Papers with Code 아카이브
Long-range modeling
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 2
- 보존된 평가 기록
- 20
A new task for testing the long-sequence modeling capabilities and efficiency of language models.
Image credit: SCROLLS: Standardized CompaRison Over Long Language Sequences
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
LaCache: Ladder-Shaped KV Caching for Efficient Long-Context Modeling of Large Language Models
MambaFusion: Height-Fidelity Dense Global Fusion for Multi-modal 3D Object Detection
Med-URWKV: Pure RWKV With ImageNet Pre-training For Medical Image Segmentation
M2Restore: Mixture-of-Experts-based Mamba-CNN Fusion Framework for All-in-One Image Restoration
CDPDNet: Integrating Text Guidance with Hybrid Vision Encoders for Medical Image Segmentation
JanusDNA: A Powerful Bi-directional Hybrid DNA Foundation Model
Hybrid-Emba3D: Geometry-Aware and Cross-Path Feature Hybrid Enhanced State Space Model for Point Cloud Classification
ZipIR: Latent Pyramid Diffusion Transformer for High-Resolution Image Restoration
VADMamba: Exploring State Space Models for Fast Video Anomaly Detection
vGamba: Attentive State Space Bottleneck for efficient Long-range Dependencies in Visual Recognition
Emulating Self-attention with Convolution for Efficient Image Super-Resolution
An Uncertainty Principle for Linear Recurrent Neural Networks
Is Long Range Sequential Modeling Necessary For Colorectal Tumor Segmentation?
ReGNet: Reciprocal Space-Aware Long-Range Modeling for Crystalline Property Prediction
Converting Transformers into DGNNs Form
KM-UNet KAN Mamba UNet for medical image segmentation
GIRAFFE: Design Choices for Extending the Context Length of Visual Language Models
MambaXCTrack: Mamba-based Tracker with SSM Cross-correlation and Motion Prompt for Ultrasound Needle Tracking
CT-Mamba: A Hybrid Convolutional State Space Model for Low-Dose CT Denoising
QuadMamba: Learning Quadtree-based Selective Scan for Visual State Space Model
S7: Selective and Simplified State Space Layers for Sequence Modeling
Shuffle Mamba: State Space Models with Random Shuffle for Multi-Modal Image Fusion
PoseMamba: Monocular 3D Human Pose Estimation with Bidirectional Global-Local Spatio-Temporal State Space Model
Pose Magic: Efficient and Temporally Consistent Human Pose Estimation with a Hybrid Mamba-GCN Network
LION: Linear Group RNN for 3D Object Detection in Point Clouds
Hierarchical Separable Video Transformer for Snapshot Compressive Imaging
Short-Long Convolutions Help Hardware-Efficient Linear Attention to Focus on Long Sequences
Long Range Propagation on Continuous-Time Dynamic Graphs
Spatio-Spectral Graph Neural Networks
SMR: State Memory Replay for Long Sequence Modeling
MambaLLIE: Implicit Retinex-Aware Low Light Enhancement with Global-then-Local State Space
MambaVC: Learned Visual Compression with Selective State Spaces
DVMSR: Distillated Vision Mamba for Efficient Super-Resolution
MambaAD: Exploring State Space Models for Multi-class Unsupervised Anomaly Detection
RS3Mamba: Visual State Space Model for Remote Sensing Images Semantic Segmentation
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.