DaNing
  文章分类
心情随笔 1 编程 3 深度学习 67 知识图谱 29 前端 1 博客 7 算法 2 Markdown 1 机器学习 16 计算机基础 4 小玩意儿 1
MeanFlow: Mean Flows for One-step Generative Modeling MeanFlow: Mean Flows for One-step Generative Modeling
本文前置知识: Flow Matching: Flow Matching for Generative Modeling. 或者: Rectified Flow: ReFlow: Flow Straight and Fast: Le
2025-05-22 深度学习
Diffusion Flow Flow Matching Mean Flow
ReFlow: Flow Straight and Fast-Learning to Generate and Transfer Data with Rectified Flow ReFlow: Flow Straight and Fast-Learning to Generate and Transfer Data with Rectified Flow
Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow 论文: Flow Straight and Fast: Learning
2025-05-20 深度学习
Diffusion Flow ReFlow
AlignSTS: Speech-to-Singing Conversion via Cross-Modal Alignment AlignSTS: Speech-to-Singing Conversion via Cross-Modal Alignment
AlignSTS: Speech-to-Singing Conversion via Cross-Modal Alignment 论文: AlignSTS: Speech-to-Singing Conversion via Cross-Mo
2025-05-13 深度学习
STS Audio
DDIM: Denoising Diffusion Implicit Models DDIM: Denoising Diffusion Implicit Models
本文前置知识: DDPM: DDPM: Denoising Diffusion Probabilistic Model. Denoising Diffusion Implicit Models 论文: Denoising Diffu
2025-03-21 深度学习
Diffusion DDIM
RoPE / RoFormer: Enhanced Transformer with Rotary Position Embedding RoPE / RoFormer: Enhanced Transformer with Rotary Position Embedding
RoPE / RoFormer: Enhanced Transformer with Rotary Position Embedding本文是论文 RoFormer: Enhanced Transformer with Rotary Pos
2025-02-12 深度学习
RoPE LLM
CLAP: Large-scale Contrastive Language-Audio Pretraining with Feature Fusion and Keyword-to-Caption Augmentation CLAP: Large-scale Contrastive Language-Audio Pretraining with Feature Fusion and Keyword-to-Caption Augmentation
Large-scale Contrastive Language-Audio Pretraining with Feature Fusion and Keyword-to-Caption Augmentation本文是论文Large-Sca
2025-02-07 深度学习
Audio
EVA-GAN: Enhanced Various Audio Generation via Scalable Generative Adversarial Networks EVA-GAN: Enhanced Various Audio Generation via Scalable Generative Adversarial Networks
本文前置知识: HiFi - GAN: HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis. EVA-
2025-01-17 深度学习
Audio SVS Vocoder TTS
HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis
HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis本文是论文HiFi-GAN: Generative Adve
2025-01-03 深度学习
Audio SVS Vocoder TTS
DiffSinger: Singing Voice Synthesis via Shallow Diffusion Mechanism DiffSinger: Singing Voice Synthesis via Shallow Diffusion Mechanism
本文前置知识: DDPM: Denoising Diffusion Probabilistic Model. DiffSinger: Singing Voice Synthesis via Shallow Diffusion Me
2024-10-18 深度学习
Audio SVS DDPM Diffusion
DDPM: Denoising Diffusion Probabilistic Model DDPM: Denoising Diffusion Probabilistic Model
2025.03.17: 更新Reverse Process中的描述. DDPM: Denoising Diffusion Probabilistic ModelDDPM Overview DDPM: Denoising Diffusio
2024-10-07 深度学习
DDPM Diffusion
Introduction: Vector Quantization Introduction: Vector Quantization
Introduction: Vector QuantizationVector QuantizationAutoEncoder(AE)由Encoder和Decoder组成, Encoder将图像压缩为一个低维的隐向量(Latent), 再由
2024-07-16 深度学习
VQ VQ-VAE VQ-GAN
Multimodal Large Language Model 总结 Multimodal Large Language Model 总结
本文前置知识: Vision & Language Pretrained Model 总结. 2025.05.06: 应评论区要求, 更新了Qwen-VL系列(Qwen-VL, Qwen2-VL, Qwen2.5-VL). Mu
2024-07-03 深度学习
MLLM MM
1 / 6