Shao-Hua Sun

26 papers · 2018–2026 · 8 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 ↓

+8 more ↓

🗺️ Taxonomy Completionist (43) 🏃 Academic Marathon · Sprint 🌍 Conference Polyglot · Silver 🌉 Interdisciplinary Bridge · Silver 🐣 Hot Topic Early Bird

🧬 Topic Evolution 👑 Triple Crown 🚀 Conference Pioneer 🔥 Unstoppable · Bronze ⚡ Prolific Year · Productive 💎 Century Club · Bronze 🌈 Renaissance Researcher (6) 🗃️ Keyword Collector (116)

Venues

ICLR (8) NeurIPS (7) ICML (4) EACL (3) CoRL (1) CVPR (1) ECCV (1) EMNLP (1)

Top co-authors

Joseph J. Lim (6) Chun-Mao Lai (3) Hung-yi Lee (3) Ping-Chun Hsieh (3) Shang-Fu Chen (2) Karl Pertsch (2) Wei Hung (2) Jesse Zhang (2) Li-Chun Lu (2) En-Pei Hu (2)

Research topics

Artificial Intelligence (15) Machine Learning (14) Core AI (13) Reinforcement Learning (11) Methods (11) Deep Learning (9) Learning Types · Machine Learning (7) Application Areas (5) Learning Types · Deep Learning (5) Learning Paradigms (4) Models (4) Natural Language Processing (3) Robotics (3) Applications (3) Capabilities (3)

Keywords

diffusion model (4) imitation learning (4) reinforcement learning (3) adversarial learning (3) program synthesis (3) deep reinforcement learning (2) policy optimization (2) sample efficiency (2) large language model (2) programmatic reinforcement learning (2) continuous control (2) hierarchical reinforcement learning (2) action constraint (2) reward function (2) program embedding (2) multimodal learning (1) knowledge distillation (1) direct preference optimization (1) multi-task learning (1) image-to-image translation (1)

Papers

Adaptive Helpfulness–Harmlessness Alignment with Preference Vectors EACL 2026 BILLY: Steering Large Language Models via Merging Persona Vectors for Creative Generation EACL 2026 Rethinking Creativity Evaluation: A Critical Analysis of Existing Creativity Evaluations EACL 2026 Action-Constrained Imitation Learning ICML 2025 Efficient Action-Constrained Reinforcement Learning via Acceptance-Rejection Method and Augmented MDPs ICLR 2025 HERO: Human-Feedback Efficient Reinforcement Learning for Online Diffusion Model Finetuning ICLR 2025 QMP: Q-switch Mixture of Policies for Multi-Task Behavior Sharing ICLR 2025 Synthesizing Programmatic Reinforcement Learning Policies with Large Language Model Guided Search ICLR 2025 Diffusion Imitation from Observation NeurIPS 2024 Diffusion Model-Augmented Behavioral Cloning ICML 2024 Diffusion-Reward Adversarial Imitation Learning NeurIPS 2024 Hierarchical Programmatic Option Framework NeurIPS 2024 Integrating Planning and Deep Reinforcement Learning via Automatic Induction of Task Substructures ICLR 2024 Learning to Act from Actionless Videos through Dense Correspondences ICLR 2024 REBORN: Reinforcement-Learned Boundary Segmentation with Iterative Training for Unsupervised ASR NeurIPS 2024 Bootstrap Your Own Skills: Learning to Solve New Tasks with Large Language Model Guidance CoRL 2023 Hierarchical Programmatic Reinforcement Learning via Learning to Compose Programs ICML 2023 Location-Aware Visual Question Generation with Lightweight Models EMNLP 2023 Skill-based Meta-Reinforcement Learning ICLR 2022 Generalizable Imitation Learning from Observation via Inferring Goal Proximity NeurIPS 2021 Learning to Synthesize Programs as Interpretable and Generalizable Policies NeurIPS 2021 Program Guided Agent ICLR 2020 Feedback Adversarial Learning: Spatial Feedback for Improving Generative Adversarial Networks CVPR 2019 Multimodal Model-Agnostic Meta-Learning via Task-Aware Modulation NeurIPS 2019 Multi-view to Novel view: Synthesizing novel views with Self-Learned Confidence ECCV 2018 Neural Program Synthesis from Diverse Demonstration Videos ICML 2018