Tag
OBB-PBD extends Parallel Box Decoding from horizontal to oriented bounding boxes via double-angle parameterization, validating the design with shuffle controls and leakage probes, and improving rotated IoU on the aerial vehicle visual grounding benchmark from 0.1253 to 0.303.
ACE-Brain-0.6 通过约150万条可验证视觉定位数据微调 Qwen3.5-9B，在七个公开定位基准中的四个上超越 GPT-6 Astra，展示了扩展多样化定位监督数据可显著提升开放多模态模型的空间感知与具身操作能力。
A tweet praising Meta's Muse Wonder model for outperforming other models at pointing to objects in images, marking a notable comeback for Meta in visual grounding.
介绍 Jag，一个 0.8B 视觉定位模型，通过单次前向传播直接预测边界框而非自回归生成坐标，在保持与 LocateAnything 相当精度的同时，速度提升 3.62 倍、峰值 GPU 显存降低 73.88%，并开源了模型权重、代码与在线演示。
该论文提出 OneSearch-VL，一个以视觉接地证据图（VGEG）为核心的统一多模态深度研究智能体，用于单图、多图和视频研究任务，并构建了 SFT/RL 数据集及细粒度评测基准，在多个图文与视频基准上显著超越 Qwen3-VL-8B。
该论文系统分析了视觉语言模型在结构化输出通道（点/边界框）上的安全对齐缺口，发现模型对以定位形式提出的有害请求的拒绝率比纯文本问答低 31-59 个百分点，并提出一种微调方法显著提升了定位形式的拒绝率。
GroundAnything 提出一个 4B 参数的视觉定位基础模型，通过块状去噪协调并行解码与精确定位，在 30 个 grounding 基准上取得同类模型新 SOTA（72.42%），并借助自投机解码实现 4.51 倍加速。
This paper proposes PIVOT, a dual-level learning framework that enhances visually-grounded reasoning in large vision-language models by using self-calibrated experience replay and vision-guided advantage allocation to optimize reinforcement learning.
This paper presents a proactive egocentric assistance method using single-token classification and visually grounded supervision, ranking first in the large-model division of the ECCV 2026 Wearable AI Challenge.
AffectOmni is a GRPO-trained framework for verifiable affective reasoning in multimodal large language models, introducing People Focus and Temporal Order rewards to enhance people-centric evidence selection and temporally structured reasoning, with experiments showing improvements over 7B scale baselines.
This paper introduces a controlled evaluation framework for interactive visual grounding in large vision-language models (LVLMs), showing that current LVLMs perform below human baselines and struggle with proactive question-driven grounding.
VLX-Seek-1.5-10B is an open-source 10B vision-language model from omlab, designed for fine-grained visual grounding in embodied scenarios like drones, robots, and surveillance, using region-reference localization instead of coordinate generation.
CURV proposes a curriculum learning framework that enhances chart question answering by developing intrinsic visual grounded reasoning in multimodal LLMs, achieving significant improvements on real-world benchmarks.
This paper introduces Evidence-Backed Video Question Answering (E-VQA), a new task requiring models to output both semantic answers and precise spatio-temporal evidence like tracked object segmentation masklets. The authors create a human-verified benchmark and a scalable training dataset, showing significant improvements over baselines.
GUICrafter introduces a weakly-supervised GUI agent that leverages massive unannotated screenshots and a two-stage curriculum learning framework to reduce reliance on expensive human annotations, achieving competitive performance with advanced systems like UI-TARS using only 0.1% of its data.
NVIDIA has open-sourced the visual grounding model LocateAnything-3B, which can accurately detect and bound all target objects in dense scenes.
NVIDIA released LocateAnything, an open-source model that achieves ~10x faster object detection by predicting all coordinates simultaneously instead of sequentially, reaching 12.7 FPS on a single H100 and outperforming 32B parameter models.
Introduces iVGR, a reinforcement learning framework that internalizes visual localization into textual reasoning for multimodal language models, eliminating the need for explicit visual grounding during inference while improving fine-grained perception performance.
NVIDIA introduces LocateAnything, a unified generative grounding and detection framework that uses Parallel Box Decoding to improve decoding throughput and localization accuracy. This work will be presented at CVPR 2026.
LocateAnything proposes Parallel Box Decoding for unified visual grounding and object detection, decoding geometric elements as atomic units to improve throughput and localization accuracy, supported by a large-scale dataset of 138M samples.