simran-arora / focus
This repo contains code for the paper: "Can Foundation Models Help Us Achieve Perfect Secrecy?"
β24Updated last year
Related projects β
Alternatives and complementary repositories for focus
- Google Researchβ45Updated 2 years ago
- π° Computing the information content of trained neural networksβ21Updated 3 years ago
- Code for T-MARS data filteringβ35Updated last year
- My explorations into editing the knowledge and memories of an attention networkβ34Updated last year
- The repository contains code for Adaptive Data Optimizationβ18Updated 3 weeks ago
- β25Updated 11 months ago
- β21Updated 7 months ago
- Official code repo for paper "Great Memory, Shallow Reasoning: Limits of kNN-LMs"β18Updated 2 months ago
- Official repository for the paper "Approximating Two-Layer Feedforward Networks for Efficient Transformers"β36Updated 11 months ago
- We introduce EMMET and unify model editing with popular algorithms ROME and MEMIT.β12Updated 2 months ago
- RWKV model implementationβ38Updated last year
- β20Updated this week
- β28Updated last year
- Code for paper "Do Language Models Have Beliefs? Methods for Detecting, Updating, and Visualizing Model Beliefs"β28Updated 2 years ago
- Code repository for the public reproduction of the language modelling experiments on "MatFormer: Nested Transformer for Elastic Inferenceβ¦β18Updated 11 months ago
- Minimum Description Length probing for neural network representationsβ16Updated last week
- β46Updated last month
- β71Updated 6 months ago
- β26Updated last year
- Reference implementation for Reward-Augmented Decoding: Efficient Controlled Text Generation With a Unidirectional Reward Modelβ41Updated 9 months ago
- β9Updated 10 months ago
- SILO Language Models code repositoryβ80Updated 8 months ago
- β23Updated 3 months ago
- β13Updated 11 months ago
- Tree prompting: easy-to-use scikit-learn interface for improved prompting.β33Updated last year
- Code for PHATGOOSE introduced in "Learning to Route Among Specialized Experts for Zero-Shot Generalization"β78Updated 8 months ago
- Code for the paper "Data Feedback Loops: Model-driven Amplification of Dataset Biases"β15Updated 2 years ago
- Code and Data for the NAACL 24 paper: MacGyver: Are Large Language Models Creative Problem Solvers?β22Updated 7 months ago
- Few-shot Learning with Auxiliary Dataβ26Updated 11 months ago