Zobrazeno 1 - 10
of 108
pro vyhledávání: '"Murata, Naoki"'
Autor:
Uchida, Kengo, Shibuya, Takashi, Takida, Yuhta, Murata, Naoki, Takahashi, Shusuke, Mitsufuji, Yuki
In motion generation, controllability as well as generation quality and speed is becoming more and more important. There are various motion editing tasks, such as in-betweening, upper body editing, and path-following, but existing methods perform mot
Externí odkaz:
http://arxiv.org/abs/2406.01867
Autor:
Zhang, Yixiao, Ikemiya, Yukara, Choi, Woosung, Murata, Naoki, Martínez-Ramírez, Marco A., Lin, Liwei, Xia, Gus, Liao, Wei-Hsiang, Mitsufuji, Yuki, Dixon, Simon
Recent advances in text-to-music editing, which employ text queries to modify music (e.g.\ by changing its style or adjusting instrumental components), present unique challenges and opportunities for AI-assisted music creation. Previous approaches in
Externí odkaz:
http://arxiv.org/abs/2405.18386
Autor:
Seo, Junyoung, Fukuda, Kazumi, Shibuya, Takashi, Narihira, Takuya, Murata, Naoki, Hu, Shoukang, Lai, Chieh-Hsin, Kim, Seungryong, Mitsufuji, Yuki
Generating novel views from a single image remains a challenging task due to the complexity of 3D scenes and the limited diversity in the existing multi-view datasets to train a model on. Recent research combining large-scale text-to-image (T2I) mode
Externí odkaz:
http://arxiv.org/abs/2405.17251
Autor:
Kim, Dongjun, Lai, Chieh-Hsin, Liao, Wei-Hsiang, Takida, Yuhta, Murata, Naoki, Uesaka, Toshimitsu, Mitsufuji, Yuki, Ermon, Stefano
To accelerate sampling, diffusion models (DMs) are often distilled into generators that directly map noise to data in a single step. In this approach, the resolution of the generator is fundamentally limited by that of the teacher DM. To overcome thi
Externí odkaz:
http://arxiv.org/abs/2405.14822
Autor:
Uesaka, Toshimitsu, Suzuki, Taiji, Takida, Yuhta, Lai, Chieh-Hsin, Murata, Naoki, Mitsufuji, Yuki
Multimodal representation learning to integrate different modalities, such as text, vision, and audio is important for real-world applications. The symmetric InfoNCE loss proposed in CLIP is a key concept in multimodal representation learning. In thi
Externí odkaz:
http://arxiv.org/abs/2404.19228
Autor:
He, Yutong, Robey, Alexander, Murata, Naoki, Jiang, Yiding, Williams, Joshua, Pappas, George J., Hassani, Hamed, Mitsufuji, Yuki, Salakhutdinov, Ruslan, Kolter, J. Zico
Prompt engineering is effective for controlling the output of text-to-image (T2I) generative models, but it is also laborious due to the need for manually crafted prompts. This challenge has spurred the development of algorithms for automated prompt
Externí odkaz:
http://arxiv.org/abs/2403.19103
Autor:
Zhang, Yixiao, Ikemiya, Yukara, Xia, Gus, Murata, Naoki, Martínez-Ramírez, Marco A., Liao, Wei-Hsiang, Mitsufuji, Yuki, Dixon, Simon
Recent advances in text-to-music generation models have opened new avenues in musical creativity. However, music generation usually involves iterative refinements, and how to edit the generated music remains a significant challenge. This paper introd
Externí odkaz:
http://arxiv.org/abs/2402.06178
Autor:
Takida, Yuhta, Ikemiya, Yukara, Shibuya, Takashi, Shimada, Kazuki, Choi, Woosung, Lai, Chieh-Hsin, Murata, Naoki, Uesaka, Toshimitsu, Uchida, Kengo, Liao, Wei-Hsiang, Mitsufuji, Yuki
Vector quantization (VQ) is a technique to deterministically learn features with discrete codebook representations. It is commonly performed with a variational autoencoding model, VQ-VAE, which can be further extended to hierarchical structures for m
Externí odkaz:
http://arxiv.org/abs/2401.00365
Autor:
Zhao, Mengjie, Ono, Junya, Zhong, Zhi, Lai, Chieh-Hsin, Takida, Yuhta, Murata, Naoki, Liao, Wei-Hsiang, Shibuya, Takashi, Wakaki, Hiromi, Mitsufuji, Yuki
Contrastive cross-modal models such as CLIP and CLAP aid various vision-language (VL) and audio-language (AL) tasks. However, there has been limited investigation of and improvement in their language encoder, which is the central component of encodin
Externí odkaz:
http://arxiv.org/abs/2310.13267
Autor:
Kim, Dongjun, Lai, Chieh-Hsin, Liao, Wei-Hsiang, Murata, Naoki, Takida, Yuhta, Uesaka, Toshimitsu, He, Yutong, Mitsufuji, Yuki, Ermon, Stefano
Consistency Models (CM) (Song et al., 2023) accelerate score-based diffusion model sampling at the cost of sample quality but lack a natural way to trade-off quality for speed. To address this limitation, we propose Consistency Trajectory Model (CTM)
Externí odkaz:
http://arxiv.org/abs/2310.02279