Alternatives and similar repositories for UMoE

Users that are interested in UMoE are comparing it to the libraries listed below

• tianyi-lab / R2-T2
  [ICML 2025] Code for "R2-T2: Re-Routing in Test-Time for Multimodal Mixture-of-Experts"
  ☆17Updated 9 months ago
• g-luo / vlm_cross_modal_reps
  Official PyTorch Implementation for Vision-Language Models Create Cross-Modal Task Representations, ICML 2025
  ☆31Updated 7 months ago
• MambaMixer / M2
  ☆48Updated last year
• HelmholtzAI-FZJ / flex_gen
  ☆19Updated 11 months ago
• OpenNLPLab / HGRN2
  HGRN2: Gated Linear RNNs with State Expansion
  ☆56Updated last year
• BryceZhuo / PolyCom
  The official implementation of ICLR 2025 paper "Polynomial Composition Activations: Unleashing the Dynamics of Large Language Models".
  ☆15Updated 7 months ago
• smonsays / hypernetwork-attention
  Official code for the paper "Attention as a Hypernetwork"
  ☆46Updated last year
• tim-lawson / skip-middle
  Learning to Skip the Middle Layers of Transformers
  ☆15Updated 4 months ago
• locuslab / llava-token-compression
  ☆46Updated last year
• qiuzh20 / RMoE
  Official implementation of RMoE (Layerwise Recurrent Router for Mixture-of-Experts)
  ☆27Updated last year
• s-sahoo / MuLAN
  [NeurIPS 2024, spotlight] Multivariate Learned Adaptive Noise for Diffusion Models
  ☆30Updated last year
• RobertCsordas / switchhead
  ☆16Updated 6 months ago
• roymiles / VeLoRA
  [NeurIPS 2024] VeLoRA : Memory Efficient Training using Rank-1 Sub-Token Projections
  ☆21Updated last year
• PKU-ML / non_neg
  Official Code for ICLR 2024 Paper: Non-negative Contrastive Learning
  ☆46Updated last year
• pixeli99 / MixLN
  [ICLR 2025] Official Pytorch Implementation of "Mix-LN: Unleashing the Power of Deeper Layers by Combining Pre-LN and Post-LN" by Pengxia…
  ☆27Updated 4 months ago
• Qichuzyy / POA
  Official implementation of ECCV24 paper: POA
  ☆24Updated last year
• VijayLingam95 / SVFT
  ☆34Updated 10 months ago
• ethanlshen / HierNet
  Code for "Are “Hierarchical” Visual Representations Hierarchical?" in NeurIPS Workshop for Symmetry and Geometry in Neural Representation…
  ☆21Updated 2 years ago
• caojiaolong / Awesome-Mamba
  Collect papers about Mamba (a selective state space model).
  ☆14Updated last year
• ExplainableML / fomo_in_flux
  Code and benchmark for the paper: "A Practitioner's Guide to Continual Multimodal Pretraining" [NeurIPS'24]
  ☆61Updated last year
• gmongaras / Cottention_Transformer
  Code for the paper "Cottention: Linear Transformers With Cosine Attention"
  ☆20Updated last month
• kyegomez / MultiQueryAttention
  This is a simple torch implementation of the high performance Multi-Query Attention
  ☆16Updated 2 years ago
• jiaangli / VLCA
  Do Vision and Language Models Share Concepts? A Vector Space Alignment Study
  ☆16Updated last year
• james-oldfield / muMoE
  [NeurIPS'24] Multilinear Mixture of Experts: Scalable Expert Specialization through Factorization
  ☆37Updated last year
• fangyuan-ksgk / selective-attention-transformer
  Unofficial Implementation of Selective Attention Transformer
  ☆18Updated last year
• minhoooo1 / CatMAE
  CatMAE
  ☆14Updated 2 years ago
• top-yun / SPARK
  A benchmark dataset and simple code examples for measuring the perception and reasoning of multi-sensor Vision Language models.
  ☆19Updated 11 months ago
• assafbk / DeciMamba
  DeciMamba: Exploring the Length Extrapolation Potential of Mamba (ICLR 2025)
  ☆31Updated 8 months ago
• epfml / pam
  ☆16Updated 2 years ago
• UCDvision / NOLA
  Code for NOLA, an implementation of "nola: Compressing LoRA using Linear Combination of Random Basis"
  ☆57Updated last year