Papers with Code 아카이브
Long-range modeling
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 2
- 보존된 평가 기록
- 20
A new task for testing the long-sequence modeling capabilities and efficiency of language models.
Image credit: SCROLLS: Standardized CompaRison Over Long Language Sequences
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
Efficient Long-Text Understanding with Short-Text Models
Weakly Supervised Object Localization via Transformer with Implicit Spatial Calibration
How to Train Your HiPPO: State Space Models with Generalized Orthogonal Basis Projections
On the Parameterization and Initialization of Diagonal State Space Models
0/1 Deep Neural Networks via Block Coordinate Descent
ChordMixer: A Scalable Neural Attention Model for Sequences with Different Lengths
UL2: Unifying Language Learning Paradigms
Paramixer: Parameterizing Mixing Links in Sparse Factors Works Better than Dot-Product Self-Attention
Diagonal State Spaces are as Effective as Structured State Spaces
SCROLLS: Standardized CompaRison Over Long Language Sequences
Classification of Long Sequential Data using Circular Dilated Convolutional Neural Networks
LongT5: Efficient Text-To-Text Transformer for Long Sequences
Efficiently Modeling Long Sequences with Structured State Spaces
Dyadformer: A Multi-modal Transformer for Long-Range Modeling of Dyadic Interactions
Long-Range Modeling of Source Code Files with eWASH: Extended Window Access by Syntax Hierarchy
Sparse Factorization of Large Square Matrices
DSANet: Dynamic Segment Aggregation Network for Video-Level Representation Learning
Long Range Arena: A Benchmark for Efficient Transformers
Disentangling and Unifying Graph Convolutions for Skeleton-Based Action Recognition
V4D:4D Convolutional Neural Networks for Video-level Representation Learning
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.