Trending Research
EfficientTrain++: Generalized Curriculum Learning for Efficient Visual Backbone Training
These patterns, when observed through frequency and spatial domains, incorporate lower-frequency components, and the natural image contents without distortion or data augmentation.
Cross-Attention Makes Inference Cumbersome in Text-to-Image Diffusion Models
This study explores the role of cross-attention during inference in text-conditional diffusion models.
DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model
MLA guarantees efficient inference through significantly compressing the Key-Value (KV) cache into a latent vector, while DeepSeekMoE enables training strong models at an economical cost through sparse computation.
Assisting in Writing Wikipedia-like Articles From Scratch with Large Language Models
We study how to apply large language models to write grounded and organized long-form articles from scratch, with comparable breadth and depth to Wikipedia pages.
From Sora What We Can See: A Survey of Text-to-Video Generation
soraw-ai/awesome-text-to-video-generation
•
•
With impressive achievements made, artificial intelligence is on the path forward to artificial general intelligence.
CDFormer:When Degradation Prediction Embraces Diffusion Model for Blind Image Super-Resolution
i2-multimedia-lab/cdformer
•
•
Existing Blind image Super-Resolution (BSR) methods focus on estimating either kernel or degradation information, but have long overlooked the essential content details.
Lumina-T2X: Transforming Text into Any Modality, Resolution, and Duration via Flow-based Large Diffusion Transformers
Sora unveils the potential of scaling Diffusion Transformer for generating photorealistic images and videos at arbitrary resolutions, aspect ratios, and durations, yet it still lacks sufficient implementation details.
SCEdit: Efficient and Controllable Image Diffusion Generation via Skip Connection Editing
modelscope/swift
•
•
Image diffusion models have been utilized in various tasks, such as text-to-image generation and controllable image synthesis.
ConsistentID: Portrait Generation with Multimodal Fine-Grained Identity Preserving
ConsistentID comprises two key components: a multimodal facial prompt generator that combines facial features, corresponding facial descriptions and the overall facial context to enhance precision in facial details, and an ID-preservation network optimized through the facial attention localization strategy, aimed at preserving ID consistency in facial regions.
MiniCPM: Unveiling the Potential of Small Language Models with Scalable Training Strategies
openbmb/minicpm
•
•
For data scaling, we introduce a Warmup-Stable-Decay (WSD) learning rate scheduler (LRS), conducive to continuous training and domain adaptation.
