback from a reasoning VLM to generate supervision signals. Experiments on ScanRefer and NR3D demonstrate that IVSGround consistently improves grounding accuracy over existing zero‑shot pipelines, underscoring the importance of selecting where to look for effective 3D visual grounding.
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.