Trending Research
Parameter-Efficient Fine-Tuning with Discrete Fourier Transform
Low-rank adaptation~(LoRA) has recently gained much interest in fine-tuning foundation models.
MRSegmentator: Robust Multi-Modality Segmentation of 40 Classes in MRI and CT Sequences
Results: The model showcased high accuracy in segmenting well-defined organs, achieving Dice Similarity Coefficient (DSC) scores of 0. 97 for the right and left lungs, and 0. 95 for the heart.
Rewrite the Stars
Recent studies have drawn attention to the untapped potential of the "star operation" (element-wise multiplication) in network design.
4D Panoptic Scene Graph Generation
jingkang50/psg4d
•
•
To facilitate research in this new area, we build a richly annotated PSG-4D dataset consisting of 3K RGB-D videos with a total of 1M frames, each of which is labeled with 4D panoptic segmentation masks as well as fine-grained, dynamic scene graphs.
OpenProteinSet: Training data for structural biology at scale
aqlaboratory/openfold
•
•
NeurIPS 2023
Multiple sequence alignments (MSAs) of proteins encode rich biological information and have been workhorses in bioinformatic methods for tasks like protein design and protein structure prediction for decades.
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.
Spectrally Pruned Gaussian Fields with Neural Compensation
However, this comes with high memory consumption, e. g., a well-trained Gaussian field may utilize three million Gaussian primitives and over 700 MB of memory.
LeMeViT: Efficient Vision Transformer with Learnable Meta Tokens for Remote Sensing Image Interpretation
Experimental results in classification and dense prediction tasks show that LeMeViT has a significant $1. 7 \times$ speedup, fewer parameters, and competitive performance compared to the baseline models, and achieves a better trade-off between efficiency and performance.
MS MARCO Web Search: a Large-scale Information-rich Web Dataset with Millions of Real Click Labels
Recent breakthroughs in large models have highlighted the critical significance of data scale, labels and modals.
DiverGen: Improving Instance Segmentation by Learning Wider Data Distribution with More Diverse Generative Data
Instance segmentation is data-hungry, and as model capacity increases, data scale becomes crucial for improving the accuracy.
Ranked #7 on
Object Detection
on LVIS v1.0 val
