Search at the Cost of Sampling: Nearly-Instant Latent Space Bayesian Optimization
本文解决了虚拟筛选中贝叶斯优化计算开销大的问题，通过利用球形域上的线性模型加速了决策过程，提高了分子和图像生成基准性能。
0 citationsRead paper
Selected work
Representative Papers
Amortizing Scaling Law Construction Costs
本文提出一种高效构建缩放定律的框架，通过贝叶斯优化问题和计算预算逐步扩展的方法，大幅降低计算成本并准确拟合缩放定律。
0 citationsRead paper
Law of Large Numbers: Accuracy as Statistical Measure for AI Compliance and Competition
本文探讨了机器学习和法律界对'准确性'的不同理解和期望，分析了五个主要矛盾，并建议通过标准化和工具来解决这些差异。
0 citationsRead paper
Beyond Predictive Fairness: Quantifying Attribution Consistency Across Demographic Groups in Diabetic Retinopathy Screening
研究通过引入基于Jensen-Shannon散度的解释一致性分数(ECS)来量化糖尿病视网膜病变筛查中不同人群归因图的一致性，以补充预测公平性的评估。
0 citationsRead paper
RevengeBench: Reverse Engineering Code-Space Policies from Behavioral Experiments
This work investigates how to reverse-engineer executable decision code of an agent solely from its behavioral trajectories in games and examines how actively designed adversarial experiments can enhance reconstruction fidelity. To this end, we introduce RevengeBench, a benchmark comprising 75 Elo-calibrated CodeClash strategies across five environments, where customized behavioral probes are generated by observing interactions between target and opponent agents to reconstruct underlying code logic. We formalize strategy reversal as a tractable inverse problem in code space and incorporate a mechanism for controlled experimentation. Experiments across 12 large language models demonstrate that our approach significantly reduces initial behavioral divergence (by 34%–72%) and yields reconstructed strategies that exhibit competitive performance in downstream adversarial settings, particularly bolstering the counterplay capabilities of weaker models.
0 citationsRead paper
Recent publications
Latest Papers
Search at the Cost of Sampling: Nearly-Instant Latent Space Bayesian Optimization
本文解决了虚拟筛选中贝叶斯优化计算开销大的问题，通过利用球形域上的线性模型加速了决策过程，提高了分子和图像生成基准性能。
0 citationsRead paper
Amortizing Scaling Law Construction Costs
本文提出一种高效构建缩放定律的框架，通过贝叶斯优化问题和计算预算逐步扩展的方法，大幅降低计算成本并准确拟合缩放定律。
0 citationsRead paper
Law of Large Numbers: Accuracy as Statistical Measure for AI Compliance and Competition
本文探讨了机器学习和法律界对'准确性'的不同理解和期望，分析了五个主要矛盾，并建议通过标准化和工具来解决这些差异。
0 citationsRead paper
Beyond Predictive Fairness: Quantifying Attribution Consistency Across Demographic Groups in Diabetic Retinopathy Screening
研究通过引入基于Jensen-Shannon散度的解释一致性分数(ECS)来量化糖尿病视网膜病变筛查中不同人群归因图的一致性，以补充预测公平性的评估。
0 citationsRead paper
RevengeBench: Reverse Engineering Code-Space Policies from Behavioral Experiments
This work investigates how to reverse-engineer executable decision code of an agent solely from its behavioral trajectories in games and examines how actively designed adversarial experiments can enhance reconstruction fidelity. To this end, we introduce RevengeBench, a benchmark comprising 75 Elo-calibrated CodeClash strategies across five environments, where customized behavioral probes are generated by observing interactions between target and opponent agents to reconstruct underlying code logic. We formalize strategy reversal as a tractable inverse problem in code space and incorporate a mechanism for controlled experimentation. Experiments across 12 large language models demonstrate that our approach significantly reduces initial behavioral divergence (by 34%–72%) and yields reconstructed strategies that exhibit competitive performance in downstream adversarial settings, particularly bolstering the counterplay capabilities of weaker models.
0 citationsRead paper