Schedule
- 经典工作
- [✓] ImageNet Classification with Deep Convolutional Neural Networks (2012)
- [✗] Generative Adversarial Nets (2014)
- [✓] Deep Residual Learning for Image Recognition (2015)
- [✓] Attention Is All You Need (2017)
- [✓] Neural Discrete Representation Learning (2017)
- [✓] Taming Transformers for High-Resolution Image Synthesis (2020)
- …
- 前沿工作
- [✓] High-Resolution Image Synthesis with Latent Diffusion Models (2021)
- [✗] Mamba: Linear-Time Sequence Modeling with Selective State Spaces (2023)
- [✗] Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction (NIPS24 best paper)
- [✗] Vision Transformers Need Registers (ICLR24 Award Winners)
- [✗] Generalization in diffusion models arises from geometry-adaptive harmonic representations (ICLR24 Award Winners)
- [✗] Position: Measure Dataset Diversity, Don’t Just Claim It
- [✗] Minimalist Vision with Freeform Pixels (ECCV24 best paper)
- [✗] Generative Image Dynamics (CVPR24 best paper)
- [✗] Rich Human Feedback for Text-to-Image Generation (CVPR24 best paper)
- …
- 模型融合
- [✓] INTELLECT-1 Technical Report (助力分布式训练)
- …
- 其他
- [✓] DIVA: DOMAIN INVARIANT VARIATIONAL AUTOEN CODERS
- …