CORGI: Efficient Pattern Matching With Quadratic Guaranteescs.AI updates on arXiv.org arXiv:2511.13942v1 Announce Type: new
Abstract: Rule-based systems must solve complex matching problems within tight time constraints to be effective in real-time applications, such as planning and reactive control for AI agents, as well as low-latency relational database querying. Pattern-matching systems can encounter issues where exponential time and space are required to find matches for rules with many underconstrained variables, or which produce combinatorial intermediate partial matches (but are otherwise well-constrained). When online AI systems automatically generate rules from example-driven induction or code synthesis, they can easily produce worst-case matching patterns that slow or halt program execution by exceeding available memory. In our own work with cognitive systems that learn from example, we’ve found that aggressive forms of anti-unification-based generalization can easily produce these circumstances. To make these systems practical without hand-engineering constraints or succumbing to unpredictable failure modes, we introduce a new matching algorithm called CORGI (Collection-Oriented Relational Graph Iteration). Unlike RETE-based approaches, CORGI offers quadratic time and space guarantees for finding single satisficing matches, and the ability to iteratively stream subsequent matches without committing entire conflict sets to memory. CORGI differs from RETE in that it does not have a traditional $beta$-memory for collecting partial matches. Instead, CORGI takes a two-step approach: a graph of grounded relations is built/maintained in a forward pass, and an iterator generates matches as needed by working backward through the graph. This approach eliminates the high-latency delays and memory overflows that can result from populating full conflict sets. In a performance evaluation, we demonstrate that CORGI significantly outperforms RETE implementations from SOAR and OPS5 on a simple combinatorial matching task.
arXiv:2511.13942v1 Announce Type: new
Abstract: Rule-based systems must solve complex matching problems within tight time constraints to be effective in real-time applications, such as planning and reactive control for AI agents, as well as low-latency relational database querying. Pattern-matching systems can encounter issues where exponential time and space are required to find matches for rules with many underconstrained variables, or which produce combinatorial intermediate partial matches (but are otherwise well-constrained). When online AI systems automatically generate rules from example-driven induction or code synthesis, they can easily produce worst-case matching patterns that slow or halt program execution by exceeding available memory. In our own work with cognitive systems that learn from example, we’ve found that aggressive forms of anti-unification-based generalization can easily produce these circumstances. To make these systems practical without hand-engineering constraints or succumbing to unpredictable failure modes, we introduce a new matching algorithm called CORGI (Collection-Oriented Relational Graph Iteration). Unlike RETE-based approaches, CORGI offers quadratic time and space guarantees for finding single satisficing matches, and the ability to iteratively stream subsequent matches without committing entire conflict sets to memory. CORGI differs from RETE in that it does not have a traditional $beta$-memory for collecting partial matches. Instead, CORGI takes a two-step approach: a graph of grounded relations is built/maintained in a forward pass, and an iterator generates matches as needed by working backward through the graph. This approach eliminates the high-latency delays and memory overflows that can result from populating full conflict sets. In a performance evaluation, we demonstrate that CORGI significantly outperforms RETE implementations from SOAR and OPS5 on a simple combinatorial matching task. Read More
Artificial Intelligence Agents in Music Analysis: An Integrative Perspective Based on Two Use Casescs.AI updates on arXiv.org arXiv:2511.13987v1 Announce Type: new
Abstract: This paper presents an integrative review and experimental validation of artificial intelligence (AI) agents applied to music analysis and education. We synthesize the historical evolution from rule-based models to contemporary approaches involving deep learning, multi-agent architectures, and retrieval-augmented generation (RAG) frameworks. The pedagogical implications are evaluated through a dual-case methodology: (1) the use of generative AI platforms in secondary education to foster analytical and creative skills; (2) the design of a multiagent system for symbolic music analysis, enabling modular, scalable, and explainable workflows.
