Papers with Code 아카이브

Mamba

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

전체 기법전체 데이터셋

하위 태스크

0

평가표

0

보존된 평가 기록

0

코드

관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.

https://github.com/olga-zats/diff_manta

MANTA: Diffusion Mamba for Efficient and Effective Stochastic Long-Term Dense Anticipation

https://github.com/oliverrensu/mvg

U-Mamba: Enhancing Long-range Dependency for Biomedical Image Segmentation

https://github.com/perceptualai-lab/awesome-domain-generalizable-person-re-id

AceVFI: A Comprehensive Survey of Advances in Video Frame Interpolation

https://github.com/piskovskyi/fMRI-VisionMamba

VMamba: Visual State Space Model

https://github.com/proger/hippogriff

Griffin: Mixing Gated Linear Recurrences with Local Attention for Efficient Language Models

https://github.com/pwc-1/Paper-9/tree/main/jamba

Jamba: A Hybrid Transformer-Mamba Language Model

https://github.com/pwc-1/Paper-9/tree/main/mamba

MambaOut: Do We Really Need Mamba for Vision?

https://github.com/reAIM-Lab/ehr_foundation_model_benchmark

Context Clues: Evaluating Long Context Models for Clinical Prediction Tasks on EHRs

https://github.com/rorschach1989/transformer-for-gmm

Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality

https://github.com/skyworkai/mvgamba

Gamba: Marry Gaussian Splatting with Mamba for single view 3D reconstruction

https://github.com/tawald/nnunet

nnU-Net Revisited: A Call for Rigorous Validation in 3D Medical Image Segmentation

https://github.com/test-time-training/ttt-lm-jax

Learning to (Learn at Test Time): RNNs with Expressive Hidden States

https://github.com/theodorblackbird/lina-speech

Gated Linear Attention Transformers with Hardware-Efficient Training

https://github.com/tk-rusch/linoss

Oscillatory State-Space Models

https://github.com/tommyip/mamba2-minimal

Mamba: Linear-Time Sequence Modeling with Selective State Spaces

https://github.com/tonyyouyou/mamba-in-speech

Mamba in Speech: Towards an Alternative to Self-Attention

https://github.com/torchrwkv/flash-linear-attention

Gated Linear Attention Transformers with Hardware-Efficient Training

https://github.com/vertaix/Alpha-Alternator

The $α$-Alternator: Dynamic Adaptation To Varying Noise Levels In Sequences Using The Vendi Score For Improved Robustness and Performance

https://github.com/vvvm23/mamba-jax

Mamba: Linear-Time Sequence Modeling with Selective State Spaces

https://github.com/wangf3014/mamba-reg

Mamba-R: Vision Mamba ALSO Needs Registers

https://github.com/wanglibo1995/unetformer

PyramidMamba: Rethinking Pyramid Feature Fusion with Selective Space State Model for Semantic Segmentation of Remote Sensing Imagery

https://github.com/weiwang31/icemamba

Mamba: Linear-Time Sequence Modeling with Selective State Spaces

https://github.com/yangyucheng000/University/tree/main/model-2/jamba

Jamba-1.5: Hybrid Transformer-Mamba Models at Scale

https://github.com/ydchen0806/tokenunify

TokenUnify: Scalable Autoregressive Visual Pre-training with Mixture Token Prediction

https://github.com/yynil/rwkvinllama

Transformers to SSMs: Distilling Quadratic Knowledge to Subquadratic Models

https://github.com/zhangzjn/ader

MambaAD: Exploring State Space Models for Multi-class Unsupervised Anomaly Detection

https://github.com/zhaoziheng/sat

One Model to Rule them All: Towards Universal Segmentation for Medical Images with Text Prompts

https://github.com/ziyangwang007/vmambamorph

MambaMorph: a Mamba-based Framework for Medical MR-CT Deformable Registration

https://github.com/ziyangwang007/weak-mamba-unet

Weak-Mamba-UNet: Visual Mamba Makes CNN and ViT Work Better for Scribble-based Medical Image Segmentation

https://github.com/zmoka-zht/BiFA

CDMamba: Incorporating Local Clues into Mamba for Remote Sensing Image Binary Change Detection

https://github.com/zzmtsvv/mamba-interface

Mamba: Linear-Time Sequence Modeling with Selective State Spaces

https://gitlab.com/birder/birder

EfficientViM: Efficient Vision Mamba with Hidden State Mixer based State Space Duality

출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.