Category: News

Stop Blaming the Data: A Better Way to Handle Covariance ShiftTowards Data Science Instead of using shift as an excuse for poor performance, use Inverse Probability Weighting to estimate how your model should perform in the new environment
The post Stop Blaming the Data: A Better Way to Handle Covariance Shift appeared first on Towards Data Science.

 Instead of using shift as an excuse for poor performance, use Inverse Probability Weighting to estimate how your model should perform in the new environment
The post Stop Blaming the Data: A Better Way to Handle Covariance Shift appeared first on Towards Data Science. Read More  

It’s complicated. The relationship of algorithmic fairness and non-discrimination provisions for high-risk systems in the EU AI Actcs.AI updates on arXiv.org arXiv:2501.12962v5 Announce Type: replace-cross
Abstract: What constitutes a fair decision? This question is not only difficult for humans but becomes more challenging when Artificial Intelligence (AI) models are used. In light of discriminatory algorithmic behaviors, the EU has recently passed the AI Act, which mandates specific rules for high-risk systems, incorporating both traditional legal non-discrimination regulations and machine learning based algorithmic fairness concepts. This paper aims to bridge these two different concepts in the AI Act through: First, a necessary high-level introduction of both concepts targeting legal and computer science-oriented scholars, and second, an in-depth analysis of the AI Act’s relationship between legal non-discrimination regulations and algorithmic fairness. Our analysis reveals three key findings: (1.) Most non-discrimination regulations target only high-risk AI systems. (2.) The regulation of high-risk systems encompasses both data input requirements and output monitoring, though these regulations are partly inconsistent and raise questions of computational feasibility. (3.) Finally, we consider the possible (future) interaction of classical EU non-discrimination law and the AI Act regulations. We recommend developing more specific auditing and testing methodologies for AI systems. This paper aims to serve as a foundation for future interdisciplinary collaboration between legal scholars and computer science-oriented machine learning researchers studying discrimination in AI systems.

 arXiv:2501.12962v5 Announce Type: replace-cross
Abstract: What constitutes a fair decision? This question is not only difficult for humans but becomes more challenging when Artificial Intelligence (AI) models are used. In light of discriminatory algorithmic behaviors, the EU has recently passed the AI Act, which mandates specific rules for high-risk systems, incorporating both traditional legal non-discrimination regulations and machine learning based algorithmic fairness concepts. This paper aims to bridge these two different concepts in the AI Act through: First, a necessary high-level introduction of both concepts targeting legal and computer science-oriented scholars, and second, an in-depth analysis of the AI Act’s relationship between legal non-discrimination regulations and algorithmic fairness. Our analysis reveals three key findings: (1.) Most non-discrimination regulations target only high-risk AI systems. (2.) The regulation of high-risk systems encompasses both data input requirements and output monitoring, though these regulations are partly inconsistent and raise questions of computational feasibility. (3.) Finally, we consider the possible (future) interaction of classical EU non-discrimination law and the AI Act regulations. We recommend developing more specific auditing and testing methodologies for AI systems. This paper aims to serve as a foundation for future interdisciplinary collaboration between legal scholars and computer science-oriented machine learning researchers studying discrimination in AI systems. Read More  

RMAAT: Astrocyte-Inspired Memory Compression and Replay for Efficient Long-Context Transformerscs.AI updates on arXiv.org arXiv:2601.00426v1 Announce Type: cross
Abstract: The quadratic complexity of self-attention mechanism presents a significant impediment to applying Transformer models to long sequences. This work explores computational principles derived from astrocytes-glial cells critical for biological memory and synaptic modulation-as a complementary approach to conventional architectural modifications for efficient self-attention. We introduce the Recurrent Memory Augmented Astromorphic Transformer (RMAAT), an architecture integrating abstracted astrocyte functionalities. RMAAT employs a recurrent, segment-based processing strategy where persistent memory tokens propagate contextual information. An adaptive compression mechanism, governed by a novel retention factor derived from simulated astrocyte long-term plasticity (LTP), modulates these tokens. Attention within segments utilizes an efficient, linear-complexity mechanism inspired by astrocyte short-term plasticity (STP). Training is performed using Astrocytic Memory Replay Backpropagation (AMRB), a novel algorithm designed for memory efficiency in recurrent networks. Evaluations on the Long Range Arena (LRA) benchmark demonstrate RMAAT’s competitive accuracy and substantial improvements in computational and memory efficiency, indicating the potential of incorporating astrocyte-inspired dynamics into scalable sequence models.