Experimental results demonstrate that AI agents effectively enhance musical pattern recognition, compositional parameterization, and educational feedback, outperforming traditional automated methods in terms of interpretability and adaptability. The findings highlight key challenges concerning transparency, cultural bias, and the definition of hybrid evaluation metrics, emphasizing the need for responsible deployment of AI in educational environments.
This research contributes to a unified framework that bridges technical, pedagogical, and ethical considerations, offering evidence-based guidance for the design and application of intelligent agents in computational musicology and music education.
arXiv:2511.13987v1 Announce Type: new
Abstract: This paper presents an integrative review and experimental validation of artificial intelligence (AI) agents applied to music analysis and education. We synthesize the historical evolution from rule-based models to contemporary approaches involving deep learning, multi-agent architectures, and retrieval-augmented generation (RAG) frameworks. The pedagogical implications are evaluated through a dual-case methodology: (1) the use of generative AI platforms in secondary education to foster analytical and creative skills; (2) the design of a multiagent system for symbolic music analysis, enabling modular, scalable, and explainable workflows.
Experimental results demonstrate that AI agents effectively enhance musical pattern recognition, compositional parameterization, and educational feedback, outperforming traditional automated methods in terms of interpretability and adaptability. The findings highlight key challenges concerning transparency, cultural bias, and the definition of hybrid evaluation metrics, emphasizing the need for responsible deployment of AI in educational environments.
This research contributes to a unified framework that bridges technical, pedagogical, and ethical considerations, offering evidence-based guidance for the design and application of intelligent agents in computational musicology and music education. Read More
Lightweight LLM powers Japanese enterprise AI deploymentsAI News Enterprise AI deployment has been facing a fundamental tension: organisations need sophisticated language models but baulk at the infrastructure costs and energy consumption of frontier systems. NTT Inc.’s recent launch of tsuzumi 2, a lightweight large language model (LLM) running on a single GPU, demonstrates how businesses are resolving this constraint—with early deployments showing performance matching larger
The post Lightweight LLM powers Japanese enterprise AI deployments appeared first on AI News.
Enterprise AI deployment has been facing a fundamental tension: organisations need sophisticated language models but baulk at the infrastructure costs and energy consumption of frontier systems. NTT Inc.’s recent launch of tsuzumi 2, a lightweight large language model (LLM) running on a single GPU, demonstrates how businesses are resolving this constraint—with early deployments showing performance matching larger
The post Lightweight LLM powers Japanese enterprise AI deployments appeared first on AI News. Read More
The founders of the Samourai Wallet (Samourai) cryptocurrency mixing service have been sent to prison for helping criminals launder over $237 million. […] Read More
Threat actors with ties to Iran engaged in cyber warfare as part of efforts to facilitate and enhance physical, real-world attacks, a trend that Amazon has called cyber-enabled kinetic targeting. The development is a sign that the lines between state-sponsored cyber attacks and kinetic warfare are increasingly blurring, necessitating the need for a new category […]
OpenAI and Foxconn collaborate to strengthen U.S. manufacturing across the AI supply chainOpenAI News OpenAI and Foxconn are collaborating to design and manufacture next-generation AI infrastructure hardware in the U.S. The partnership will develop multiple generations of data-center systems, strengthen U.S. supply chains, and build key components domestically to accelerate advanced AI infrastructure.
