Hosting Language Models on a BudgetKDnuggets Learn how to run your own language model for free using lightweight models and Hugging Face Spaces.
Learn how to run your own language model for free using lightweight models and Hugging Face Spaces. Read More
The Subset Sum Problem Solved in Linear Time for Dense Enough InputsTowards Data Science An optimal solution to the well-known NP-complete problem, when the input values are close enough to each other.
The post The Subset Sum Problem Solved in Linear Time for Dense Enough Inputs appeared first on Towards Data Science.
An optimal solution to the well-known NP-complete problem, when the input values are close enough to each other.
The post The Subset Sum Problem Solved in Linear Time for Dense Enough Inputs appeared first on Towards Data Science. Read More
5 Top AI-Powered App BuildersKDnuggets Take a tour of 5 of the most popular AI-powered app builders out there to leverage automation in the process of building software.
Take a tour of 5 of the most popular AI-powered app builders out there to leverage automation in the process of building software. Read More
Evaluating chain-of-thought monitorabilityOpenAI News OpenAI introduces a new framework and evaluation suite for chain-of-thought monitorability, covering 13 evaluations across 24 environments. Our findings show that monitoring a model’s internal reasoning is far more effective than monitoring outputs alone, offering a promising path toward scalable control as AI systems grow more capable.
OpenAI introduces a new framework and evaluation suite for chain-of-thought monitorability, covering 13 evaluations across 24 environments. Our findings show that monitoring a model’s internal reasoning is far more effective than monitoring outputs alone, offering a promising path toward scalable control as AI systems grow more capable. Read More
RePo: Language Models with Context Re-Positioningcs.AI updates on arXiv.org arXiv:2512.14391v1 Announce Type: cross
Abstract: In-context learning is fundamental to modern Large Language Models (LLMs); however, prevailing architectures impose a rigid and fixed contextual structure by assigning linear or constant positional indices. Drawing on Cognitive Load Theory (CLT), we argue that this uninformative structure increases extraneous cognitive load, consuming finite working memory capacity that should be allocated to deep reasoning and attention allocation. To address this, we propose RePo, a novel mechanism that reduces extraneous load via context re-positioning. Unlike standard approaches, RePo utilizes a differentiable module, $f_phi$, to assign token positions that capture contextual dependencies, rather than replying on pre-defined integer range. By continually pre-training on the OLMo-2 1B backbone, we demonstrate that RePo significantly enhances performance on tasks involving noisy contexts, structured data, and longer context length, while maintaining competitive performance on general short-context tasks. Detailed analysis reveals that RePo successfully allocate higher attention to distant but relevant information, assign positions in dense and non-linear space, and capture the intrinsic structure of the input context. Our code is available at https://github.com/SakanaAI/repo.
arXiv:2512.14391v1 Announce Type: cross
Abstract: In-context learning is fundamental to modern Large Language Models (LLMs); however, prevailing architectures impose a rigid and fixed contextual structure by assigning linear or constant positional indices. Drawing on Cognitive Load Theory (CLT), we argue that this uninformative structure increases extraneous cognitive load, consuming finite working memory capacity that should be allocated to deep reasoning and attention allocation. To address this, we propose RePo, a novel mechanism that reduces extraneous load via context re-positioning. Unlike standard approaches, RePo utilizes a differentiable module, $f_phi$, to assign token positions that capture contextual dependencies, rather than replying on pre-defined integer range. By continually pre-training on the OLMo-2 1B backbone, we demonstrate that RePo significantly enhances performance on tasks involving noisy contexts, structured data, and longer context length, while maintaining competitive performance on general short-context tasks. Detailed analysis reveals that RePo successfully allocate higher attention to distant but relevant information, assign positions in dense and non-linear space, and capture the intrinsic structure of the input context. Our code is available at https://github.com/SakanaAI/repo. Read More
Causal Structure Learning for Dynamical Systems with Theoretical Score Analysiscs.AI updates on arXiv.org arXiv:2512.14361v1 Announce Type: cross
Abstract: Real world systems evolve in continuous-time according to their underlying causal relationships, yet their dynamics are often unknown. Existing approaches to learning such dynamics typically either discretize time — leading to poor performance on irregularly sampled data — or ignore the underlying causality. We propose CaDyT, a novel method for causal discovery on dynamical systems addressing both these challenges. In contrast to state-of-the-art causal discovery methods that model the problem using discrete-time Dynamic Bayesian networks, our formulation is grounded in Difference-based causal models, which allow milder assumptions for modeling the continuous nature of the system. CaDyT leverages exact Gaussian Process inference for modeling the continuous-time dynamics which is more aligned with the underlying dynamical process. We propose a practical instantiation that identifies the causal structure via a greedy search guided by the Algorithmic Markov Condition and Minimum Description Length principle. Our experiments show that CaDyT outperforms state-of-the-art methods on both regularly and irregularly-sampled data, discovering causal networks closer to the true underlying dynamics.
