Awesome Recommender Systems
📄
Papers
🧭
Topics
🔥
Trending
🗺️
Map
🏆
Leaderboards
🎓
Learn
🤖
Ask AI
⋯
More
👥
Authors
📚
Reading Packs
📊
Datasets
🛠️
Tools
📰
News
📝
Blogs
✉️
Newsletter
🎯
Research Radar
🔖
Saved
+ Add Paper
☾
☀
← authors
·
overview
Loading author…
🤖
Ask AI
Xiaohan Wang — most-cited papers & profile · Recommender Systems
← authors
·
overview
Xiaohan Wang
41
papers ·
5951
citations ·
0
h-index
Chinese Academy of Sciences · Guangzhou Institute of Energy Conversion · East China Normal University
Google Scholar ↗
Semantic Scholar ↗
OpenAlex ↗
Most-cited papers
DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
2025 · 5456 citations
DeepSeek-V3 Technical Report
2024 · 248 citations
DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model
2024 · 105 citations
Multi-robot Cooperative Pursuit via Potential Field-Enhanced Reinforcement Learning
2022 · 46 citations
Multi-robot Cooperative Pursuit via Potential Field-Enhanced Reinforcement Learning
2022 · 46 citations
VideoAgent: Long-form Video Understanding with Large Language Model as Agent
2024 · 42 citations
DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models
2025 · 5 citations
Scalable Video Object Segmentation with Identification Mechanism
2022 · 3 citations
Joint Training of Multi-Token Prediction in Reinforcement Learning via Optimal Coefficient Calibration
2026
Contextual Rollout Bandits for Reinforcement Learning with Verifiable Rewards
2026
TAPO: Tool-Aware Policy Optimization via Credit Transfer for Multimodal Search Agents
2026
When Self-Belief Misleads: Active Label Acquisition for Reinforcement Learning with Verifiable Rewards
2026
On the Hidden Costs of Counterfactual Knowledge Training in LLM Unlearning
2026
DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence
2026
CDRRM: Contrast-Driven Rubric Generation for Reliable and Interpretable Reward Modeling
2026
Topics
Training Techniques
cs.AI
Evaluation
cs.LG
Multi-Agent
Reinforcement Learning
In-Context Learning
Tool Use
Benchmarks
Fine-Tuning