OpenAI and Foxconn are collaborating to design and manufacture next-generation AI infrastructure hardware in the U.S. The partnership will develop multiple generations of data-center systems, strengthen U.S. supply chains, and build key components domestically to accelerate advanced AI infrastructure. Read More
Threat actors are leveraging bogus installers masquerading as popular software to trick users into installing malware as part of a global malvertising campaign dubbed TamperedChef. The end goal of the attacks is to establish persistence and deliver JavaScript malware that facilitates remote access and control, per a new report from Acronis Threat Research Unit (TRU). […]
Cybersecurity researchers have disclosed details of a new Android banking trojan called Sturnus that enables credential theft and full device takeover to conduct financial fraud. “A key differentiator is its ability to bypass encrypted messaging,” ThreatFabric said in a report shared with The Hacker News. “By capturing content directly from the device screen after decryption, […]
Patent Language Model Pretraining with ModernBERTcs.AI updates on arXiv.org arXiv:2509.14926v3 Announce Type: replace-cross
Abstract: Transformer-based language models such as BERT have become foundational in NLP, yet their performance degrades in specialized domains like patents, which contain long, technical, and legally structured text. Prior approaches to patent NLP have primarily relied on fine-tuning general-purpose models or domain-adapted variants pretrained with limited data. In this work, we pretrain 3 domain-specific masked language models for patents, using the ModernBERT architecture and a curated corpus of over 60 million patent records. Our approach incorporates architectural optimizations, including FlashAttention, rotary embeddings, and GLU feed-forward layers. We evaluate our models on four downstream patent classification tasks. Our model, ModernBERT-base-PT, consistently outperforms the general-purpose ModernBERT baseline on three out of four datasets and achieves competitive performance with a baseline PatentBERT. Additional experiments with ModernBERT-base-VX and Mosaic-BERT-large demonstrate that scaling the model size and customizing the tokenizer further enhance performance on selected tasks. Notably, all ModernBERT variants retain substantially faster inference over – 3x that of PatentBERT – underscoring their suitability for time-sensitive applications. These results underscore the benefits of domain-specific pretraining and architectural improvements for patent-focused NLP tasks.
arXiv:2509.14926v3 Announce Type: replace-cross
Abstract: Transformer-based language models such as BERT have become foundational in NLP, yet their performance degrades in specialized domains like patents, which contain long, technical, and legally structured text. Prior approaches to patent NLP have primarily relied on fine-tuning general-purpose models or domain-adapted variants pretrained with limited data. In this work, we pretrain 3 domain-specific masked language models for patents, using the ModernBERT architecture and a curated corpus of over 60 million patent records. Our approach incorporates architectural optimizations, including FlashAttention, rotary embeddings, and GLU feed-forward layers. We evaluate our models on four downstream patent classification tasks. Our model, ModernBERT-base-PT, consistently outperforms the general-purpose ModernBERT baseline on three out of four datasets and achieves competitive performance with a baseline PatentBERT. Additional experiments with ModernBERT-base-VX and Mosaic-BERT-large demonstrate that scaling the model size and customizing the tokenizer further enhance performance on selected tasks. Notably, all ModernBERT variants retain substantially faster inference over – 3x that of PatentBERT – underscoring their suitability for time-sensitive applications. These results underscore the benefits of domain-specific pretraining and architectural improvements for patent-focused NLP tasks. Read More
Energy Consumption of Dataframe Libraries for End-to-End Deep Learning Pipelines:A Comparative Analysiscs.AI updates on arXiv.org arXiv:2511.08644v2 Announce Type: replace-cross
Abstract: This paper presents a detailed comparative analysis of the performance of three major Python data manipulation libraries – Pandas, Polars, and Dask – specifically when embedded within complete deep learning (DL) training and inference pipelines. The research bridges a gap in existing literature by studying how these libraries interact with substantial GPU workloads during critical phases like data loading, preprocessing, and batch feeding. The authors measured key performance indicators including runtime, memory usage, disk usage, and energy consumption (both CPU and GPU) across various machine learning models and datasets.
arXiv:2511.08644v2 Announce Type: replace-cross
Abstract: This paper presents a detailed comparative analysis of the performance of three major Python data manipulation libraries – Pandas, Polars, and Dask – specifically when embedded within complete deep learning (DL) training and inference pipelines. The research bridges a gap in existing literature by studying how these libraries interact with substantial GPU workloads during critical phases like data loading, preprocessing, and batch feeding. The authors measured key performance indicators including runtime, memory usage, disk usage, and energy consumption (both CPU and GPU) across various machine learning models and datasets. Read More
