SceneTAP: Scene-Coherent Typographic Adversarial Planner against Vision-Language Models in Real-World Environmentsby Yue Cao, Yun Xing,…
RoboSpatial: Teaching Spatial Understanding to 2D and 3D Vision-Language Models for Roboticsby Chan Hee Song,…
UniGaussian: Driving Scene Reconstruction from Multiple Camera Models via Unified Gaussian Representationsby Yuan Ren, Guile…
Dynamics-Aware Gaussian Splatting Streaming Towards Fast On-the-Fly Training for 4D Reconstructionby Zhening Liu, Yingdong Hu,…
LoLI-Street: Benchmarking Low-Light Image Enhancement and Beyondby Md Tanvir Islam, Inzamamul Alam, Simon S. Woo,…
Procedure-Aware Surgical Video-language Pretraining with Hierarchical Knowledge Augmentationby Kun Yuan, Vinkle Srivastav, Nassir Navab, Nicolas…
DAE-Fuse: An Adaptive Discriminative Autoencoder for Multi-Modality Image Fusionby Yuchen Guo, Ruoxiang Xu, Rongcheng Li,…
UrBench: A Comprehensive Benchmark for Evaluating Large Multimodal Models in Multi-View Urban Scenariosby Baichuan Zhou,…
DriveGenVLM: Real-world Video Generation for Vision Language Model based Autonomous Drivingby Yongjie Fu, Anmol Jain,…
MTMamba++: Enhancing Multi-Task Dense Scene Understanding via Mamba-Based Decodersby Baijiong Lin, Weisen Jiang, Pengguang Chen,…