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。
Qwen, An Yang, Baosong Yang +39 authors
Qwen2.5, an enhanced series of large language models, demonstrates superior performance across various benchmarks and use cases through extensive pre-training and advanced post-training techniques.
Weiyun Wang, Zhangwei Gao, Lixin Gu +58 authors
InternVL 3.5 introduces Cascade RL, ViR, and DvD to enhance reasoning, efficiency, and performance in multimodal models.
Andrés Marafioti, Orr Zohar, Miquel Farré +14 authors
SmolVLM, a series of compact multimodal models, achieves high performance with minimal GPU memory usage, making efficient deployment on mobile and edge devices possible.
Zuhao Yang, Sudong Wang, Kaichen Zhang +7 authors
LongVT, an end-to-end framework, enhances long video reasoning by interleaving global and local analysis using multimodal tools, outperforming existing methods on challenging benchmarks.
An Yang, Baosong Yang, Binyuan Hui +55 authors
The Qwen2 series, comprising 0.5 to 72 billion parameter models, surpasses prior open models across language understanding, generation, multilingualism, coding, math, and reasoning, with exceptional performance in benchmarks like MMLU, GPQA, HumanEval, GSM8K, BBH, MT-Bench, Arena-Hard, and LiveCodeBench.
Matt Deitke, Christopher Clark, Sangho Lee +48 authors
Molmo, a new family of open-weight VLMs, excels through a high-quality human-annotated image caption dataset and a diverse fine-tuning dataset, outperforming both proprietary and open models in benchmark and human evaluations.
Shengbang Tong, David Fan, John Nguyen +18 authors
Controlled multimodal pretraining experiments reveal key insights about unified visual representations, data complementarity, world modeling emergence, and efficient scaling through mixture-of-experts architectures.
Kaining Ying, Hengrui Hu, Siyu Ren +6 authors
WBench presents a comprehensive multi-turn benchmark for evaluating interactive world models across five dimensions using 289 test cases and 1,058 interaction turns with diverse scenarios and interaction types.
Xinlong Wang, Xiaosong Zhang, Zhengxiong Luo +22 authors
Emu3, a transformer-based multimodal model trained exclusively with next-token prediction, outperforms existing diffusion and compositional models in generation and perception tasks.
Runqi Qiao, Qiuna Tan, Minghan Yang +10 authors
V-Thinker, a multimodal reasoning assistant using reinforcement learning, enhances image-interactive thinking by synthesizing datasets and aligning perception for improved performance in vision-centric tasks.
Juanxi Tian, Siyuan Li, Conghui He +2 authors
A benchmark for chained text-to-multi-image generation assesses models' ability to model dynamic causal processes and world knowledge, revealing that unified multimodal models outperform specialized ones but still struggle with spatiotemporal consistency.
Junliang Ye, Kenkun Liu, Guocun Wang +12 authors
Hunyuan3D-Buffalo 1.0 unifies 3D understanding, generation, editing, and part generation via a multimodal architecture trained on a large-scale 3D corpus, achieving leading benchmark results.
Xiangyu Zhao, Peiyuan Zhang, Kexian Tang +7 authors
RISEBench evaluates Reasoning-Informed Visual Editing by assessing temporal, causal, spatial, and logical reasoning in multimodal models like GPT-4o-Native.
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.
Bo Li, Yuanhan Zhang, Dong Guo +7 authors
LLaVA-OneVision is a unified multimodal model that advances performance across single-image, multi-image, and video scenarios with strong transfer learning capabilities.
Gemma Team, Aishwarya Kamath, Johan Ferret +213 authors
Gemma 3 introduces vision capabilities, broader language coverage, and extended context length, featuring an optimized architecture and post-training enhancements to outperform previous versions.
Chufan Shi, Cheng Yang, Yaxin Liu +11 authors
ChartMimic is a new benchmark assessing large multimodal models' visually-grounded code generation for chart rendering, evaluating multi-level cognitive capabilities with diverse chart types and metrics.
Junyan Ye, Baichuan Zhou, Zilong Huang +12 authors
LOKI is a benchmark for evaluating the synthetic data detection capabilities of large multimodal models across various modalities.
Zhengfeng Lai, Vasileios Saveris, Chen Chen +9 authors
A study examines the use of synthetic and AltText captions in multimodal models, finding that a hybrid approach using both types improves alignment and performance across various models.
Gemini Team, Rohan Anil, Sebastian Borgeaud +939 authors
Gemini, a family of multimodal models, achieves state-of-the-art performance across various benchmarks, including human-expert performance on MMLU, through advanced cross-modal reasoning and language understanding.
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