Anthony GX-Chen

发表论文 10 篇 · 总被引 57 次 · h-index 3

代表论文

• KL-Regularized Reinforcement Learning is Designed to Mode Collapse (2025 · arXiv.org · 被引 29)
• Light-weight probing of unsupervised representations for Reinforcement Learning (2022 · RLJ · 被引 22)
• Language Agents Mirror Human Causal Reasoning Biases. How Can We Help Them Think Like Scientists? (2025 · arXiv.org · 被引 8)
• Sample-efficient generative molecular design using memory manipulation (2026 · Nature Machine Intelligence · 被引 7)
• Failing to Falsify: Evaluating and Mitigating Confirmation Bias in Language Models (2026 · arXiv.org · 被引 5)
• Efficient Exploration and Discriminative World Model Learning with an Object-Centric Abstraction (2024 · International Conference on Learning Representations · 被引 3)