Alternatives and similar repositories for autoregressive_diffusion

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

• alexiglad / EBT
  PyTorch Code for Energy-Based Transformers paper -- generalizable reasoning and scalable learning
  ☆224Updated last week
• KindXiaoming / grow-crystals
  Getting crystal-like representations with harmonic loss
  ☆192Updated 3 months ago
• LucasPrietoAl / grokking-at-the-edge-of-numerical-stability
  ☆98Updated 5 months ago
• akarshkumar0101 / fer
  Code for the Fractured Entangled Representation Hypothesis position paper!
  ☆135Updated last month
• facebookresearch / capi
  Code and weights for the paper "Cluster and Predict Latents Patches for Improved Masked Image Modeling"
  ☆112Updated 3 months ago
• idiap / sigma-gpt
  σ-GPT: A New Approach to Autoregressive Models
  ☆65Updated 11 months ago
• dome272 / Flow-Matching
  My take on Flow Matching
  ☆66Updated 6 months ago
• apoorvkh / academic-pretraining
  $100K or 100 Days: Trade-offs when Pre-Training with Academic Resources
  ☆140Updated last month
• cloneofsimo / scaling-guide
  WIP
  ☆93Updated 11 months ago
• zaydzuhri / softpick-attention
  Implementations of attention with the softpick function, naive and FlashAttention-2
  ☆80Updated 2 months ago
• fal-ai / diffusion-speedrun
  Focused on fast experimentation and simplicity
  ☆76Updated 6 months ago
• apple / ml-act
  ☆49Updated 7 months ago
• dvruette / gidd
  Code accompanying the paper "Generalized Interpolating Discrete Diffusion"
  ☆94Updated last month
• lucidrains / grokfast-pytorch
  Explorations into the proposal from the paper "Grokfast, Accelerated Grokking by Amplifying Slow Gradients"
  ☆101Updated 6 months ago
• Sohl-Dickstein / fractal
  The boundary of neural network trainability is fractal
  ☆210Updated last year
• lucidrains / transformer-directed-evolution
  Explorations into whether a transformer with RL can direct a genetic algorithm to converge faster
  ☆70Updated last month
• iliao2345 / CompressARC
  ☆167Updated 3 months ago
• cloneofsimo / min-max-gpt
  Minimal (400 LOC) implementation Maximum (multi-node, FSDP) GPT training
  ☆129Updated last year
• fal-ai-community / alphabet-dataset
  Synthetic Alphabet Dataset
  ☆19Updated 3 months ago
• riverstone496 / awesome-second-order-optimization
  ☆27Updated last year
• mcleish7 / arithmetic
  Code to reproduce "Transformers Can Do Arithmetic with the Right Embeddings", McLeish et al (NeurIPS 2024)
  ☆190Updated last year
• KellerJordan / cifar10-airbench
  CIFAR-10 speedruns: 94% in 2.6 seconds and 96% in 27 seconds
  ☆263Updated 4 months ago
• clement-bonnet / lpn
  Latent Program Network (from the "Searching Latent Program Spaces" paper)
  ☆91Updated 4 months ago
• cloneofsimo / zeroshampoo
  ☆34Updated 10 months ago
• ShadeAlsha / ICon
  ICLR 2025 - official implementation for "I-Con: A Unifying Framework for Representation Learning"
  ☆101Updated 3 weeks ago
• cloneofsimo / min-fsdp
  ☆80Updated last year
• subhashk01 / LLM-addition
  LLMs represent numbers on a helix and manipulate that helix to do addition.
  ☆25Updated 5 months ago
• ethansmith2000 / fsdp_optimizers
  supporting pytorch FSDP for optimizers
  ☆82Updated 7 months ago
• lucidrains / GAF-microbatch-pytorch
  Implementation of Gradient Agreement Filtering, from Chaubard et al. of Stanford, but for single machine microbatches, in Pytorch
  ☆25Updated 5 months ago
• AllanYangZhou / universal_neural_functional
  ☆51Updated last year