akarshkumar0101 / ferLinks
Code for the Fractured Entangled Representation Hypothesis position paper!
☆204Updated last week
Alternatives and similar repositories for fer
Users that are interested in fer are comparing it to the libraries listed below
Sorting:
- Diffusion on syntax trees for program synthesis☆474Updated last year
- A package for defining deep learning models using categorical algebraic expressions.☆61Updated last year
- Cellular Automata Accelerated in JAX (Oral at ICLR 2025)☆230Updated last week
- Brain-like variational inference☆57Updated 5 months ago
- ☆198Updated 3 months ago
- Reasoning Computers. Lambda Calculus, Fully Differentiable. Also Neural Stacks, Queues, Arrays, Lists, Trees, and Latches.☆280Updated last year
- Getting crystal-like representations with harmonic loss☆192Updated 7 months ago
- The history files when recording human interaction while solving ARC tasks☆118Updated 2 weeks ago
- Latent Program Network (from the "Searching Latent Program Spaces" paper)☆103Updated last month
- ☆62Updated 8 months ago
- explore token trajectory trees on instruct and base models☆148Updated 5 months ago
- A character-level language diffusion model trained on Tiny Shakespeare☆330Updated this week
- This repo contains the source code for the paper "Evolution Strategies at Scale: LLM Fine-Tuning Beyond Reinforcement Learning"☆252Updated last week
- Automated Capability Discovery via Foundation Model Self-Exploration☆65Updated 9 months ago
- ☆45Updated 5 months ago
- Code to train and evaluate Neural Attention Memory Models to obtain universally-applicable memory systems for transformers.☆327Updated last year
- Repository to create traveling waves integrate special information through time☆56Updated 3 months ago
- lossily compress representation vectors using product quantization☆59Updated 2 weeks ago
- ☆143Updated 2 months ago
- LLMs represent numbers on a helix and manipulate that helix to do addition.☆27Updated 9 months ago
- ☆155Updated 3 months ago
- ☆107Updated 11 months ago
- ☆172Updated 4 months ago
- The boundary of neural network trainability is fractal☆217Updated last year
- σ-GPT: A New Approach to Autoregressive Models☆68Updated last year
- Gradient descent is cool and all, but what if we could delete it?☆104Updated 2 months ago
- Pytorch script hot swap: Change code without unloading your LLM from VRAM☆124Updated 6 months ago
- Materials for ConceptARC paper☆105Updated last year
- ☆28Updated last year
- ☆237Updated 8 months ago