Alternatives and similar repositories for Value-Residual-Learning

Users that are interested in Value-Residual-Learning 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 10 months ago
• ZihaoHuang-notabot / Ultra-Sparse-Memory-Network
  ☆40Updated 4 months ago
• corl-team / lime
  Official implementation of the paper "You Do Not Fully Utilize Transformer's Representation Capacity"
  ☆31Updated 8 months ago
• shangshang-wang / Resa
  Resa: Transparent Reasoning Models via SAEs
  ☆47Updated 4 months ago
• ALT-JS / OthelloSAE
  CS194-196 Course Project
  ☆14Updated 11 months ago
• arubique / OCCAM
  This is an implementation of the paper "Are We Done with Object-Centric Learning?"
  ☆12Updated 4 months ago
• tim-lawson / skip-middle
  Learning to Skip the Middle Layers of Transformers
  ☆17Updated 5 months ago
• yale-nlp / refdpo
  ☆16Updated last year
• MeganTj / multimodal_alignment
  ☆19Updated 7 months ago
• fangyuan-ksgk / selective-attention-transformer
  Unofficial Implementation of Selective Attention Transformer
  ☆20Updated last year
• OpenNLPLab / HGRN2
  HGRN2: Gated Linear RNNs with State Expansion
  ☆56Updated last year
• kyegomez / MultiQueryAttention
  This is a simple torch implementation of the high performance Multi-Query Attention
  ☆16Updated 2 years ago
• VITA-Group / TAPE
  [ICML'25] "Rethinking Addressing in Language Models via Contextualized Equivariant Positional Encoding" by Jiajun Zhu, Peihao Wang, Ruisi…
  ☆14Updated 7 months ago
• MarkXCloud / CSpD
  The official repo of continuous speculative decoding
  ☆31Updated 10 months ago
• Qichuzyy / POA
  Official implementation of ECCV24 paper: POA
  ☆24Updated last year
• g-luo / vlm_cross_modal_reps
  Official PyTorch Implementation for Vision-Language Models Create Cross-Modal Task Representations, ICML 2025
  ☆31Updated 9 months ago
• BryceZhuo / PolyCom
  The official implementation of ICLR 2025 paper "Polynomial Composition Activations: Unleashing the Dynamics of Large Language Models".
  ☆17Updated 9 months ago
• smonsays / hypernetwork-attention
  Official code for the paper "Attention as a Hypernetwork"
  ☆47Updated last year
• BryceZhuo / HybridNorm
  The official implementation of HybridNorm: Towards Stable and Efficient Transformer Training via Hybrid Normalization
  ☆18Updated 10 months ago
• ysngki / UMoE
  ☆20Updated 3 months ago
• formll / resolving-scaling-law-discrepancies
  ☆20Updated 2 months ago
• HelmholtzAI-FZJ / flex_gen
  ☆19Updated last year
• RobertCsordas / linear_layer_as_attention
  The official repository for our paper "The Dual Form of Neural Networks Revisited: Connecting Test Time Predictions to Training Patterns …
  ☆16Updated 7 months ago
• piotrpiekos / MoSA
  User-friendly implementation of the Mixture-of-Sparse-Attention (MoSA). MoSA selects distinct tokens for each head with expert choice rou…
  ☆28Updated 8 months ago
• tianyi-lab / C3PO
  [COLM 2025] "C3PO: Critical-Layer, Core-Expert, Collaborative Pathway Optimization for Test-Time Expert Re-Mixing"
  ☆19Updated 9 months ago
• minhoooo1 / CatMAE
  CatMAE
  ☆14Updated 2 years ago
• UCDvision / NOLA
  Code for NOLA, an implementation of "nola: Compressing LoRA using Linear Combination of Random Basis"
  ☆57Updated last year
• allenai / signal-and-noise
  Measuring the Signal to Noise Ratio in Language Model Evaluation
  ☆28Updated 5 months ago
• Shalev-Lifshitz / MultiAgentVerification
  Multi-Agent Verification: Scaling Test-Time Compute with Multiple Verifiers
  ☆26Updated 11 months ago
• locuslab / llava-token-compression
  ☆46Updated last year