Kevin Blin's repositories
CS4NLP_Project2022
Virtual Adversarial Training techniques for MC-TACO and CUAD
Generative-Spatial-Control
Research project for the seminar "Generative Visual Models".
BRJ
Materials for "Building a Robot Judge: Data Science for Decision-Making", Autumn 2022
CausalLLMs
Collection of experiments and utilities for testing causal reasoning in LLMs.
DeepPolyVerifier
Implementation of the DeepPoly neural network verifier.
evals
Evals is a framework for evaluating OpenAI models and an open-source registry of benchmarks.
FRL23-project
Benchmarking and improvement of ACNO-MDP’s
ParlAI
A framework for training and evaluating AI models on a variety of openly available dialogue datasets.
RANLP21-70
RANLP21 submission #70
smart-pytorch
PyTorch – SMART: Robust and Efficient Fine-Tuning for Pre-trained Natural Language Models
sheeprl
Distributed Reinforcement Learning accelerated by Lightning Fabric