MedVLM-R1 employs reinforcement learning with GRPO to generate explicit reasoning, boosting accuracy to 78.22% on medical VQA tasks.

Jiazhen Pan, Che Liu, Junde Wu et al.

ViDoRAG combines GMM-based multi-modal retrieval with multi-agent iterative reasoning, achieving over 10% improvement on ViDoSeek.

Qiuchen Wang, Ruixue Ding, Zehui Chen et al.

This survey frames video generation as sequential sampling from a high-dimensional spatiotemporal distribution and compares VAE, AR, diffusion, and flow models.

Zhiyu Yin, Kehai Chen, Xuefeng Bai et al.

PosterSum employs a hierarchical segmentation and summarization approach, improving ROUGE-L by 3.14% for scientific poster abstracts.

Rohit Saxena, Pasquale Minervini, Frank Keller

VideoGrain modulates space-time attention for fine-grained video editing, achieving state-of-the-art results in zero-shot multi-grained control.

Xiangpeng Yang, Linchao Zhu, Hehe Fan et al.

ReAuSE integrates a built-in autoregressive search engine into a multi-modal LLM, achieving 9.6% improvement on knowledge-based VQA.

Xinwei Long, Zhiyuan Ma, Ermo Hua et al.

CCGS integrates pointmap association and piecewise-plane constraint to achieve consistent and compact 3D Gaussian segmentation fields, excelling on ScanNet and Replica datasets.

Wenhao Hu, Wenhao Chai, Shengyu Hao et al.

Proposed an SNN-driven multimodal human action recognition framework, significantly improving energy efficiency and accuracy.

Naichuan Zheng, Hailun Xia, Zeyu Liang et al.

YOLOv12 integrates attention mechanisms with efficient architecture, achieving 40.6% mAP at 1.64ms on T4 GPU, outperforming YOLOv10/11.

Yunjie Tian, Qixiang Ye, David Doermann

Introduced UTR framework to address temporal hacking in video MLLMs, enhancing video comprehension.

En Yu, Kangheng Lin, Liang Zhao et al.

Introduced Conv-LiGRU to reduce test-time overthinking, improving accuracy on CIFAR10-C.

Hieu Tran Bao, Nguyen Cong Dat, Nguyen Duc Anh et al.

NPSim transforms daytime images to nighttime using monocular inverse rendering and ray tracing, enhancing nighttime semantic segmentation.

Shutong Zhang

VidCRAFT3 models interactions among geometry, motion, and lighting for precise image-to-video control.

Sixiao Zheng, Zimian Peng, Yanpeng Zhou et al.

MMGDreamer introduces a dual-branch diffusion framework with a novel Mixed-Modality Graph, achieving high-precision geometry control in 3D indoor scene synthesis, outperforming state-of-the-art.

Zhifei Yang, Keyang Lu, Chao Zhang et al.

Long-VITA is a multimodal model supporting 1 million tokens, achieving high short-sequence accuracy in image, video, and text understanding.

Yunhang Shen, Chaoyou Fu, Shaoqi Dong et al.

Goku employs rectified flow Transformer for joint image-video generation, achieving top-tier performance with 0.76 on GenEval and 84.85 on VBench.

Shoufa Chen, Chongjian Ge, Yuqi Zhang et al.

Introduces Sliding Tile Attention (STA), achieving 2.8-17× speedup in video diffusion models with minimal quality loss, based on local 3D attention patterns.

Peiyuan Zhang, Yongqi Chen, Runlong Su et al.

Mosaic3D introduces a novel pipeline and model, generating 5.6M high-quality 3D mask-text pairs, achieving SOTA open-vocabulary 3D segmentation.

Junha Lee, Chunghyun Park, Jaesung Choe et al.

MotionLab introduces a unified human motion generation and editing framework based on the Motion-Condition-Motion paradigm, leveraging rectified flows for multi-task learning, achieving state-of-the-art results.

Ziyan Guo, Zeyu Hu, De Wen Soh et al.

BVINet achieves blind video inpainting with zero annotations, significantly improving restoration performance.

Zhiliang Wu, Kerui Chen, Kun Li et al.