lucidrains / spline-based-transformer
Implementation of the proposed Spline-Based Transformer from Disney Research
☆74Updated this week
Related projects ⓘ
Alternatives and complementary repositories for spline-based-transformer
- Explorations into improving ViTArc with Slot Attention☆36Updated 3 weeks ago
- Exploration into the Firefly algorithm in Pytorch☆35Updated last month
- RS-IMLE☆35Updated last month
- ☆21Updated 4 months ago
- Implementation of a framework for Gamengen in Pytorch☆90Updated last month
- Explorations into the proposal from the paper "Grokfast, Accelerated Grokking by Amplifying Slow Gradients"☆84Updated 2 months ago
- Exploration into the proposed "Self Reasoning Tokens" by Felipe Bonetto☆53Updated 5 months ago
- Implementation of a multimodal diffusion transformer in Pytorch☆97Updated 4 months ago
- Pytorch implementation of a simple way to enable (Stochastic) Frame Averaging for any network☆46Updated 3 months ago
- Implementation of the proposed MaskBit from Bytedance AI☆58Updated 2 weeks ago
- Exploring an idea where one forgets about efficiency and carries out attention across each edge of the nodes (tokens)☆43Updated last month
- Exploration into the Scaling Value Iteration Networks paper, from Schmidhuber's group☆36Updated last month
- A JAX implementation of the continuous time formulation of Consistency Models☆83Updated last year
- Explorations into the recently proposed Taylor Series Linear Attention☆89Updated 2 months ago
- Transformer implementation for "Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusion"☆55Updated 3 weeks ago
- Implementation of a Light Recurrent Unit in Pytorch☆46Updated last month
- Implementation of the Kalman Filtering Attention proposed in "Kalman Filtering Attention for User Behavior Modeling in CTR Prediction"☆57Updated last year
- ☆28Updated last week
- Implementation of the proposed Adam-atan2 from Google Deepmind in Pytorch☆94Updated 2 weeks ago
- Implementation of π₀, the robotic foundation model architecture proposed by Physical Intelligence☆81Updated this week
- ☆33Updated 6 months ago
- Some personal experiments around routing tokens to different autoregressive attention, akin to mixture-of-experts☆108Updated 3 weeks ago
- ☆31Updated 2 months ago
- ☆53Updated 9 months ago
- Experimental scripts for researching data adaptive learning rate scheduling.☆23Updated last year
- 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
- Collection of autoregressive model implementation☆66Updated last week
- Implementation of the general framework for AMIE, from the paper "Towards Conversational Diagnostic AI", out of Google Deepmind☆52Updated last month