Songjun Tu

3 papers · 2025–2026 · 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 📈 Trend Setter

Venues

AAAI (1) CVPR (1) ICLR (1)

Top co-authors

Qichao Zhang (3) Ke Chen (3) Jingbo Sun (3) Dongbin Zhao (3) Haoran Li (2) Yupeng Zheng (1) Yaran Chen (1) Xin Liu (1) Jia Liu (1) Xing Fang (1)

Research topics

Reinforcement Learning (3) Methods (3) Artificial Intelligence (2) Core AI (2) Deep Learning (1) Machine Learning (1) Learning Paradigms (1) Learning Types · Deep Learning (1) Learning Types · Machine Learning (1)

Keywords

unsupervised reinforcement learning (2) zero-shot generalization (2) offline reinforcement learning (1) trajectory modeling (1) skill discovery (1) reward model (1) decision transformer (1) preference-based learning (1) classifier-free guidance (1) intrinsic reward (1) successor representation (1) preference-based rl (1) trajectory return (1) skill-conditioned policy (1) forward-backward representation (1) representation learning (1) successor measure (1) reward modeling (1)

Papers

Saliency-Guided Representation with Consistency Policy Learning for Visual Unsupervised Reinforcement Learning CVPR 2026 In-Dataset Trajectory Return Regularization for Offline Preference-based Reinforcement Learning AAAI 2025 Unsupervised Zero-Shot Reinforcement Learning via Dual-Value Forward-Backward Representation ICLR 2025