Dingmin Wang

Working Memory Capacity of ChatGPT: An Empirical Study

2024 · 8 Zit. · Proceedings of the AAAI Conference on Artificial Intelligence

Train Less, Learn More: Adaptive Efficient Rollout Optimization for Group-Based Reinforcement Learning

2026 · 0 Zit. · arXiv (Cornell University)

BigCodeArena: Unveiling More Reliable Human Preferences in Code Generation via Execution

2025 · 0 Zit. · ArXiv.org

Train Less, Learn More: Adaptive Efficient Rollout Optimization for Group-Based Reinforcement Learning

2026 · 0 Zit. · Open MIND