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。
Mengting Chen, Zhengrui Chen, Yongchao Du +16 authors
A commercial-scale virtual try-on system achieves high success rates, photorealistic results, and real-time performance through integrated system design and multi-stage training.
Boyang Zheng, Nanye Ma, Shengbang Tong +1 authors
Replacing VAEs with pretrained representation encoders in Diffusion Transformers enhances generative quality and convergence speed without auxiliary losses.
Xiangyan Qu, Zhenlong Yuan, Jing Tang +9 authors
Image-CoT methods are extended to image editing with ADE-CoT, which improves efficiency and performance through adaptive resource allocation, edit-specific verification, and opportunistic stopping mechanisms.
Chameleon Team
Chameleon is a mixed-modal early-fusion token-based model that achieves state-of-the-art performance across various tasks, including image captioning, text generation, and long-form mixed-modal generation, using a unified architecture.
David Bensaïd, Noam Rotstein, Roy Velich +2 authors
SingLoRA, a reformulated low-rank adaptation method, enhances parameter-efficient fine-tuning by learning a single low-rank matrix and its transpose, ensuring stable optimization and reducing parameter count.
Samuel Cahyawijaya, Holy Lovenia, Joel Ruben Antony Moniz +89 authors
SEA-VL is an open-source project aimed at creating a large, culturally relevant dataset for Southeast Asian languages to improve AI inclusivity.
Jiuhai Chen, Zhiyang Xu, Xichen Pan +10 authors
A diffusion transformer is used in a unified multimodal model framework to improve image generation while maintaining image understanding capabilities.
Siyuan Li, Luyuan Zhang, Zedong Wang +8 authors
MergeVQ and MergeAR enhance MIM with VQ by integrating token merging and KV cache compression, improving both image generation and visual representation learning.
Dianyi Wang, Ruihang Li, Feng Han +17 authors
DeepGen 1.0 is a lightweight 5B unified multimodal model that achieves superior performance in image generation and editing through advanced alignment techniques and progressive training strategies.
Zhiheng Liu, Weiming Ren, Haozhe Liu +22 authors
TUNA, a unified multimodal model, uses a cascaded VAE and representation encoder for end-to-end multimodal understanding and generation, outperforming decoupled models and achieving state-of-the-art results across various benchmarks.
Nanye Ma, Shangyuan Tong, Haolin Jia +8 authors
Inference-time scaling of diffusion models improves sample quality beyond increasing denoising steps through better noise selection and verification.
Chenyang Si, Ziqi Huang, Yuming Jiang +1 authors
A method called FreeU improves diffusion U-Net models' generation quality by re-weighting skip connections and backbone features without additional training.
Zeyi Sun, Ziyang Chu, Pan Zhang +6 authors
X-Prompt, an auto-regressive large-vision language model, uses in-context learning to achieve competitive performance in seen and unseen image generation tasks.
Chunting Zhou, Lili Yu, Arun Babu +7 authors
Transfusion combines language modeling and diffusion training to develop a multi-modal transformer model that scales effectively across text and image data, matching the performance of specialized models.
Jintao Zhang, Chendong Xiang, Haofeng Huang +4 authors
SpargeAttn is a universal sparse and quantized attention method that accelerates diverse models by predicting the attention map and using an online softmax-aware filter to skip unnecessary matrix multiplications.
Jintao Zhang, Haofeng Huang, Pengle Zhang +3 authors
SageAttention2 improves attention computation speed with 4-bit matrix multiplication and adaptive quantization, achieving significant OPS increases without compromising accuracy.
Duy-Kien Nguyen, Mahmoud Assran, Unnat Jain +3 authors
Vanilla Transformers achieve high performance in computer vision tasks by treating individual pixels as tokens, challenging the conventional use of local neighborhoods.
Li Chen, Mengyi Zhao, Yiheng Liu +8 authors
PhotoVerse uses a dual-branch conditioning mechanism and facial identity loss to generate high-quality, identity-preserving images efficiently with minimal tuning.
Jintao Zhang, Jia wei, Pengle Zhang +2 authors
A new quantization method for attention mechanisms, named SageAttention, enhances inference speed and accuracy without significant loss in performance across various models.
Xiangxiang Chu, Jianlin Su, Bo Zhang +1 authors
A LLaMA-like vision transformer, VisionLLaMA, is introduced for processing 2D images and achieves state-of-the-art performance in various vision tasks.
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