Multi-view representations enable pretrained image and video vision-language models to understand 3D scenes, but their long visual token sequences make inference costly. Redundancy arises both from repeated observations of the same scene regions across views and from processing all visual tokens at every LLM layer, regardless of their relevance to the current computation. We propose GeoGR, a two-stage framework that jointly compresses scene representations and visual computation. At the projector level, GeoSemZip consolidates cross-view observations into 3D voxel tokens and combines semantic saliency with spatial coverage to construct a compact scene representation. Unselected voxel features are aggregated into contextual anchors to retain scene information that would otherwise be discarded. At the LLM level, we identify an effective visual computation window and observe that query-conditioned token relevance remains locally stable but changes over longer layer intervals. Guided by these findings, GroupRoute combines late entry and early exit with recoverable group-wise skipping. Low-relevance tokens bypass complete LLM layers while retaining their hidden states and can rejoin the active group at subsequent anchor layers selected under a computation budget. For compression-aware post-training, we construct a compact dataset of 67K samples by retaining 30% of the original training pool. With this protocol, GeoGR retains 95.2% and 96.8% of the dense post-trained models' performance on LLaVA-OneVision-7B and Video-3D LLM-7B, respectively, while accelerating LLM prefill by $6.8\times$ and $6.1\times$. These results demonstrate the consistent effectiveness of GeoGR across 3D VLMs with and without explicit 3D spatial encoding, highlighting a favorable performance-efficiency trade-off. The code is available at https://github.com/EIT-NLP/GeoGR.
BioVLM: Routing Prompts, Not Parameters, for Cross-Modality Generalization in Biomedical VLMs
University of Trento(特伦托大学);Carnegie Mellon University(卡内基梅隆大学);LNMIIT Jaipur(贾伊普尔 LNMIIT);MBZUAI;Sunandan Divatia School of Science(Sunandan Divatia 科学学院);IIT Bombay(博伊斯大学)
VL-RouterBench: A Benchmark for Vision-Language Model Routing
Institute of Image Processing and Pattern Recognition, Shanghai Jiao Tong University(1 图像处理与模式识别研究所,上海交通大学);The Hong Kong University of Science and Technology (Guangzhou)(2 香港科学与技术大学(广州));The Hong Kong University of Science and Technology(3 香港科学与技术大学)
LLM-empowered Dynamic Prompt Routing for Vision-Language Models Tuning under Long-Tailed Distributions
Shandong University(山东大学);The Hong Kong University of Science and Technology(香港科技大学);AiLF Instruments(AiLF仪器);Shandong Key Laboratory of Intelligent Electronic Packaging Testing and Application(山东省智能电子封装测试与应用重点实验室)
INTCORT: Training-Free Spatial Reasoning Enhancement for Vision-Language Models via Input Transformations and Confidence Routing
The University of Hong Kong(香港大学);University of Southern California(南加州大学);China Telecom(中国电信);Columbia University(哥伦比亚大学);City University of Hong Kong(香港城市大学);Chinese Academy of Sciences(中国科学院)
GeoMag: A Vision-Language Model for Pixel-level Fine-Grained Remote Sensing Image Parsing
Institute of Space Earth Science, School of Frontier Sciences, Nanjing University(南京大学空间地球科学学院);Computer Network Information Center, Chinese Academy of Sciences(中国科学院计算机网络信息中心)
Hanfu-Bench: A Multimodal Benchmark on Cross-Temporal Cultural Understanding and Transcreation
The Chinese University of Hong Kong, Shenzhen(香港中文大学(深圳));Shenzhen Research Institute of Big Data(深圳大数据研究院);Chengdu Technological University(成都理工大学);University of Copenhagen(哥本哈根大学)
GTR-Bench: Evaluating Geo-Temporal Reasoning in Vision-Language Models
Tsinghua University(清华大学);SenseTime Research(商汤科技研究院);Peking University(北京大学);Technical University of Munich, Heilbronn Data Science Center, Munich Data Science Institute(慕尼黑技术大学,海德堡数据科学中心,慕尼黑数据科学研究所)
PETR: Prompt Ensembling with Training-free Routing for Vision-Language Models
State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所多模态人工智能系统国家重点实验室);School of Artificial Intelligence, University of Chinese Academy of Sciences(中国科学院大学人工智能学院);Purple Mountain Laboratories(紫金山实验室);Beijing University of Posts and Telecommunications(北京邮电大学)
Scope: Selective Cross-modal Orchestration of Visual Perception Experts
ServiceNow;Université de Montréal(蒙特利尔大学);École de Technologie Supérieure(高级技术学院);University of Waterloo(滑铁卢大学);McGill University(麦吉尔大学);York University(约克大学);CIFAR AI Chair(CIFAR人工智能主席);Mila;Law Zero
MAPWise: Evaluating Vision-Language Models for Advanced Map Queries
IIIT Hyderabad(印度信息技术学院海得拉巴分校);University of Utah(犹他大学);University of Delaware(特拉华大学);Arizona State University(亚利桑那州立大学);University of Pennsylvania(宾夕法尼亚大学)
TimeSpot: Benchmarking Geo-Temporal Understanding in Vision-Language Models in Real-World Settings
Computational Intelligence and Operations Laboratory (CIOL), Bangladesh(计算智能与运筹实验室(CIOL),孟加拉国);Shahjalal University of Science and Technology (SUST), Sylhet, Bangladesh(沙赫jalal科学与技术大学(SUST),沙赫里尔,孟加拉国);North South University (NSU), Dhaka, Bangladesh(北南大学(NSU),达卡,孟加拉国);Qatar Computing Research Institute (QCRI), Doha, Qatar(卡塔尔计算研究中心(QCRI),多哈,卡塔尔)
GeoGround: A Unified Large Vision-Language Model for Remote Sensing Visual Grounding
Nanyang Technological University(南洋理工大学);University of Reading(阅读大学);Shanghai Jiao Tong University(上海交通大学);Harbin Institute of Technology(哈尔滨工业大学);SenseTime Research(商汤科技研究院)
WikiSeeker: Rethinking the Role of Vision-Language Models in Knowledge-Based Visual Question Answering
School of Artificial Intelligence, University of Chinese Academy of Sciences(中国科学院大学人工智能学院);State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS), Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所多模态人工智能系统国家重点实验室 (MAIS))
Evaluating Precise Geolocation Inference Capabilities of Vision Language Models
Apart Research(阿帕特研究院);University of Maryland(马里兰大学);Hanoi University of Science and Technology(河内科技大学);University of Science and Technology of Hanoi(河内科学技术大学)
本文构建 Google Street View 全球分布基准,评估基础 VLM 及可调用工具的智能体在单图像地理定位上的能力,揭示其低误差表现及在线隐私风险。