LumenPallidium / jepaLinks
Experiments in Joint Embedding Predictive Architectures (JEPAs).
☆40Updated last year
Alternatives and similar repositories for jepa
Users that are interested in jepa are comparing it to the libraries listed below
Sorting:
- Pytorch implementation of a simple way to enable (Stochastic) Frame Averaging for any network☆50Updated 11 months ago
- Explorations into the proposal from the paper "Grokfast, Accelerated Grokking by Amplifying Slow Gradients"☆101Updated 6 months ago
- σ-GPT: A New Approach to Autoregressive Models☆65Updated 11 months ago
- Pytorch implementation of Evolutionary Policy Optimization, from Wang et al. of the Robotics Institute at Carnegie Mellon University☆97Updated last week
- Implementation of Gradient Agreement Filtering, from Chaubard et al. of Stanford, but for single machine microbatches, in Pytorch☆25Updated 5 months ago
- Efficiently discovering algorithms via LLMs with evolutionary search and reinforcement learning.☆103Updated this week
- ☆81Updated last year
- Swarming algorithms like PSO, Ant Colony, Sakana, and more in PyTorch 😊☆126Updated last month
- Exploration into the proposed "Self Reasoning Tokens" by Felipe Bonetto☆56Updated last year
- Explorations into improving ViTArc with Slot Attention☆42Updated 9 months ago
- Code and pretrained models for the paper: "MatMamba: A Matryoshka State Space Model"☆59Updated 7 months ago
- Explorations into the recently proposed Taylor Series Linear Attention☆99Updated 11 months ago
- Implementation of 🌻 Mirasol, SOTA Multimodal Autoregressive model out of Google Deepmind, in Pytorch☆89Updated last year
- A practical implementation of GradNorm, Gradient Normalization for Adaptive Loss Balancing, in Pytorch☆99Updated last year
- Implementation of Mind Evolution, Evolving Deeper LLM Thinking, from Deepmind☆55Updated last month
- Just some miscellaneous utility functions / decorators / modules related to Pytorch and Accelerate to help speed up implementation of new…☆124Updated 11 months ago
- The official repository for HyperZ⋅Z⋅W Operator Connects Slow-Fast Networks for Full Context Interaction.☆38Updated 3 months ago
- Efficient World Models with Context-Aware Tokenization. ICML 2024☆105Updated 9 months ago
- Generative cellular automaton-like learning environments for RL.☆19Updated 5 months ago
- PyTorch Code for Energy-Based Transformers paper -- generalizable reasoning and scalable learning☆298Updated last week
- My take on Flow Matching☆66Updated 6 months ago
- Implementation of the Llama architecture with RLHF + Q-learning☆165Updated 5 months ago
- Implementation of the proposed Spline-Based Transformer from Disney Research☆101Updated 8 months ago
- Implementation of GateLoop Transformer in Pytorch and Jax☆89Updated last year
- FID computation in Jax/Flax.☆28Updated last year
- The Gaussian Histogram Loss (HL-Gauss) proposed by Imani et al. with a few convenient wrappers for regression, in Pytorch☆65Updated last month
- Some personal experiments around routing tokens to different autoregressive attention, akin to mixture-of-experts☆120Updated 9 months ago
- Explorations into whether a transformer with RL can direct a genetic algorithm to converge faster☆70Updated 2 months ago
- Exploration into the Firefly algorithm in Pytorch☆40Updated 5 months ago
- Implementation of Infini-Transformer in Pytorch☆111Updated 6 months ago