Princeton-RL / CRTRLinks
Official code for the paper "Contrastive Representations for Temporal Reasoning".
☆31Updated last week
Alternatives and similar repositories for CRTR
Users that are interested in CRTR are comparing it to the libraries listed below
Sorting:
- H-Net Dynamic Hierarchical Architecture☆79Updated last month
- σ-GPT: A New Approach to Autoregressive Models☆67Updated last year
- A simple, performant and scalable JAX-based world modeling codebase☆70Updated last week
- ☆32Updated last year
- Exploration into the Firefly algorithm in Pytorch☆40Updated 6 months ago
- Efficiently discovering algorithms via LLMs with evolutionary search and reinforcement learning.☆106Updated last month
- 📄Small Batch Size Training for Language Models☆57Updated last week
- Code for "Goal-Guided Neural Cellular Automata: Learning to Control Self-Organising Systems"☆56Updated 3 years ago
- The Automated LLM Speedrunning Benchmark measures how well LLM agents can reproduce previous innovations and discover new ones in languag…☆96Updated last month
- Getting crystal-like representations with harmonic loss☆194Updated 5 months ago
- LLMs represent numbers on a helix and manipulate that helix to do addition.☆25Updated 7 months ago
- ☆44Updated last month
- Implementations of attention with the softpick function, naive and FlashAttention-2☆83Updated 4 months ago
- ☆102Updated last month
- The Gaussian Histogram Loss (HL-Gauss) proposed by Imani et al. with a few convenient wrappers for regression, in Pytorch☆65Updated 3 weeks ago
- Mobile Viewer for W&B, built on top of Flutter.☆36Updated last year
- Efficient World Models with Context-Aware Tokenization. ICML 2024☆107Updated 11 months ago
- Focused on fast experimentation and simplicity☆75Updated 8 months ago
- ☆53Updated last year
- train with kittens!☆62Updated 10 months ago
- Implementation of the proposed Spline-Based Transformer from Disney Research☆103Updated 9 months ago
- Minimal (400 LOC) implementation Maximum (multi-node, FSDP) GPT training☆131Updated last year
- Implementation of Gradient Agreement Filtering, from Chaubard et al. of Stanford, but for single machine microbatches, in Pytorch☆25Updated 7 months ago
- Modular, scalable library to train ML models☆156Updated last week
- Jax like function transformation engine but micro, microjax☆33Updated 10 months ago
- LLM training in simple, raw C/CUDA☆18Updated last year
- ☆100Updated last month
- Code for the paper "Function-Space Learning Rates"☆23Updated 3 months ago
- Implementation of a framework for Genie2 in Pytorch☆151Updated 7 months ago
- realtime latent world model inference demo☆47Updated 9 months ago