2012: comp. Physics grad school. Get really into gpu compute
2014: convolving halo densities with had-chosen filters / wavelets. What if we “fit” the filters? Find info on CNNs. A long hobby rabbit hole
2016-17: 3d convnet HOD idea falls apart when SPH cosmo sims discredited
Long time ago - before ChatGPT released:
One day AI will take over but who knows if it happens in my lifetime.
ChatGPT released:
Holy shit, it's happening!
Ever since:
There are no walls, superintelligence is just a matter of continued iteration.
2012: comp. Physics grad school. Get really into gpu compute
2014: convolving halo densities with had-chosen filters / wavelets. What if we “fit” the filters? Find info on CNNs. A long hobby rabbit hole
2016-17: 3d convnet HOD idea falls apart when SPH cosmo sims discredited
Zwar von 2028, aber immer noch relevant.
arxiv.org/abs/1911.06073
Zwar von 2028, aber immer noch relevant.
arxiv.org/abs/1911.06073
本報告書では、高度な多言語対応、制御可能、堅牢性、ストリーミング対応を備えたテキスト音声変換モデル群であるQwen3-TTSシリーズを提示する。Qwen3-TTSは最先端の3秒音声クローン技術と記述ベース制御をサポートし、全く新しい音声の生成と出力音声の微細な操作を可能にします。10言語にまたがる500万時間...
本報告書では、高度な多言語対応、制御可能、堅牢性、ストリーミング対応を備えたテキスト音声変換モデル群であるQwen3-TTSシリーズを提示する。Qwen3-TTSは最先端の3秒音声クローン技術と記述ベース制御をサポートし、全く新しい音声の生成と出力音声の微細な操作を可能にします。10言語にまたがる500万時間...
2311.15599, cs․CV | cs․AI | cs․LG, 27 Nov 2023
🆕UniRepLKNet: A Universal Perception Large-Kernel ConvNet for Audio, Video, Point Cloud, Time-Series and Image Recognition
Xiaohan Ding, Yiyuan Zhang, Yixiao Ge, Sijie Zhao, Lin Song, Xiangyu Yue, Ying Shan
2311.15599, cs․CV | cs․AI | cs․LG, 27 Nov 2023
🆕UniRepLKNet: A Universal Perception Large-Kernel ConvNet for Audio, Video, Point Cloud, Time-Series and Image Recognition
Xiaohan Ding, Yiyuan Zhang, Yixiao Ge, Sijie Zhao, Lin Song, Xiangyu Yue, Ying Shan
1. The audio is cut into 80ms, which are sampled to 16 KHz (16000*0.08=1280 floats).
2. It is converted to a spectrogram,
3. A whisper-style encoder converts it to an audio token embedding through a convnet,
1. The audio is cut into 80ms, which are sampled to 16 KHz (16000*0.08=1280 floats).
2. It is converted to a spectrogram,
3. A whisper-style encoder converts it to an audio token embedding through a convnet,
The tape on the floor is so I know where to step. The stools are so I don't accidentally step on cameras
The tape on the floor is so I know where to step. The stools are so I don't accidentally step on cameras
Междувременно, cuda надебеля. Сега тези имат оптимизирана имплементация на PTX ISA, което е едно ниво под cuda. За мен това е нещото.
Междувременно, cuda надебеля. Сега тези имат оптимизирана имплементация на PTX ISA, което е едно ниво под cuda. За мен това е нещото.
Zhimin Shao, Abhay Yadav, Rama Chellappa, Cheng Peng
tl;dr: 3D VFM+2D ConvNet->feature extraction backbone; 3D descriptor head (for geometry)+2D warp head (for pattern) fusion
arxiv.org/abs/2511.17750
Zhimin Shao, Abhay Yadav, Rama Chellappa, Cheng Peng
tl;dr: 3D VFM+2D ConvNet->feature extraction backbone; 3D descriptor head (for geometry)+2D warp head (for pattern) fusion
arxiv.org/abs/2511.17750
Azwar Abdulsalam, Joseph G. Makin
Action editor: Ying Nian Wu
https://openreview.net/forum?id=i5K4SZeqtq
#langevin #convnet #sampling
Azwar Abdulsalam, Joseph G. Makin
Action editor: Ying Nian Wu
https://openreview.net/forum?id=i5K4SZeqtq
#langevin #convnet #sampling