Trends · 研究趋势
数据来自 Hugging Face 论文的 AI 提取关键词,按月统计研究方向的增长与热度。
Zimo Wen, Boxiu Li, Wanbo Zhang +11 authors
Unified multimodal models show mixed performance in generation-to-understanding tasks, with specific subtasks benefiting from enhanced spatial and reasoning capabilities while overall performance lags behind specialized vision-language models.
Yuanyuan Gao, Hao Li, Yifei Liu +14 authors
Holi-Spatial presents the first fully automated, large-scale, spatially-aware multimodal dataset constructed from raw video inputs, supporting multi-level spatial supervision for 3D scene understanding and spatial reasoning tasks.
Qiushi Sun, Kanzhi Cheng, Zichen Ding +12 authors
OS-Genesis is a novel GUI data synthesis pipeline that enhances the training of GUI agents by reversing the trajectory collection process to improve data quality and diversity.
Zongxia Li, Wenhao Yu, Chengsong Huang +8 authors
Vision-SR1 uses reinforcement learning to enhance visual reasoning in vision-language models by decomposing the process into visual perception and language reasoning stages, improving accuracy and reducing hallucinations.
Ujjwal Upadhyay, Mukul Ranjan, Zhiqiang Shen +1 authors
SpookyBench is a benchmark for temporal pattern recognition in videos that highlights the limitations of vision-language models in processing noise-like frames without spatial information.
Xiaomi LLM-Core Team, Zihao Yue, Zhenru Lin +71 authors
MiMo-VL-7B-SFT and MiMo-VL-7B-RL provide state-of-the-art general visual understanding and multimodal reasoning through four-stage pre-training and Mixed On-policy Reinforcement Learning, outperforming models with up to 78B parameters.
Luis Wiedmann, Orr Zohar, Amir Mahla +6 authors
FineVision, a large-scale and curated dataset, enhances vision-language models through rigorous data collection, de-duplication, and human oversight, leading to improved performance.
Senqiao Yang, Junyi Li, Xin Lai +3 authors
VisionThink dynamically adjusts image resolution and visual token processing for efficient and effective vision-language tasks, improving performance and reducing computational cost.
Qiushi Sun, Mukai Li, Zhoumianze Liu +11 authors
A hybrid safety detection framework combining formal verification and VLM-based contextual assessment improves the detection of unsafe operations in mobile agents.
Qiushi Sun, Kanzhi Cheng, Yian Wang +20 authors
Researchers introduce a benchmark and open reward models to evaluate and improve vision-language judges for computer-using agent trajectories, revealing systematic leniency biases and offering cost-effective alternatives.
Haoran Wei, Yaofeng Sun, Yukun Li
DeepSeek-OCR 2 introduces DeepEncoder V2 that dynamically reorders visual tokens based on semantic content, enabling more human-like causal reasoning in 2D image understanding through cascaded 1D causal structures.
Guo Chen, Zhiqi Li, Shihao Wang +18 authors
Eagle 2.5 improves long-context multimodal learning through Automatic Degrade Sampling and Image Area Preservation techniques, enhancing VLMs for video and image understanding, and matches state-of-the-art performance on benchmarks.
Pravesh Agrawal, Szymon Antoniak, Emma Bou Hanna +34 authors
Pixtral-12B, a 12-billion-parameter multimodal language model, excels in both natural language and image understanding, surpassing larger models and introducing an open-source benchmark for evaluation.
01. AI, Alex Young, Bei Chen +28 authors
The Yi model family, based on transformer architecture, showcases strong performance across benchmarks and modalities through optimized data and scalable infrastructure.
Yan Ma, Linge Du, Xuyang Shen +7 authors
A unified reinforcement learning system, V-Triune, combines visual reasoning and perception tasks in vision-language models through a single training pipeline, achieving significant improvements across various tasks.
Jianwei Yang, Reuben Tan, Qianhui Wu +10 authors
Magma is a multimodal foundation model with both verbal intelligence and spatial-temporal intelligence, trained on diverse datasets to perform agentic tasks like UI navigation and robotic manipulation, outperforming specialized models.
Hugo Laurençon, Léo Tronchon, Victor Sanh
A synthetic dataset of HTML code and screenshots is introduced to enhance the ability of vision-language models to convert screenshots into HTML code.
Mingjie Pan, Jiyao Zhang, Tianshu Wu +3 authors
A novel object-centric representation bridges the gap between Vision-Language Models' high-level reasoning and the low-level precision needed for robotic manipulation tasks, enabling zero-shot generalization across diverse tasks.
Alejandro Lozano, Min Woo Sun, James Burgess +13 authors
BIOMEDICA is a scalable framework that creates a large, publicly accessible dataset of image-text pairs from PubMed Central, enabling state-of-the-art performance across various biomedical tasks with efficient CLIP-style models.
Haiwen Diao, Yufeng Cui, Xiaotong Li +3 authors
EVE is an encoder-free vision-language model that achieves competitive performance on multiple benchmarks using a unified decoder and extra supervision.
北京市昌平区探索星信息技术及软件开发工作室
京ICP备2026059466号