https://github.com/tonyby/ramqa
공식 코드RAMQA: A Unified Framework for Retrieval-Augmented Multi-Modal Question Answering
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
RAMQA: A Unified Framework for Retrieval-Augmented Multi-Modal Question Answering
GCN-MIF: Graph Convolutional Network with Multi-Information Fusion for Low-dose CT Denoising
GCN-MIF: Graph Convolutional Network with Multi-Information Fusion for Low-dose CT Denoising
On the Quantitative Analysis of Decoder-Based Generative Models
Decoder Pre-Training with only Text for Scene Text Recognition
QTSeg: A Query Token-Based Architecture for Efficient 2D Medical Image Segmentation
A Novel Encoder-Decoder Network with Guided Transmission Map for Single Image Dehazing
Transformer-VQ: Linear-Time Transformers via Vector Quantization
Permutation-Aware Action Segmentation via Unsupervised Frame-to-Segment Alignment
MacLaSa: Multi-Aspect Controllable Text Generation via Efficient Sampling from Compact Latent Space
Predicting time-varying flux and balance in metabolic systems using structured neural-ODE processes
GeoMAE: Masked Geometric Target Prediction for Self-supervised Point Cloud Pre-Training
Generalizing Motion Planners with Mixture of Experts for Autonomous Driving
How to Benchmark Vision Foundation Models for Semantic Segmentation?
Spatiotemporal Tile-based Attention-guided LSTMs for Traffic Video Prediction
FourierNets enable the design of highly non-local optical encoders for computational imaging
Generating Long and Informative Reviews with Aspect-Aware Coarse-to-Fine Decoding
Context-aware Difference Distilling for Multi-change Captioning
Exploiting Cross-Sentence Context for Neural Machine Translation
RM-Depth: Unsupervised Learning of Recurrent Monocular Depth in Dynamic Scenes
Crystal Diffusion Variational Autoencoder for Periodic Material Generation
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.