arXiv:2512.14361v1 Announce Type: cross
Abstract: Real world systems evolve in continuous-time according to their underlying causal relationships, yet their dynamics are often unknown. Existing approaches to learning such dynamics typically either discretize time — leading to poor performance on irregularly sampled data — or ignore the underlying causality. We propose CaDyT, a novel method for causal discovery on dynamical systems addressing both these challenges. In contrast to state-of-the-art causal discovery methods that model the problem using discrete-time Dynamic Bayesian networks, our formulation is grounded in Difference-based causal models, which allow milder assumptions for modeling the continuous nature of the system. CaDyT leverages exact Gaussian Process inference for modeling the continuous-time dynamics which is more aligned with the underlying dynamical process. We propose a practical instantiation that identifies the causal structure via a greedy search guided by the Algorithmic Markov Condition and Minimum Description Length principle. Our experiments show that CaDyT outperforms state-of-the-art methods on both regularly and irregularly-sampled data, discovering causal networks closer to the true underlying dynamics. Read More
Masked Omics Modeling for Multimodal Representation Learning across Histopathology and Molecular Profilescs.AI updates on arXiv.org arXiv:2508.00969v2 Announce Type: replace-cross
Abstract: Self-supervised learning (SSL) has driven major advances in computational pathology by enabling the learning of rich representations from histopathology data. Yet, tissue analysis alone may fall short in capturing broader molecular complexity, as key complementary information resides in high-dimensional omics profiles such as transcriptomics, methylomics, and genomics. To address this gap, we introduce MORPHEUS, the first multimodal pre-training strategy that integrates histopathology images and multi-omics data within a shared transformer-based architecture. At its core, MORPHEUS relies on a novel masked omics modeling objective that encourages the model to learn meaningful cross-modal relationships. This yields a general-purpose pre-trained encoder that can be applied to histopathology alone or in combination with any subset of omics modalities. Beyond inference, MORPHEUS also supports flexible any-to-any omics reconstruction, enabling one or more omics profiles to be reconstructed from any modality subset that includes histopathology. Pre-trained on a large pan-cancer cohort, MORPHEUS shows substantial improvements over supervised and SSL baselines across diverse tasks and modality combinations. Together, these capabilities position it as a promising direction for the development of multimodal foundation models in oncology. Code is publicly available at https://github.com/Lucas-rbnt/MORPHEUS
arXiv:2508.00969v2 Announce Type: replace-cross
Abstract: Self-supervised learning (SSL) has driven major advances in computational pathology by enabling the learning of rich representations from histopathology data. Yet, tissue analysis alone may fall short in capturing broader molecular complexity, as key complementary information resides in high-dimensional omics profiles such as transcriptomics, methylomics, and genomics. To address this gap, we introduce MORPHEUS, the first multimodal pre-training strategy that integrates histopathology images and multi-omics data within a shared transformer-based architecture. At its core, MORPHEUS relies on a novel masked omics modeling objective that encourages the model to learn meaningful cross-modal relationships. This yields a general-purpose pre-trained encoder that can be applied to histopathology alone or in combination with any subset of omics modalities. Beyond inference, MORPHEUS also supports flexible any-to-any omics reconstruction, enabling one or more omics profiles to be reconstructed from any modality subset that includes histopathology. Pre-trained on a large pan-cancer cohort, MORPHEUS shows substantial improvements over supervised and SSL baselines across diverse tasks and modality combinations. Together, these capabilities position it as a promising direction for the development of multimodal foundation models in oncology. Code is publicly available at https://github.com/Lucas-rbnt/MORPHEUS Read More
Scale-Agnostic Kolmogorov-Arnold Geometry in Neural Networkscs.AI updates on arXiv.org arXiv:2511.21626v3 Announce Type: replace-cross
Abstract: Recent work by Freedman and Mulligan demonstrated that shallow multilayer perceptrons spontaneously develop Kolmogorov-Arnold geometric (KAG) structure during training on synthetic three-dimensional tasks. However, it remained unclear whether this phenomenon persists in realistic high-dimensional settings and what spatial properties this geometry exhibits.
We extend KAG analysis to MNIST digit classification (784 dimensions) using 2-layer MLPs with systematic spatial analysis at multiple scales. We find that KAG emerges during training and appears consistently across spatial scales, from local 7-pixel neighborhoods to the full 28×28 image. This scale-agnostic property holds across different training procedures: both standard training and training with spatial augmentation produce the same qualitative pattern. These findings reveal that neural networks spontaneously develop organized, scale-invariant geometric structure during learning on realistic high-dimensional data.
arXiv:2511.21626v3 Announce Type: replace-cross
Abstract: Recent work by Freedman and Mulligan demonstrated that shallow multilayer perceptrons spontaneously develop Kolmogorov-Arnold geometric (KAG) structure during training on synthetic three-dimensional tasks. However, it remained unclear whether this phenomenon persists in realistic high-dimensional settings and what spatial properties this geometry exhibits.
