태그
자연어처리,
nlp,
skip-gram,
CBOW,
RLHF,
PPO,
huggingface,
LSTM,
GRU,
bi-directional RNN,
over-fitting,
rnn,
word vector,
skip gram,
DPO 논문리뷰,
Direct Preference Optimization,
DPO,
reward model,
feedback reward,
LLM 피드백 활용,
LLM feedback,
huggingface서빙,
LLM서빙,
vLLM,
TaskMatrix.AI,
Proximal Policy Optimization,
TRL,
Colossal AI,
DeepLift,
captum,
2022 CIKM,
2022 KDD,
Meta AI,
Multimodal Shopping Model,
e-CLIP,
commerce MM,
Policy optimization,
Model-based,
Model-free,
ChatGPT,
Explainable AI,
intergrated gradient,
네이버 입사,
네이버 입사 후기,
AI개발직군,
AI 개발자 취업 후기,
네이버 경력 이직 후기,
paper review,
경력이직,
XAI,
Multimodal,
off-policy,
on-policy,
Q-learning,
RL,
pytorch,
논문리뷰,
explained,
네이버 쇼핑,
seq2seq,
Depp RNN,
Deep RNN,
PTX,
Batch Normalization,
augmentation,
logistic regression,
sentiment,
감정 분석,
주성분분석,
work2vec,
neural network,
softmax,
cs224n,
Hierarchical Softmax,
강화학습,
reinforcement learning,
negative sampling,
information theory,
cross entropy,
objective function,
cooccurance,
svd,
word space,
one hot,
Shopping,
PCA,
Word2Vec,
비전공자,
Alignment,
BN,
glove,
AI,
Director,
후기,
Microsoft,
네이버,