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 2650 of 95 papers

TitleStatusHype
LION: Linear Group RNN for 3D Object Detection in Point CloudsCode3
Hierarchical Separable Video Transformer for Snapshot Compressive ImagingCode1
Short-Long Convolutions Help Hardware-Efficient Linear Attention to Focus on Long Sequences0
Long Range Propagation on Continuous-Time Dynamic GraphsCode1
Spatio-Spectral Graph Neural NetworksCode1
SMR: State Memory Replay for Long Sequence Modeling0
MambaLLIE: Implicit Retinex-Aware Low Light Enhancement with Global-then-Local State Space0
MambaVC: Learned Visual Compression with Selective State SpacesCode2
DVMSR: Distillated Vision Mamba for Efficient Super-ResolutionCode2
MambaAD: Exploring State Space Models for Multi-class Unsupervised Anomaly DetectionCode3
RS3Mamba: Visual State Space Model for Remote Sensing Images Semantic SegmentationCode0
LKM-UNet: Large Kernel Vision Mamba UNet for Medical Image SegmentationCode2
MedMamba: Vision Mamba for Medical Image ClassificationCode4
nnMamba: 3D Biomedical Image Segmentation, Classification and Landmark Detection with State Space ModelCode2
MambaMorph: a Mamba-based Framework for Medical MR-CT Deformable RegistrationCode2
A Simple LLM Framework for Long-Range Video Question-AnsweringCode1
Part Representation Learning with Teacher-Student Decoder for Occluded Person Re-identificationCode0
Recurrent Distance Filtering for Graph Representation LearningCode1
Mamba: Linear-Time Sequence Modeling with Selective State SpacesCode6
Dimension Mixer: Group Mixing of Input Dimensions for Efficient Function ApproximationCode0
Advancing Regular Language Reasoning in Linear Recurrent Neural NetworksCode0
Improving FHB Screening in Wheat Breeding Using an Efficient Transformer Model0
TaskExpert: Dynamically Assembling Multi-Task Representations with Memorial Mixture-of-ExpertsCode2
AICT: An Adaptive Image Compression Transformer0
ViTEraser: Harnessing the Power of Vision Transformers for Scene Text Removal with SegMIM PretrainingCode1
Show:102550
← PrevPage 2 of 4Next →

No leaderboard results yet.