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。
Xuyang Liu, Shihao Wang, Xinyu Wei +5 authors
OmniCompass is a holistic benchmark for omni-modal video grounding and understanding that evaluates vision-language and audio-visual reasoning through temporal grounding, spatial grounding, and question answering tasks.
Yuhan Zhu, Xiangyu Zeng, Qingyi Si +15 authors
VideoJev converts video observations into structured decisions by scoring temporal intervals and text options, enabling efficient reusable inference for visual agents.
Dongsheng Ma, Jiayu Li, Zhengren Wang +8 authors
CiteVQA introduces a benchmark for document vision-language models that evaluates both answer accuracy and correct citation of supporting evidence, revealing significant attribution hallucinations in current models.
Xi Xiao, Tianchen Zhao, Youngeun Kim +10 authors
ReaLVR improves latent visual reasoning by supervising latent tokens with visual evidence and answer contrast, scaling robustly to 235B parameters.
Chengwen Liu, Xiaomin Yu, Zhuoyue Chang +13 authors
VideoDR benchmark enables video question answering by combining cross-frame visual extraction, web retrieval, and multi-hop reasoning in open-domain settings.
Caixin Kang, Tianyu Yan, Sitong Gong +8 authors
Researchers introduce a new task and dataset for evaluating personality reasoning in multimodal language models, revealing significant gaps between accurate predictions and grounded reasoning processes.
Wenxuan Huang, Yu Zeng, Qiuchen Wang +12 authors
Vision-DeepResearch introduces a multimodal deep-research paradigm enabling multi-turn, multi-entity, and multi-scale visual and textual search with deep-research capabilities integrated through cold-start supervision and reinforcement learning.
Weimin Xiong, Shuhao Gu, Bowen Ye +5 authors
A large-scale GUI dataset was created by automatically extracting interaction trajectories from internet videos, enabling improved performance in GUI agents through pre-training on this diverse collection.
Runqi Qiao, Qiuna Tan, Peiqing Yang +11 authors
We-Math 2.0 enhances MLLMs' mathematical reasoning through a structured knowledge system, model-centric data space modeling, and reinforcement learning, demonstrating competitive performance on benchmarks.
Qiutong Chen, Yuchan Guo, Zhenlong Yuan +10 authors
VepAgent improves video event prediction by combining causal reasoning with tool-augmented reinforcement learning and a diagnostic tool library to recover missing visual evidence.
Xiaomin Yu, Yi Xin, Wenjie Zhang +12 authors
Researchers address the modality gap in multimodal learning by proposing a fixed-frame theory and a training-free alignment method that enables efficient scaling of multimodal models using unpaired data.
Khalil Hennara, Muhammad Hreden, Mohamed Motasim Hamed +4 authors
Baseer, a vision-language model fine-tuned for Arabic document OCR, achieves state-of-the-art performance using a decoder-only strategy and a large-scale dataset, outperforming existing solutions with a WER of 0.25.
Haolong Yan, Jia Wang, Xin Huang +94 authors
A self-evolving training pipeline with the Calibrated Step Reward System and GUI-MCP protocol improve GUI automation efficiency, accuracy, and privacy in real-world scenarios.
Kwai Keye Team, Biao Yang, Bin Wen +57 authors
Kwai Keye-VL, an 8-billion-parameter multimodal model, excels in short-video understanding and general vision-language tasks through a comprehensive pre-training and post-training process, including a five-mode data mixture and reinforcement learning.
Brandon McKinzie, Zhe Gan, Jean-Philippe Fauconnier +28 authors
A study of Multimodal Large Language Models finds a mix of pre-training data and image encoder design crucial for SOTA performance on multimodal benchmarks.
Yu Zeng, Wenxuan Huang, Zhen Fang +13 authors
Vision-DeepResearch benchmark addresses limitations in evaluating visual-textual search capabilities of multimodal models by introducing realistic evaluation conditions and improving visual retrieval through multi-round cropped-search workflow.
LASA Team, Weiwen Xu, Hou Pong Chan +16 authors
A medical-specialized multimodal large language model, Lingshu, is introduced with enhanced data curation and reinforcement learning to address limitations in medical applications.
Jie Jiang, Qi Yang, Bolin Ni +3 authors
R-4B, an auto-thinking multimodal large language model, uses bi-mode annealing and Bi-mode Policy Optimization to adaptively decide on problem-solving strategies, achieving state-of-the-art performance with lower computational cost.
Xiangyu Zhao, Junming Lin, Tianhao Liang +11 authors
Existing Multimodal Large Language Models show performance deficits in long-chain reflective reasoning, which is addressed by developing MM-HELIX-100K and Adaptive Hybrid Policy Optimization, leading to improved accuracy and generalization.
Yilei Jiang, Yaozhi Zheng, Yuxuan Wan +4 authors
A modular multi-agent framework named ScreenCoder decomposes UI design-to-code translation into grounding, planning, and generation stages, achieving superior layout accuracy and code correctness through specialized agents and fine-tuned multimodal models.
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