 arXiv:2601.00426v1 Announce Type: cross
Abstract: The quadratic complexity of self-attention mechanism presents a significant impediment to applying Transformer models to long sequences. This work explores computational principles derived from astrocytes-glial cells critical for biological memory and synaptic modulation-as a complementary approach to conventional architectural modifications for efficient self-attention. We introduce the Recurrent Memory Augmented Astromorphic Transformer (RMAAT), an architecture integrating abstracted astrocyte functionalities. RMAAT employs a recurrent, segment-based processing strategy where persistent memory tokens propagate contextual information. An adaptive compression mechanism, governed by a novel retention factor derived from simulated astrocyte long-term plasticity (LTP), modulates these tokens. Attention within segments utilizes an efficient, linear-complexity mechanism inspired by astrocyte short-term plasticity (STP). Training is performed using Astrocytic Memory Replay Backpropagation (AMRB), a novel algorithm designed for memory efficiency in recurrent networks. Evaluations on the Long Range Arena (LRA) benchmark demonstrate RMAAT’s competitive accuracy and substantial improvements in computational and memory efficiency, indicating the potential of incorporating astrocyte-inspired dynamics into scalable sequence models. Read More  

Ask, Clarify, Optimize: Human-LLM Agent Collaboration for Smarter Inventory Controlcs.AI updates on arXiv.org arXiv:2601.00121v1 Announce Type: new
Abstract: Inventory management remains a challenge for many small and medium-sized businesses that lack the expertise to deploy advanced optimization methods. This paper investigates whether Large Language Models (LLMs) can help bridge this gap. We show that employing LLMs as direct, end-to-end solvers incurs a significant “hallucination tax”: a performance gap arising from the model’s inability to perform grounded stochastic reasoning. To address this, we propose a hybrid agentic framework that strictly decouples semantic reasoning from mathematical calculation. In this architecture, the LLM functions as an intelligent interface, eliciting parameters from natural language and interpreting results while automatically calling rigorous algorithms to build the optimization engine.
To evaluate this interactive system against the ambiguity and inconsistency of real-world managerial dialogue, we introduce the Human Imitator, a fine-tuned “digital twin” of a boundedly rational manager that enables scalable, reproducible stress-testing. Our empirical analysis reveals that the hybrid agentic framework reduces total inventory costs by 32.1% relative to an interactive baseline using GPT-4o as an end-to-end solver. Moreover, we find that providing perfect ground-truth information alone is insufficient to improve GPT-4o’s performance, confirming that the bottleneck is fundamentally computational rather than informational. Our results position LLMs not as replacements for operations research, but as natural-language interfaces that make rigorous, solver-based policies accessible to non-experts.

 arXiv:2601.00121v1 Announce Type: new
Abstract: Inventory management remains a challenge for many small and medium-sized businesses that lack the expertise to deploy advanced optimization methods. This paper investigates whether Large Language Models (LLMs) can help bridge this gap. We show that employing LLMs as direct, end-to-end solvers incurs a significant “hallucination tax”: a performance gap arising from the model’s inability to perform grounded stochastic reasoning. To address this, we propose a hybrid agentic framework that strictly decouples semantic reasoning from mathematical calculation. In this architecture, the LLM functions as an intelligent interface, eliciting parameters from natural language and interpreting results while automatically calling rigorous algorithms to build the optimization engine.
To evaluate this interactive system against the ambiguity and inconsistency of real-world managerial dialogue, we introduce the Human Imitator, a fine-tuned “digital twin” of a boundedly rational manager that enables scalable, reproducible stress-testing. Our empirical analysis reveals that the hybrid agentic framework reduces total inventory costs by 32.1% relative to an interactive baseline using GPT-4o as an end-to-end solver. Moreover, we find that providing perfect ground-truth information alone is insufficient to improve GPT-4o’s performance, confirming that the bottleneck is fundamentally computational rather than informational. Our results position LLMs not as replacements for operations research, but as natural-language interfaces that make rigorous, solver-based policies accessible to non-experts. Read More  

Mortar: Evolving Mechanics for Automatic Game Designcs.AI updates on arXiv.org arXiv:2601.00105v1 Announce Type: new
Abstract: We present Mortar, a system for autonomously evolving game mechanics for automatic game design. Game mechanics define the rules and interactions that govern gameplay, and designing them manually is a time-consuming and expert-driven process. Mortar combines a quality-diversity algorithm with a large language model to explore a diverse set of mechanics, which are evaluated by synthesising complete games that incorporate both evolved mechanics and those drawn from an archive. The mechanics are evaluated by composing complete games through a tree search procedure, where the resulting games are evaluated by their ability to preserve a skill-based ordering over players — that is, whether stronger players consistently outperform weaker ones. We assess the mechanics based on their contribution towards the skill-based ordering score in the game. We demonstrate that Mortar produces games that appear diverse and playable, and mechanics that contribute more towards the skill-based ordering score in the game. We perform ablation studies to assess the role of each system component and a user study to evaluate the games based on human feedback.

