Seokin Seo
7 papers · 2018–2025 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+4 more ↓ Show less ↑
π Cross-Pollinator (15) π Academic Marathon (7) π£ Hot Topic Early Bird π Conference Polyglot (4) π Renaissance Researcher (5)
π
Interdisciplinary Bridge
πΊοΈ
Taxonomy Completionist
(16)
π₯
Unstoppable
(5)
π
Trend Setter
Conferences
NIPS (3)
ICLR (2)
ICML (1)
NAACL (1)
Top co-authors
Keywords
imitation learning
(2)
reinforcement learning
(1)
sample efficiency
(1)
adversarial learning
(1)
bayesian inference
(1)
direct preference optimization
(1)
policy learning
(1)
ai safety
(1)
behavior cloning
(1)
covariate shift
(1)
partial observability
(1)
distributionally robust
(1)
offline learning
(1)
stationary distribution
(1)
state space model
(1)
latent representation
(1)
language model
(1)
generative adversarial network
(1)
behavioral cloning
(1)
missing datum
(1)
Papers
Goal-Conditioned DPO: Prioritizing Safety in Misaligned Instructions
NAACL 2025
Mitigating Covariate Shift in Behavioral Cloning via Robust Stationary Distribution Correction
NIPS 2024
Information-Theoretic State Space Model for Multi-View Reinforcement Learning
ICML 2023
Regularized Behavior Cloning for Blocking the Leakage of Past Action Information
NIPS 2023
DemoDICE: Offline Imitation Learning with Supplementary Imperfect Demonstrations
ICLR 2022
Monte-Carlo Planning and Learning with Language Action Value Estimates
ICLR 2021
A Bayesian Approach to Generative Adversarial Imitation Learning
NIPS 2018