SOTAVerified

Long-range modeling

A new task for testing the long-sequence modeling capabilities and efficiency of language models.

Image credit: SCROLLS: Standardized CompaRison Over Long Language Sequences

Papers

Showing 5195 of 95 papers

TitleStatusHype
V4D:4D Convolutional Neural Networks for Video-level Representation LearningCode1
VADMamba: Exploring State Space Models for Fast Video Anomaly DetectionCode1
ViTEraser: Harnessing the Power of Vision Transformers for Scene Text Removal with SegMIM PretrainingCode1
Weakly Supervised Object Localization via Transformer with Implicit Spatial CalibrationCode1
What Makes Convolutional Models Great on Long Sequence Modeling?Code1
AICT: An Adaptive Image Compression Transformer0
MambaXCTrack: Mamba-based Tracker with SSM Cross-correlation and Motion Prompt for Ultrasound Needle Tracking0
Exploring Historical Information for RGBE Visual Tracking with Mamba0
Improving FHB Screening in Wheat Breeding Using an Efficient Transformer Model0
Dyadformer: A Multi-modal Transformer for Long-Range Modeling of Dyadic Interactions0
Is Long Range Sequential Modeling Necessary For Colorectal Tumor Segmentation?0
S7: Selective and Simplified State Space Layers for Sequence Modeling0
ZipIR: Latent Pyramid Diffusion Transformer for High-Resolution Image Restoration0
CoLT5: Faster Long-Range Transformers with Conditional Computation0
Short-Long Convolutions Help Hardware-Efficient Linear Attention to Focus on Long Sequences0
Long-Range Modeling of Source Code Files with eWASH: Extended Window Access by Syntax Hierarchy0
Shuffle Mamba: State Space Models with Random Shuffle for Multi-Modal Image Fusion0
Pose Magic: Efficient and Temporally Consistent Human Pose Estimation with a Hybrid Mamba-GCN Network0
M2Restore: Mixture-of-Experts-based Mamba-CNN Fusion Framework for All-in-One Image Restoration0
0/1 Deep Neural Networks via Block Coordinate Descent0
MambaLLIE: Implicit Retinex-Aware Low Light Enhancement with Global-then-Local State Space0
An Uncertainty Principle for Linear Recurrent Neural Networks0
SMR: State Memory Replay for Long Sequence Modeling0
Med-URWKV: Pure RWKV With ImageNet Pre-training For Medical Image Segmentation0
Pose Guided Human Image Synthesis with Partially Decoupled GAN0
Token Transformer: Can class token help window-based transformer build better long-range interactions?0
Focus Your Attention (with Adaptive IIR Filters)0
Gated Relational Graph Attention Networks0
ReGNet: Reciprocal Space-Aware Long-Range Modeling for Crystalline Property Prediction0
HST-MRF: Heterogeneous Swin Transformer with Multi-Receptive Field for Medical Image Segmentation0
A General-Purpose Multilingual Document EncoderCode0
Advancing Regular Language Reasoning in Linear Recurrent Neural NetworksCode0
How to Train Your HiPPO: State Space Models with Generalized Orthogonal Basis ProjectionsCode0
CNSNet: A Cleanness-Navigated-Shadow Network for Shadow RemovalCode0
On the Parameterization and Initialization of Diagonal State Space ModelsCode0
Sparse Factorization of Large Square MatricesCode0
Part Representation Learning with Teacher-Student Decoder for Occluded Person Re-identificationCode0
CDPDNet: Integrating Text Guidance with Hybrid Vision Encoders for Medical Image SegmentationCode0
Hybrid-Emba3D: Geometry-Aware and Cross-Path Feature Hybrid Enhanced State Space Model for Point Cloud ClassificationCode0
vGamba: Attentive State Space Bottleneck for efficient Long-range Dependencies in Visual RecognitionCode0
RS3Mamba: Visual State Space Model for Remote Sensing Images Semantic SegmentationCode0
LaCache: Ladder-Shaped KV Caching for Efficient Long-Context Modeling of Large Language ModelsCode0
Dimension Mixer: Group Mixing of Input Dimensions for Efficient Function ApproximationCode0
Diagonal State Spaces are as Effective as Structured State SpacesCode0
RFR-WWANet: Weighted Window Attention-Based Recovery Feature Resolution Network for Unsupervised Image RegistrationCode0
Show:102550
← PrevPage 2 of 2Next →

No leaderboard results yet.