LumenPallidium / jepa
Experiments in Joint Embedding Predictive Architectures (JEPAs).
☆36Updated 10 months ago
Related projects ⓘ
Alternatives and complementary repositories for jepa
- Pytorch implementation of a simple way to enable (Stochastic) Frame Averaging for any network☆48Updated 3 months ago
- Implementation of a framework for Gamengen in Pytorch☆90Updated 2 months ago
- Implementation of the proposed Spline-Based Transformer from Disney Research☆77Updated 2 weeks ago
- Exploration into the proposed "Self Reasoning Tokens" by Felipe Bonetto☆53Updated 6 months ago
- Some personal experiments around routing tokens to different autoregressive attention, akin to mixture-of-experts☆109Updated last month
- Exploring an idea where one forgets about efficiency and carries out attention across each edge of the nodes (tokens)☆43Updated last month
- Implementation of 🌻 Mirasol, SOTA Multimodal Autoregressive model out of Google Deepmind, in Pytorch☆88Updated 11 months ago
- Implementation of DreamerV3 in Pytorch☆34Updated this week
- Implementation of GateLoop Transformer in Pytorch and Jax☆86Updated 5 months ago
- Explorations into improving ViTArc with Slot Attention☆37Updated last month
- A practical implementation of GradNorm, Gradient Normalization for Adaptive Loss Balancing, in Pytorch☆77Updated 10 months ago
- Official Implementation of NeurIPS'23 Paper "Cross-Episodic Curriculum for Transformer Agents"☆31Updated last year
- Implementation of Infini-Transformer in Pytorch☆104Updated last month
- Implementation of the proposed Adam-atan2 from Google Deepmind in Pytorch☆94Updated this week
- A repository to house some personal attempts to beat some state-of-the-art for medical datasets☆97Updated last year
- Efficient World Models with Context-Aware Tokenization. ICML 2024☆84Updated 2 months ago
- Implementation of Agent Attention in Pytorch☆86Updated 4 months ago
- Implementation of the general framework for AMIE, from the paper "Towards Conversational Diagnostic AI", out of Google Deepmind☆53Updated 2 months ago
- Implementation of the Kalman Filtering Attention proposed in "Kalman Filtering Attention for User Behavior Modeling in CTR Prediction"☆57Updated last year
- Implementation of Recurrent Interface Network (RIN), for highly efficient generation of images and video without cascading networks, in P…☆194Updated 9 months ago
- Code and pretrained models for the paper: "MatMamba: A Matryoshka State Space Model"☆53Updated this week
- ☆48Updated 9 months ago
- Explorations into the proposal from the paper "Grokfast, Accelerated Grokking by Amplifying Slow Gradients"☆85Updated 2 months ago
- Implementation of an Attention layer where each head can attend to more than just one token, using coordinate descent to pick topk☆46Updated last year
- The official repository for HyperZ⋅Z⋅W Operator Connects Slow-Fast Networks for Full Context Interaction.☆31Updated 2 months ago
- Self contained pytorch implementation of a sinkhorn based router, for mixture of experts or otherwise☆31Updated 2 months ago
- Implementation of a multimodal diffusion transformer in Pytorch☆97Updated 5 months ago
- Explorations into the recently proposed Taylor Series Linear Attention☆90Updated 3 months ago
- Just some miscellaneous utility functions / decorators / modules related to Pytorch and Accelerate to help speed up implementation of new…☆119Updated 3 months ago