 arXiv:2601.00105v1 Announce Type: new
Abstract: We present Mortar, a system for autonomously evolving game mechanics for automatic game design. Game mechanics define the rules and interactions that govern gameplay, and designing them manually is a time-consuming and expert-driven process. Mortar combines a quality-diversity algorithm with a large language model to explore a diverse set of mechanics, which are evaluated by synthesising complete games that incorporate both evolved mechanics and those drawn from an archive. The mechanics are evaluated by composing complete games through a tree search procedure, where the resulting games are evaluated by their ability to preserve a skill-based ordering over players — that is, whether stronger players consistently outperform weaker ones. We assess the mechanics based on their contribution towards the skill-based ordering score in the game. We demonstrate that Mortar produces games that appear diverse and playable, and mechanics that contribute more towards the skill-based ordering score in the game. We perform ablation studies to assess the role of each system component and a user study to evaluate the games based on human feedback. Read More  

Towards Automated Differential Diagnosis of Skin Diseases Using Deep Learning and Imbalance-Aware Strategiescs.AI updates on arXiv.org arXiv:2601.00286v1 Announce Type: cross
Abstract: As dermatological conditions become increasingly common and the availability of dermatologists remains limited, there is a growing need for intelligent tools to support both patients and clinicians in the timely and accurate diagnosis of skin diseases. In this project, we developed a deep learning based model for the classification and diagnosis of skin conditions. By leveraging pretraining on publicly available skin disease image datasets, our model effectively extracted visual features and accurately classified various dermatological cases. Throughout the project, we refined the model architecture, optimized data preprocessing workflows, and applied targeted data augmentation techniques to improve overall performance. The final model, based on the Swin Transformer, achieved a prediction accuracy of 87.71 percent across eight skin lesion classes on the ISIC2019 dataset. These results demonstrate the model’s potential as a diagnostic support tool for clinicians and a self assessment aid for patients.

 arXiv:2601.00286v1 Announce Type: cross
Abstract: As dermatological conditions become increasingly common and the availability of dermatologists remains limited, there is a growing need for intelligent tools to support both patients and clinicians in the timely and accurate diagnosis of skin diseases. In this project, we developed a deep learning based model for the classification and diagnosis of skin conditions. By leveraging pretraining on publicly available skin disease image datasets, our model effectively extracted visual features and accurately classified various dermatological cases. Throughout the project, we refined the model architecture, optimized data preprocessing workflows, and applied targeted data augmentation techniques to improve overall performance. The final model, based on the Swin Transformer, achieved a prediction accuracy of 87.71 percent across eight skin lesion classes on the ISIC2019 dataset. These results demonstrate the model’s potential as a diagnostic support tool for clinicians and a self assessment aid for patients. Read More  

Beyond Perfect APIs: A Comprehensive Evaluation of LLM Agents Under Real-World API Complexitycs.AI updates on arXiv.org arXiv:2601.00268v1 Announce Type: cross
Abstract: We introduce WildAGTEval, a benchmark designed to evaluate large language model (LLM) agents’ function-calling capabilities under realistic API complexity. Unlike prior work that assumes an idealized API system and disregards real-world factors such as noisy API outputs, WildAGTEval accounts for two dimensions of real-world complexity: 1. API specification, which includes detailed documentation and usage constraints, and 2. API execution, which captures runtime challenges. Consequently, WildAGTEval offers (i) an API system encompassing 60 distinct complexity scenarios that can be composed into approximately 32K test configurations, and (ii) user-agent interactions for evaluating LLM agents on these scenarios. Using WildAGTEval, we systematically assess several advanced LLMs and observe that most scenarios are challenging, with irrelevant information complexity posing the greatest difficulty and reducing the performance of strong LLMs by 27.3%. Furthermore, our qualitative analysis reveals that LLMs occasionally distort user intent merely to claim task completion, critically affecting user satisfaction.

 arXiv:2601.00268v1 Announce Type: cross
Abstract: We introduce WildAGTEval, a benchmark designed to evaluate large language model (LLM) agents’ function-calling capabilities under realistic API complexity. Unlike prior work that assumes an idealized API system and disregards real-world factors such as noisy API outputs, WildAGTEval accounts for two dimensions of real-world complexity: 1. API specification, which includes detailed documentation and usage constraints, and 2. API execution, which captures runtime challenges. Consequently, WildAGTEval offers (i) an API system encompassing 60 distinct complexity scenarios that can be composed into approximately 32K test configurations, and (ii) user-agent interactions for evaluating LLM agents on these scenarios. Using WildAGTEval, we systematically assess several advanced LLMs and observe that most scenarios are challenging, with irrelevant information complexity posing the greatest difficulty and reducing the performance of strong LLMs by 27.3%. Furthermore, our qualitative analysis reveals that LLMs occasionally distort user intent merely to claim task completion, critically affecting user satisfaction. Read More