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

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 51–75 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
An Uncertainty Principle for Linear Recurrent Neural Networks—0
MambaXCTrack: Mamba-based Tracker with SSM Cross-correlation and Motion Prompt for Ultrasound Needle Tracking—0
ZipIR: Latent Pyramid Diffusion Transformer for High-Resolution Image Restoration—0
Diagonal State Spaces are as Effective as Structured State Spaces—0
CoLT5: Faster Long-Range Transformers with Conditional Computation—0
Short-Long Convolutions Help Hardware-Efficient Linear Attention to Focus on Long Sequences—0
Long-Range Modeling of Source Code Files with eWASH: Extended Window Access by Syntax Hierarchy—0
Shuffle Mamba: State Space Models with Random Shuffle for Multi-Modal Image Fusion—0
Pose Magic: Efficient and Temporally Consistent Human Pose Estimation with a Hybrid Mamba-GCN Network—0
M2Restore: Mixture-of-Experts-based Mamba-CNN Fusion Framework for All-in-One Image Restoration—0
0/1 Deep Neural Networks via Block Coordinate Descent—0
MambaLLIE: Implicit Retinex-Aware Low Light Enhancement with Global-then-Local State Space—0
AICT: An Adaptive Image Compression Transformer—0
SMR: State Memory Replay for Long Sequence Modeling—0
Med-URWKV: Pure RWKV With ImageNet Pre-training For Medical Image Segmentation—0
On the Parameterization and Initialization of Diagonal State Space Models—0
Pose Guided Human Image Synthesis with Partially Decoupled GAN—0
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 Networks—0
Show:102550
← PrevPage 3 of 4Next →

No leaderboard results yet.