Jiajun Fan

4 papers · 2022–2025 · 3 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Bronze 🌉 Interdisciplinary Bridge · Bronze 🐣 Hot Topic Early Bird

Venues

ICLR (2) ICML (1) NeurIPS (1)

Top co-authors

Hao Wang (2) Yuzheng Zhuang (1) Weiming Liu (1) Yuecheng Liu (1) Jiangcheng Zhu (1) Zhenhua Dong (1) Haoxuan Li (1) Ge Liu (1) Zhichao Chen (1) Quanyu Dai (1)

Research topics

Machine Learning (4) Reinforcement Learning (2) Methods (2) Optimization & Theory (2) Artificial Intelligence (1) Deep Learning (1) Application Areas (1) Applications (1) Core AI (1) Learning Types (1) Models (1)

Keywords

sample efficiency (2) causal inference (1) deep reinforcement learning (1) reinforcement learning (1) domain adaptation (1) optimal transport (1) flow matching (1) exploration exploitation (1) policy iteration (1) generative model (1) multi-armed bandit (1) treatment effect estimation (1) behavior policy (1) data distribution (1) actor-critic method (1) counterfactual regression (1) fine tuning (1) behavior control (1) wasserstein distance (1) treatment selection bia (1)

Papers

Online Reward-Weighted Fine-Tuning of Flow Matching with Wasserstein Regularization ICLR 2025 Learnable Behavior Control: Breaking Atari Human World Records via Sample-Efficient Behavior Selection ICLR 2023 Optimal Transport for Treatment Effect Estimation NeurIPS 2023 Generalized Data Distribution Iteration ICML 2022