KTO: Model Alignment as Prospect Theoretic Optimization （ICML2024 ）
<script async class=”docswell-embed” src=”https://bcdn.docswell. more
カテゴリー: seminar
SlotDiffusion: Object-Centric Generative Modeling with Diffusion Models
【拡散モデル勉強会】SlotDiffusion: Object-Centric Generative Modeling with Diffusion Models by more
Scaling Diffusion Transformers to 16 Billion Parameters
【Diffusion勉強会】Scaling Diffusion Transformers to 16 Billion Parameters by @DeepLearnin more
Scaling-Diffusion-Transformers-to-16-Billion-Parameters
【拡散モデル勉強会】Scaling-Diffusion-Transformers-to-16-Billion-Parameters by @DeepLearning202 more
Bigger is not Always Better: Scaling Properties of Latent Diffusion Models
【拡散モデル勉強会】Bigger is not Always Better: Scaling Properties of Latent Diffusion Models more
Data Level Lottery Ticket Hypothesis
Data Level Lottery Ticket Hypothesis by @DeepLearning2023
“C-NERF: Representing Scene Changes asDirectional Consistency Difference-based NeRF”
“C-NERF: Representing Scene Changes as Directional Consistency Difference-based NeRF” more
Scaling Rectified Flow Transformers for High-Resolution Image Synthesis
【拡散モデル勉強会】Scaling Rectified Flow Transformers for High-Resolution Image Synthesis by more
CADS: Unleashing the diversity of diffusion models through condition-annealed sampling
【Diffusion勉強会】CADS: Unleashing the diversity of diffusion models through condition-an more
Neural Redshift: Random Networks are not Random Functions
Neural Redshift: Random Networks are not Random Functions by @DeepLearning2023