Pinned Repositories
ddpo-overopt
ParallelTreeSampling.jl
MCTS-based Parallel Sampling for Risk Estimation
t2i-ft
Fine-tuning of text-to-image models
TextNorm
[ICLR 2024] Confidence-aware Reward Optimization for Fine-tuning Text-to-Image Models
kykim0's Repositories
kykim0/TextNorm
[ICLR 2024] Confidence-aware Reward Optimization for Fine-tuning Text-to-Image Models
kykim0/ParallelTreeSampling.jl
MCTS-based Parallel Sampling for Risk Estimation
kykim0/ddpo-overopt
kykim0/t2i-ft
Fine-tuning of text-to-image models
kykim0/alignment-handbook
Robust recipes to align language models with human and AI preferences
kykim0/asst1
Stanford CS149 -- Assignment 1
kykim0/asst2
Stanford CS149 -- Assignment 2
kykim0/asst3
Stanford CS149 -- Assignment 3
kykim0/asst4
Stanford CS149 - Assignment 4
kykim0/AutonomousRiskFramework.jl
Framework for autonomous vehicle risk assessment
kykim0/BayesianDeepLearning-Survey
Bayesian Deep Learning: A Survey
kykim0/carla
Open-source simulator for autonomous driving research.
kykim0/configs
kykim0/convex-optimization-for-all.github.io
모두를 위한 컨백스 최적화
kykim0/betty
Betty: an automatic differentiation library for generalized meta-learning and multilevel optimization
kykim0/FastChat
An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.
kykim0/GaussianProcesses.jl
A Julia package for Gaussian Processes
kykim0/gemm_extra_credit
CS149 Extra credit: See how fast you can implement GEMM
kykim0/generative_agents
Generative Agents: Interactive Simulacra of Human Behavior
kykim0/keras
Deep Learning for humans
kykim0/kykim0.github.io
kykim0/LESS
[ICML 2024] LESS: Selecting Influential Data for Targeted Instruction Tuning
kykim0/margin-matching-pref-opt
kykim0/meta-learning-curiosity-algorithms
kykim0/nanoGPT
The simplest, fastest repository for training/finetuning medium-sized GPTs.
kykim0/POMDPGym.jl
kykim0/Probabilistic-Programming-and-Bayesian-Methods-for-Hackers
aka "Bayesian Methods for Hackers": An introduction to Bayesian methods + probabilistic programming with a computation/understanding-first, mathematics-second point of view. All in pure Python ;)
kykim0/tinkering
kykim0/Tinkering.jl
kykim0/trl
Train transformer language models with reinforcement learning.