6 papers
VideoSEAL: Mitigating Evidence Misalignment in Agentic Long Video Understanding by Decoupling Answer Authority
Chenhao Qiu, Yechao Zhang, Xin Luo +2
Long video question answering requires locating sparse, time-scattered visual evidence within highly redundant content. Although current MLLMs perform well on short videos, long vi…
OmniGen2: Towards Instruction-Aligned Multimodal Generation
Chenyuan Wu, Pengfei Zheng, Ruiran Yan +19
In this work, we introduce OmniGen2, a versatile and open-source generative model designed to provide a unified solution for diverse generation tasks, including text-to-image, imag…
Multimodal Peer Review Simulation with Actionable To-Do Recommendations for Community-Aware Manuscript Revisions
Mengze Hong, Di Jiang, Weiwei Zhao +5
While large language models (LLMs) offer promising capabilities for automating academic workflows, existing systems for academic peer review remain constrained by text-only inputs,…
EditScore: Unlocking Online RL for Image Editing via High-Fidelity Reward Modeling
Xin Luo, Jiahao Wang, Chenyuan Wu +6
Instruction-guided image editing has achieved remarkable progress, yet current models still face challenges with complex instructions and often require multiple samples to produce…
Osprey: Pixel Understanding with Visual Instruction Tuning
Yuqian Yuan, Wentong Li, Jian Liu +5
Multimodal large language models (MLLMs) have recently achieved impressive general-purpose vision-language capabilities through visual instruction tuning. However, current MLLMs pr…
Humanoid-VLA: Towards Universal Humanoid Control with Visual Integration
Pengxiang Ding, Jianfei Ma, Xinyang Tong +13
This paper addresses the limitations of current humanoid robot control frameworks, which primarily rely on reactive mechanisms and lack autonomous interaction capabilities due to d…