Wan Ju Kang

4 papers · 2019–2025 · 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 🏃 Academic Marathon · Sprint 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (11)

Venues

ACL (2) ICLR (1) ICML (1)

Top co-authors

Daewoo Kim (2) James Thorne (2) Kyunghwan Son (2) Yung Yi (2) David Hostallero (1) Sangryul Kim (1) Eunki Kim (1) Taeyoung Lee (1) Sangwoo Moon (1) Ki Hoon Kwak (1)

Research topics

Artificial Intelligence (3) Core AI (3) Machine Learning (2) Reinforcement Learning (2) Learning Types (2) Methods (2) Computer Vision (1) Applications (1) Core Methods (1) Domain-Specific (1)

Keywords

multi-agent reinforcement learning (2) contrastive learning (1) preference learning (1) information retrieval (1) action selection (1) vision-language model (1) value factorization (1) cooperative multi-agent (1) user feedback (1) centralized training decentralized execution (1) preference data (1) sentence embedding (1) diagram description (1) latent supervision (1) joint action-value function (1) communication scheduling (1) large language model (1) blind low vision (1) argument retrieval (1) message encoding (1)

Papers

Sightation Counts: Leveraging Sighted User Feedback in Building a BLV-aligned Dataset of Diagram Descriptions ACL 2025 XFACT Team0331 at PerspectiveArg2024: Sampling from Bounded Clusters for Diverse Relevant Argument Retrieval ACL 2024 Learning to Schedule Communication in Multi-agent Reinforcement Learning ICLR 2019 QTRAN: Learning to Factorize with Transformation for Cooperative Multi-Agent Reinforcement Learning ICML 2019