Safe reinforcement learning (RL) requires the agent to finish a given task while obeying specific constraints. Giving constraints in natural language form has great potential for practical scenarios due to its flexible transfer capability and accessibility. Previous safe RL methods with natural language constraints typically need to design cost functions manually for each constraint, which requires domain expertise and lacks flexibility. In this paper, we harness the dual role of text in this task, using it not only to provide constraint but also as a training signal. We introduce the Trajectory-level Textual Constraints Translator (TTCT) to replace the manually designed cost function. Our empirical results demonstrate that TTCT effectively comprehends textual constraint and trajectory, and the policies trained by TTCT can achieve a lower violation rate than the standard cost function. Extra studies are conducted to demonstrate that the TTCT has zero-shot transfer capability to adapt to constraint-shift environments.

We consider the problem of how a trusted, but computationally bounded agent (a 'verifier') can learn to interact with one or more powerful but untrusted agents ('provers') in order to solve a given task. More specifically, we study the case in which agents are represented using neural networks and refer to solutions of this problem as neural interactive proofs. First we introduce a unifying framework based on prover-verifier games, which generalises previously proposed interaction protocols. We then describe several new protocols for generating neural interactive proofs, and provide a theoretical comparison of both new and existing approaches. Finally, we support this theory with experiments in two domains: a toy graph isomorphism problem that illustrates the key ideas, and a code validation task using large language models. In so doing, we aim to create a foundation for future work on neural interactive proofs and their application in building safer AI systems.

The advancement of novel combinatorial CRISPR screening technologies enables the identification of synergistic gene combinations on a large scale. This is crucial for developing novel and effective combination therapies, but the combinatorial space makes exhaustive experimentation infeasible. We introduce NAIAD, an active learning framework that efficiently discovers optimal gene pairs capable of driving cells toward desired cellular phenotypes. NAIAD leverages single-gene perturbation effects and adaptive gene embeddings that scale with the training data size, mitigating overfitting in small-sample learning while capturing complex gene interactions as more data is collected. Evaluated on four CRISPR combinatorial perturbation datasets totaling over 350,000 genetic interactions, NAIAD, trained on small datasets, outperforms existing models by up to 40\% relative to the second-best. NAIAD's recommendation system prioritizes gene pairs with the maximum predicted effects, resulting in the highest marginal gain in each AI-experiment round and accelerating discovery with fewer CRISPR experimental iterations. Our NAIAD framework (https://github.com/NeptuneBio/NAIAD) improves the identification of novel, effective gene combinations, enabling more efficient CRISPR library design and offering promising applications in genomics research and therapeutic development.

Video capsule endoscopy has transformed gastrointestinal endoscopy (GIE) diagnostics by offering a non-invasive method for capturing detailed images of the gastrointestinal tract, enabling early disease detection. However, its potential is limited by the sheer volume of images generated during the imaging procedure, which can take anywhere from 6-8 hours and often produce up to 1 million images, necessitating automated analysis. Additionally, the variability of these images, combined with the need for expert annotations and the scarcity of large, high-quality labeled datasets, constrains the effectiveness of current medical image analysis models. To address this, we introduce a novel large GIE dataset, called EndoExtend24, created by merging ten existing public and private datasets, ensuring patient integrity across splits. EndoExtend24 includes over 226,000 labeled images, as well as dynamic class mappings, which allow unified training across datasets with differing labeling granularity, supporting up to 123 distinct pathological findings. Further, we propose to leverage domain adaptive pre-training of foundation models trained with self-supervision on generic image data, to adapt them to the task of GIE medical image diagnosis. Specifically, the EVA-02 model, which is based on the ViT architecture and trained on ImageNet-22k with masked image modeling (using EVA-CLIP as a MIM teacher), is pre-trained on the EndoExtend24 dataset to achieve domain adaptation, and finally trained on the Capsule Endoscopy 2024 Challenge dataset. Our model demonstrates robust performance, securing third place in the Capsule Endoscopy 2024 Challenge. We achieved a macro AUC of 0.762 and a balanced accuracy of 37.1% on the test set. These results emphasize the effectiveness of our domain-adaptive pre-training approach and the enriched EndoExtend24 dataset in advancing gastrointestinal endoscopy diagnostics.

In-group language is an important signifier of group dynamics. This paper proposes a novel method for inducing lexicons of in-group language, which incorporates its socio-temporal context. Existing methods for lexicon induction do not capture the evolving nature of in-group language, nor the social structure of the community. Using dynamic word and user embeddings trained on conversations from online anti-women communities, our approach outperforms prior methods for lexicon induction. We develop a test set for the task of lexicon induction and a new lexicon of manosphere language, validated by human experts, which quantifies the relevance of each term to a specific sub-community at a given point in time. Finally, we present novel insights on in-group language which illustrate the utility of this approach.

