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 125 of 95 papers

TitleStatusHype
Mamba: Linear-Time Sequence Modeling with Selective State SpacesCode6
MedMamba: Vision Mamba for Medical Image ClassificationCode4
MambaAD: Exploring State Space Models for Multi-class Unsupervised Anomaly DetectionCode3
Investigating Efficiently Extending Transformers for Long Input SummarizationCode3
LION: Linear Group RNN for 3D Object Detection in Point CloudsCode3
Liquid Structural State-Space ModelsCode2
TaskExpert: Dynamically Assembling Multi-Task Representations with Memorial Mixture-of-ExpertsCode2
DVMSR: Distillated Vision Mamba for Efficient Super-ResolutionCode2
nnMamba: 3D Biomedical Image Segmentation, Classification and Landmark Detection with State Space ModelCode2
MambaVC: Learned Visual Compression with Selective State SpacesCode2
PoseMamba: Monocular 3D Human Pose Estimation with Bidirectional Global-Local Spatio-Temporal State Space ModelCode2
Hungry Hungry Hippos: Towards Language Modeling with State Space ModelsCode2
LKM-UNet: Large Kernel Vision Mamba UNet for Medical Image SegmentationCode2
Mega: Moving Average Equipped Gated AttentionCode2
Emulating Self-attention with Convolution for Efficient Image Super-ResolutionCode2
MambaMorph: a Mamba-based Framework for Medical MR-CT Deformable RegistrationCode2
Simplified State Space Layers for Sequence ModelingCode2
MambaFusion: Height-Fidelity Dense Global Fusion for Multi-modal 3D Object DetectionCode2
Classification of Long Sequential Data using Circular Dilated Convolutional Neural NetworksCode1
ChordMixer: A Scalable Neural Attention Model for Sequences with Different LengthsCode1
Adapting Pretrained Text-to-Text Models for Long Text SequencesCode1
Efficient Long-Text Understanding with Short-Text ModelsCode1
CAB: Comprehensive Attention Benchmarking on Long Sequence ModelingCode1
GIRAFFE: Design Choices for Extending the Context Length of Visual Language ModelsCode1
Long Range Arena: A Benchmark for Efficient TransformersCode1
Show:102550
← PrevPage 1 of 4Next →

No leaderboard results yet.