Publication See, Point, Refine: Multi-Turn Approach to GUI Grounding with Visual Feedback Himangi Mittal, Gaurav Mittal, Nelson Troncoso, Yu Hu April 2026 arXiv | April 2026
Publication LumiMotion: Improving Gaussian Relighting with Scene Dynamics Joanna Kaleta, Piotr W'ojcik, Kacper Marzol, Tomasz Trzci'nski, Kacper Kania, Marek Kowalski April 2026 arXiv | April 2026
Publication FF3R: Feedforward Feature 3D Reconstruction from Unconstrained views Chaoyi Zhou, Runze Wang, Feng Luo, Mert D. Pes'e, Zhiwen Fan, Yiqi Zhong, Siyu Huang April 2026 arXiv | April 2026
Publication Kuramoto Oscillatory Phase Encoding: Neuro-inspired Synchronization for Improved Learning Efficiency Mingqing Xiao, Yansen Wang, Dongqi Han, Caihua Shan, Dongsheng Li April 2026 arXiv | April 2026
Publication Entropy-Gradient Grounding: Training-Free Evidence Retrieval in Vision-Language Models Marcel Gropl, Jaewoo Jung, Seungryong Kim, Marc Pollefeys, Sung‐Jin Hong April 2026 arXiv | April 2026
Publication AVGen-Bench: A Task-Driven Benchmark for Multi-Granular Evaluation of Text-to-Audio-Video Generation Ziwei Zhou, Zeyuan Lai, Rui Wang, Yifan Yang, Zhening Xing, Yuqing Yang, Qi Dai, Lili Qiu, Chong Luo April 2026 arXiv | April 2026
Publication Faithful GRPO: Improving Visual Spatial Reasoning in Multimodal Language Models via Constrained Policy Optimization Sai Srinivas Kancheti, Aditya Kanade, Rohit Sinha, Vineeth N Balasubramanian, Tanuja Ganu 2026 COLM | April 2026
Publication Training-free Spatially Grounded Geometric Shape Encoding (Technical Report) Yuhan He April 2026 arXiv | April 2026
Publication FlowInOne:Unifying Multimodal Generation as Image-in, Image-out Flow Matching Junchao Yi, Rui Zhao, Jiahao Tang, Weixian Lei, Linjie Li, Qi Su, Zhengyuan Yang, Lijuan Wang, Xiaofeng Zhu, Alex Jinpeng Wang April 2026 arXiv | April 2026
Publication FlowInOne:Unifying Multimodal Generation as Image-in, Image-out Flow Matching Junchao Yi, Rui Zhao, Jiahao Tang, Weixian Lei, Linjie Li, Qi Su, Zhengyuan Yang, Lijuan Wang, Xiaofeng Zhu, Alex Jinpeng Wang April 2026 arXiv | April 2026