ekinakyurek / marc
Public repository for "The Surprising Effectiveness of Test-Time Training for Abstract Reasoning"
☆92Updated this week
Related projects ⓘ
Alternatives and complementary repositories for marc
- code for training & evaluating Contextual Document Embedding models☆93Updated this week
- look how they massacred my boy☆54Updated 3 weeks ago
- Repository for the paper Stream of Search: Learning to Search in Language☆84Updated 3 months ago
- Like ARC, but code to generate visual puzzles. 1D puzzles first.☆15Updated 2 months ago
- ☆100Updated 3 months ago
- ☆36Updated 3 months ago
- Aidan Bench attempts to measure <big_model_smell> in LLMs.☆90Updated this week
- Simple Transformer in Jax☆115Updated 4 months ago
- The history files when recording human interaction while solving ARC tasks☆94Updated this week
- Dataset and benchmark for assessing LLMs in translating natural language descriptions of planning problems into PDDL☆43Updated 3 weeks ago
- Experiments for efforts to train a new and improved t5☆76Updated 6 months ago
- Code to reproduce "Transformers Can Do Arithmetic with the Right Embeddings", McLeish et al (NeurIPS 2024)☆177Updated 5 months ago
- Archon provides a modular framework for combining different inference-time techniques and LMs with just a JSON config file.☆119Updated 3 weeks ago
- ☆74Updated 2 weeks ago
- Evaluation of neuro-symbolic engines☆33Updated 3 months ago
- Functional Benchmarks and the Reasoning Gap☆78Updated last month
- Tree Attention: Topology-aware Decoding for Long-Context Attention on GPU clusters☆104Updated last month
- An introduction to LLM Sampling☆62Updated this week
- ☆20Updated last week
- Sparse and discrete interpretability tool for neural networks☆54Updated 9 months ago
- Scaling is a distributed training library and installable dependency designed to scale up neural networks, with a dedicated module for tr…☆46Updated 2 weeks ago
- ☆105Updated this week
- The simplest, fastest repository for training/finetuning medium-sized GPTs.☆84Updated 2 weeks ago
- Implementation of the paper: "AssistantBench: Can Web Agents Solve Realistic and Time-Consuming Tasks?"☆38Updated 3 weeks ago
- ☆94Updated last month
- Learning Universal Predictors☆69Updated 3 months ago
- A MAD laboratory to improve AI architecture designs 🧪☆95Updated 6 months ago
- ☆68Updated 2 months ago
- ☆48Updated last year
- Mixing Language Models with Self-Verification and Meta-Verification☆97Updated last year