Internet services have led to the eruption of network traffic, and machine learning on these Internet data has become an indispensable tool, especially when the application is risk-sensitive. This paper focuses on network traffic classification in the presence of severe class imbalance. Such a distributional trait mostly drifts the optimal decision boundary and results in an unsatisfactory solution. This raises safety concerns in the network traffic field when previous class imbalance methods hardly deal with numerous minority malicious classes. To alleviate these effects, we design a \textit{group \& reweight} strategy for alleviating class imbalance. Inspired by the group distributionally optimization framework, our approach heuristically clusters classes into groups, iteratively updates the non-parametric weights for separate classes, and optimizes the learning model by minimizing reweighted losses. We theoretically interpret the optimization process from a Stackelberg game and perform extensive experiments on typical benchmarks. Results show that our approach can not only suppress the negative effect of class imbalance but also improve the comprehensive performance in prediction.

Recently, machine learning (ML) has gained popularity in the early stages of drug discovery. This trend is unsurprising given the increasing volume of relevant experimental data and the continuous improvement of ML algorithms. However, conventional models, which rely on the principle of molecular similarity, often fail to capture the complexities of chemical interactions, particularly those involving activity cliffs (ACs) - compounds that are structurally similar but exhibit evidently different activity behaviors. In this work, we address two distinct yet related tasks: (1) activity cliff (AC) prediction and (2) drug-target interaction (DTI) prediction. Leveraging insights gained from the AC prediction task, we aim to improve the performance of DTI prediction through transfer learning. A universal model was developed for AC prediction, capable of identifying activity cliffs across diverse targets. Insights from this model were then incorporated into DTI prediction, enabling better handling of challenging cases involving ACs while maintaining similar overall performance. This approach establishes a strong foundation for integrating AC awareness into predictive models for drug discovery. Scientific Contribution This study presents a novel approach that applies transfer learning from AC prediction to enhance DTI prediction, addressing limitations of traditional similarity-based models. By introducing AC-awareness, we improve DTI model performance in structurally complex regions, demonstrating the benefits of integrating compound-specific and protein-contextual information. Unlike previous studies, which treat AC and DTI predictions as separate problems, this work establishes a unified framework to address both data scarcity and prediction challenges in drug discovery.

Biased human decisions have consequential impacts across various domains, yielding unfair treatment of individuals and resulting in suboptimal outcomes for organizations and society. In recognition of this fact, organizations regularly design and deploy interventions aimed at mitigating these biases. However, measuring human decision biases remains an important but elusive task. Organizations are frequently concerned with mistaken decisions disproportionately affecting one group. In practice, however, this is typically not possible to assess due to the scarcity of a gold standard: a label that indicates what the correct decision would have been. In this work, we propose a machine learning-based framework to assess bias in human-generated decisions when gold standard labels are scarce. We provide theoretical guarantees and empirical evidence demonstrating the superiority of our method over existing alternatives. This proposed methodology establishes a foundation for transparency in human decision-making, carrying substantial implications for managerial duties, and offering potential for alleviating algorithmic biases when human decisions are used as labels to train algorithms.

In this study, we presented two innovative methods, which are Threshold-Based Derivative (TBD) and Adaptive Derivative Peak Detection(ADPD), that enhance the accuracy of Learning models for blood glucose estimation using Mid-Infrared (MIR) spectroscopy. In these presented methods, we have enhanced the model's accuracy by integrating absorbance data and its differentiation with critical points. Blood samples were characterized with Fourier Transform Infrared (FTIR) spectroscopy and advanced preprocessing steps. The learning models were Ridge Regression and Support Vector Regression(SVR) using Leave-One-out Cross-Validation. Results exhibited that TBD and ADPD significantly outperform basic used methods. For SVR, the TBD increased the r2 score by around 27%, and ADPD increased it by around 10%. these Ridge Regression values were between 36% and 24%. In addition, Results demonstrate that TBD and ADPD significantly outperform conventional methods, achieving lower error rates and improved clinical accuracy, validated through Clarke and Parkes Error Grid Analysis.

Credit card fraud detection remains a critical challenge in financial security, with machine learning models like XGBoost(eXtreme gradient boosting) emerging as powerful tools for identifying fraudulent transactions. However, the inherent class imbalance in credit card transaction datasets poses significant challenges for model performance. Although sampling techniques are commonly used to address this imbalance, their implementation sometimes precedes the train-test split, potentially introducing data leakage. This study presents a comparative analysis of XGBoost's performance in credit card fraud detection under three scenarios: Firstly without any imbalance handling techniques, secondly with sampling techniques applied only to the training set after the train-test split, and third with sampling techniques applied before the train-test split. We utilized a dataset from Kaggle of 284,807 credit card transactions, containing 0.172\% fraudulent cases, to evaluate these approaches. Our findings show that although sampling strategies enhance model performance, the reliability of results is greatly impacted by when they are applied. Due to a data leakage issue that frequently occurs in machine learning models during the sampling phase, XGBoost models trained on data where sampling was applied prior to the train-test split may have displayed artificially inflated performance metrics. Surprisingly, models trained with sampling techniques applied solely to the training set demonstrated significantly lower results than those with pre-split sampling, all the while preserving the integrity of the evaluation process.