![[Long Review] Cascaded Diffusion Models for High Fidelity Image Generation](/media/video/2022/06/long-review-cascaded-diffusion-models-for-high-fidelity-image-generation/preview.jpg)
Tutorials
[長篇評論] Cascaded Diffusion Models for High Fidelity Image Generation
在Imagen和DALL-E 2將擴散設定為生成式影像的預設之前，這篇Google Brain論文奠定了Cascaded Diffusion的方案，許多後來的文字轉圖像系統都悄悄地採用：從一個小
![[Short Review] Cascaded Diffusion Models for High Fidelity Image Generation](/media/video/2022/06/short-review-cascaded-diffusion-models-for-high-fidelity-image-generation/preview.jpg)
Tutorials
[短篇評論] Cascaded Diffusion Models for High Fidelity Image Generation
Cascaded Diffusion是許多現代生成工作背後的二階以上方案：用一個擴散模型生成小影像，然後交給超解析度擴散模型來添加高頻細
![[Long Review] Axial Attention in Multidimensional Transformers](/media/video/2022/05/long-review-axial-attention-in-multidimensional-transformers/preview.jpg)
Tutorials
[長篇評論] Axial Attention in Multidimensional Transformers
對影像或影片進行完整自注意力在計算上極其昂貴，那麼如何在不引入二次方複雜度的情況下保持Transformer的表現力？
![[Short Review] Axial Attention in Multidimensional Transformers](/media/video/2022/05/short-review-axial-attention-in-multidimensional-transformers/preview.jpg)
Tutorials
[短篇評論] Axial Attention in Multidimensional Transformers
Axial Attention是一個優雅的想法，它使Transformers對高維數據保持可控：無需一次性對所有像素或所有時頻箱進行注意，而是每次只沿著一個軸進行注意。
![[Long Review] Transfer Learning from Speaker Verification to Multispeaker Text-To-Speech Synthesis](/media/video/2022/05/long-review-transfer-learning-from-speaker-verification-to-multispeaker-text-to-speech/preview.jpg)
Tutorials
[長評論] 從說話人驗證到多說話人TTS合成的遷移學習
這是使零樣本語音克隆成為實用的論文：在具有數千個嘈雜、無文本記錄的語音上訓練說話人編碼器進行判別性驗證任務，然後將這些嵌入輸入到Tacotron 2 s
![[Short Review] Transfer Learning from Speaker Verification to Multispeaker Text-To-Speech Synthesis](/media/video/2022/05/short-review-transfer-learning-from-speaker-verification-to-multispeaker-text-to-speech/preview.jpg)
Tutorials
[短評論] 從說話人驗證到多說話人TTS合成的遷移學習
Google的論文啟動了現代零樣本語音克隆浪潮，具有簡潔優美的架構：一個在驗證上訓練的說話人編碼器、一個Tacotron 2合成器可將文本加說話人嵌入轉換
![[Short Review] Wav2Seq: Pre-training Speech-to-Text Encoder-Decoder Models Using Pseudo Languages](/media/video/2022/05/short-review-wav2seq-pre-training-speech-to-text-encoder-decoder-models-using-pseudo/preview.jpg)
Tutorials
[短評論] Wav2Seq：使用偽語言預訓練語音轉文本編碼器-解碼器模型
像wav2vec 2.0這樣的自監督預訓練給了我們很好的語音編碼器，但如果你想要一個完整的編碼器-解碼器ASR系統，解碼器仍然從零開始。
![[Long Review] Towards Zero-Label Language Learning](/media/video/2022/05/long-review-towards-zero-label-language-learning/preview.jpg)
Tutorials
[長篇評論] Towards Zero-Label Language Learning
如果您可以在沒有任何人工標註範例的情況下訓練任務特定的 NLP 模型呢？"Towards Zero-Label Language Learning" 著力強調了這個問題。
![[Short Review] Deduplicating Training Data Makes Language Models Better](/media/video/2022/04/short-review-deduplicating-training-data-makes-language-models-better/preview.jpg)