Trending Research
InstaFlow: One Step is Enough for High-Quality Diffusion-Based Text-to-Image Generation
Leveraging our new pipeline, we create, to the best of our knowledge, the first one-step diffusion-based text-to-image generator with SD-level image quality, achieving an FID (Frechet Inception Distance) of $23. 3$ on MS COCO 2017-5k, surpassing the previous state-of-the-art technique, progressive distillation, by a significant margin ($37. 2$ $\rightarrow$ $23. 3$ in FID).
OpenBA: An Open-sourced 15B Bilingual Asymmetric seq2seq Model Pre-trained from Scratch
opennlg/openba
•
•
This report provides the main details to pre-train an analogous model, including pre-training data processing, Bilingual Flan data collection, the empirical observations that inspire our model architecture design, training objectives of different stages, and other enhancement techniques.
3D Gaussian Splatting for Real-Time Radiance Field Rendering
graphdeco-inria/gaussian-splatting
•
•
Radiance Field methods have recently revolutionized novel-view synthesis of scenes captured with multiple photos or videos.
Kani: A Lightweight and Highly Hackable Framework for Building Language Model Applications
Language model applications are becoming increasingly popular and complex, often including features like tool usage and retrieval augmentation.
DreamLLM: Synergistic Multimodal Comprehension and Creation
This paper presents DreamLLM, a learning framework that first achieves versatile Multimodal Large Language Models (MLLMs) empowered with frequently overlooked synergy between multimodal comprehension and creation.
LayoutNUWA: Revealing the Hidden Layout Expertise of Large Language Models
Graphic layout generation, a growing research field, plays a significant role in user engagement and information perception.
GPT Can Solve Mathematical Problems Without a Calculator
thudm/mathglm
•
•
Previous studies have typically assumed that large language models are unable to accurately perform arithmetic operations, particularly multiplication of >8 digits, and operations involving decimals and fractions, without the use of calculator tools.
MMICL: Empowering Vision-language Model with Multi-Modal In-Context Learning
haozhezhao/mic
•
•
Specifically, the current VLMs primarily emphasize utilizing multi-modal data with a single image some, rather than multi-modal prompts with interleaved multiple images and text.
EfficientViT: Lightweight Multi-Scale Attention for On-Device Semantic Segmentation
Unlike prior semantic segmentation models that rely on heavy self-attention, hardware-inefficient large-kernel convolution, or complicated topology structure to obtain good performances, our lightweight multi-scale attention achieves a global receptive field and multi-scale learning (two critical features for semantic segmentation models) with only lightweight and hardware-efficient operations.
Ranked #19 on
Semantic Segmentation
on Cityscapes val
Petals: Collaborative Inference and Fine-tuning of Large Models
bigscience-workshop/petals
•
•
However, these techniques have innate limitations: offloading is too slow for interactive inference, while APIs are not flexible enough for research that requires access to weights, attention or logits.
