Wanli Ouyang

发表论文 299 篇 · 总被引 10524 次 · h-index 47

代表论文

• The Entropy Mechanism of Reinforcement Learning for Reasoning Language Models (2025 · arXiv.org · 被引 404)
• Attention Reallocation: Towards Zero-cost and Controllable Hallucination Mitigation of MLLMs (2025 · International Journal of Computer Vision · 被引 27)
• CoMAS: Co-Evolving Multi-Agent Systems via Interaction Rewards (2025 · arXiv.org · 被引 26)
• Do We Truly Need So Many Samples? Multi-LLM Repeated Sampling Efficiently Scales Test-Time Compute (2025 · AAAI Conference on Artificial Intelligence · 被引 21)
• AdaBrain-Bench: Benchmarking Brain Foundation Models for Brain-Computer Interface Applications (2025 · arXiv.org · 被引 17)
• Dolphin: Moving Towards Closed-loop Auto-research through Thinking, Practice, and Feedback (2025 · Annual Meeting of the Association for Computational Linguistics · 被引 14)