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。
Weijie Wang, Haomin Zhang, Ye Li +7 authors
ATAS improves long-form video consistency by compiling screenplays into referenced shot requests, retrieving spatial and temporal evidence from scene and event memories, and conditionally updating memory after generation.
Jingxuan Wei, Siyuan Li, Yuhang Xu +21 authors
World Models require three consistency principles—modal, spatial, and temporal—for general artificial intelligence, with a proposed benchmark evaluating multimodal learning systems.
Zhengyang Sun, Yu Chen, Xin Zhou +4 authors
NUMINA enhances text-to-video diffusion models' numerical accuracy through a training-free identify-then-guide framework that uses attention heads to detect layout inconsistencies and refine object counts.
Zheng-Hui Huang, Zhixiang Wang, Jiaming Tan +6 authors
A large-scale dynamic dataset derived from AAA games is introduced to improve generative inverse and forward rendering, featuring high-resolution synchronized RGB and G-buffer data alongside a novel VLM-based evaluation method that correlates well with human judgment.
Justin Cui, Jie Wu, Ming Li +6 authors
A method is proposed to enhance long-horizon video generation by using sampled segments from self-generated long videos to guide student models, maintaining quality and consistency without additional supervision or retraining.
Guixu Lin, Zheng-Hui Huang, Siqi Yang +3 authors
AlayaRenderer-Flash accelerates a generative world renderer to real-time speeds via few-step autoregressive streaming and distilled codecs while preserving structured scene dynamics.
Lizhen Wang, Yongming Zhu, Zhipeng Ge +15 authors
FlowAct-R1 enables real-time interactive humanoid video generation with high-fidelity synthesis and low-latency responsiveness through MMDiT architecture and chunkwise diffusion forcing strategies.
Xiaopeng Lin, Shijie Lian, Bin Yu +8 authors
Proposed Egocentric2Embodiment pipeline translates human egocentric videos into structured training data for robots, enhancing their egocentric understanding and task performance.
Jianxiong Gao, Zhaoxi Chen, Xian Liu +7 authors
LongVie 2, an end-to-end autoregressive framework, enhances controllability, visual quality, and temporal consistency in video world models through three progressive training stages.
Yihao Meng, Hao Ouyang, Hanlin Wang +6 authors
AniDoc uses video diffusion models to automate colorization and in-betweening in 2D animation, improving efficiency by leveraging correspondence matching.
Rui Xie, Yinhong Liu, Penghao Zhou +7 authors
A novel approach using text-to-video models with local information enhancement and dynamic frequency loss improves spatio-temporal quality in real-world video super-resolution.
Ziming Liu, Yifan Yang, Chengruidong Zhang +4 authors
RAS, a novel sampling strategy for diffusion transformers, dynamically adjusts sampling ratios based on regions of focus, achieving speedups in diffusion models with minimal quality loss.
Pengyang Ling, Jiazi Bu, Pan Zhang +6 authors
MotionClone, a training-free framework, uses motion cloning to control text-to-video generation, yielding superior motion fidelity, textual alignment, and temporal consistency.
Enric Corona, Andrei Zanfir, Eduard Gabriel Bazavan +3 authors
VLOGGER generates audio-driven human videos from a single image using a diffusion-based method that includes 3D motion and text-to-image models, outperforming existing methods in quality, identity, and consistency.
Han Lin, Abhay Zala, Jaemin Cho +1 authors
VideoDirectorGPT combines LLMs for video content planning with a layout-controlled video generator, enabling temporally consistent multi-scene video generation from text prompts.
Tianxing Wu, Chenyang Si, Yuming Jiang +2 authors
FreeInit addresses the temporal consistency and unnatural dynamics issues in diffusion-based video generation by refining spatial-temporal low-frequency components during inference, improving subject appearance and consistency.
Bichen Wu, Ching-Yao Chuang, Xiaoyan Wang +6 authors
Fairy, an adaptation of image-editing diffusion models for video editing, uses anchor-based cross-frame attention to enhance temporal coherence and efficiency, outperforming existing methods.
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