…A Unified Framework for Cross-view Image-retrieval and Pose-estimation Published on Jun 3 Submitted by Yurim Jeon on Jun 9 Seoul National University Authors: Yurim Jeon , , Abstract CIPER is a…
…A Unified Multimodal Framework for Versatile Video Generation via Diffusion Priors Published on May 1 Submitted by taesiri on May 4 #1 Paper of the day Authors: Houyuan Chen , Hong Li , Xianghao…
…Sai Niranjan Ramachandran , Abstract Decision trees and diffusion models are mathematically unified through a shared optimization principle called Global Trajectory Score Matching, enabling efficient generative models and neural network distillation methods. AI…
…A Unified Perspective of On-Policy Distillation in Diffusion Models Published on May 14 Submitted by Quanhao Li on May 15 Authors: Quanhao Li , , , , , , , , , Abstract DiffusionOPD enables efficient multi-task training for…
…Yaorui Shi , Yuxin Chen , Zhengxi Lu , , , , , , Abstract Skill1 is a unified framework that trains a single policy to simultaneously evolve skill selection, utilization, and distillation capabilities using a shared task-outcome objective…
…A Unified Benchmark for Image Editing and Reward Modeling Published on May 13 Submitted by Yang Shi on May 14 Authors: Xuehai Bai , Yang Shi , , Xuanyu Zhu , Yuran Wang , Yifan Dai , , , , Abstract…
…Toward a Unified Driving World Model for 3D Scene Understanding and Generation Published on Apr 30 Submitted by Xin Zhou on May 7 H-EmbodVis Authors: Xin Zhou , , , , , , Abstract HERMES++ combines 3D…
…Hao Wang , , , , , , Abstract X2SAM is a unified multimodal model that extends segmentation capabilities from images to videos while supporting conversational instructions and visual prompts for both modalities. AI-generated summary Multimodal Large…
Papers arxiv:2605.13301 Achieving Gold-Medal-Level Olympiad Reasoning via Simple and Unified Scaling Published on May 13 Submitted by Yafu Li on May 15 #1 Paper of the day Authors…
…Scaling Interleaved Instructions for Unified Visual Generation Published on May 12 Submitted by taesiri on May 13 Authors: , , , , Abstract INSET is a unified multimodal model that embeds images as native vocabulary within…