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 81–90 of 95 papers

TitleStatusHype
Paramixer: Parameterizing Mixing Links in Sparse Factors Works Better than Dot-Product Self-AttentionCode1
Diagonal State Spaces are as Effective as Structured State Spaces—0
SCROLLS: Standardized CompaRison Over Long Language SequencesCode1
Classification of Long Sequential Data using Circular Dilated Convolutional Neural NetworksCode1
LongT5: Efficient Text-To-Text Transformer for Long SequencesCode1
Efficiently Modeling Long Sequences with Structured State SpacesCode1
Dyadformer: A Multi-modal Transformer for Long-Range Modeling of Dyadic Interactions—0
Long-Range Modeling of Source Code Files with eWASH: Extended Window Access by Syntax Hierarchy—0
Sparse Factorization of Large Square MatricesCode0
Image Super-Resolution With Non-Local Sparse AttentionCode1
Show:102550
← PrevPage 9 of 10Next →

No leaderboard results yet.