We extend KAG analysis to MNIST digit classification (784 dimensions) using 2-layer MLPs with systematic spatial analysis at multiple scales. We find that KAG emerges during training and appears consistently across spatial scales, from local 7-pixel neighborhoods to the full 28×28 image. This scale-agnostic property holds across different training procedures: both standard training and training with spatial augmentation produce the same qualitative pattern. These findings reveal that neural networks spontaneously develop organized, scale-invariant geometric structure during learning on realistic high-dimensional data. Read More
STEMS: Spatial-Temporal Enhanced Safe Multi-Agent Coordination for Building Energy Managementcs.AI updates on arXiv.org arXiv:2510.14112v2 Announce Type: replace
Abstract: Building energy management is essential for achieving carbon reduction goals, improving occupant comfort, and reducing energy costs. Coordinated building energy management faces critical challenges in exploiting spatial-temporal dependencies while ensuring operational safety across multi-building systems. Current multi-building energy systems face three key challenges: insufficient spatial-temporal information exploitation, lack of rigorous safety guarantees, and system complexity. This paper proposes Spatial-Temporal Enhanced Safe Multi-Agent Coordination (STEMS), a novel safety-constrained multi-agent reinforcement learning framework for coordinated building energy management. STEMS integrates two core components: (1) a spatial-temporal graph representation learning framework using a GCN-Transformer fusion architecture to capture inter-building relationships and temporal patterns, and (2) a safety-constrained multi-agent RL algorithm incorporating Control Barrier Functions to provide mathematical safety guarantees. Extensive experiments on real-world building datasets demonstrate STEMS’s superior performance over existing methods, showing that STEMS achieves 21% cost reduction, 18% emission reduction, and dramatically reduces safety violations from 35.1% to 5.6% while maintaining optimal comfort with only 0.13 discomfort proportion. The framework also demonstrates strong robustness during extreme weather conditions and maintains effectiveness across different building types.
arXiv:2510.14112v2 Announce Type: replace
Abstract: Building energy management is essential for achieving carbon reduction goals, improving occupant comfort, and reducing energy costs. Coordinated building energy management faces critical challenges in exploiting spatial-temporal dependencies while ensuring operational safety across multi-building systems. Current multi-building energy systems face three key challenges: insufficient spatial-temporal information exploitation, lack of rigorous safety guarantees, and system complexity. This paper proposes Spatial-Temporal Enhanced Safe Multi-Agent Coordination (STEMS), a novel safety-constrained multi-agent reinforcement learning framework for coordinated building energy management. STEMS integrates two core components: (1) a spatial-temporal graph representation learning framework using a GCN-Transformer fusion architecture to capture inter-building relationships and temporal patterns, and (2) a safety-constrained multi-agent RL algorithm incorporating Control Barrier Functions to provide mathematical safety guarantees. Extensive experiments on real-world building datasets demonstrate STEMS’s superior performance over existing methods, showing that STEMS achieves 21% cost reduction, 18% emission reduction, and dramatically reduces safety violations from 35.1% to 5.6% while maintaining optimal comfort with only 0.13 discomfort proportion. The framework also demonstrates strong robustness during extreme weather conditions and maintains effectiveness across different building types. Read More
Text-guided multi-property molecular optimization with a diffusion language modelcs.AI updates on arXiv.org arXiv:2410.13597v4 Announce Type: replace-cross
Abstract: Molecular optimization (MO) is a crucial stage in drug discovery in which task-oriented generated molecules are optimized to meet practical industrial requirements. Existing mainstream MO approaches primarily utilize external property predictors to guide iterative property optimization. However, learning all molecular samples in the vast chemical space is unrealistic for predictors. As a result, errors and noise are inevitably introduced during property prediction due to the nature of approximation. This leads to discrepancy accumulation, generalization reduction and suboptimal molecular candidates. In this paper, we propose a text-guided multi-property molecular optimization method utilizing transformer-based diffusion language model (TransDLM). TransDLM leverages standardized chemical nomenclature as semantic representations of molecules and implicitly embeds property requirements into textual descriptions, thereby mitigating error propagation during diffusion process. By fusing physically and chemically detailed textual semantics with specialized molecular representations, TransDLM effectively integrates diverse information sources to guide precise optimization, which enhances the model’s ability to balance structural retention and property enhancement. Additionally, the success of a case study further demonstrates TransDLM’s ability to solve practical problems. Experimentally, our approach surpasses state-of-the-art methods in maintaining molecular structural similarity and enhancing chemical properties on the benchmark dataset.
arXiv:2410.13597v4 Announce Type: replace-cross
Abstract: Molecular optimization (MO) is a crucial stage in drug discovery in which task-oriented generated molecules are optimized to meet practical industrial requirements. Existing mainstream MO approaches primarily utilize external property predictors to guide iterative property optimization. However, learning all molecular samples in the vast chemical space is unrealistic for predictors. As a result, errors and noise are inevitably introduced during property prediction due to the nature of approximation. This leads to discrepancy accumulation, generalization reduction and suboptimal molecular candidates. In this paper, we propose a text-guided multi-property molecular optimization method utilizing transformer-based diffusion language model (TransDLM). TransDLM leverages standardized chemical nomenclature as semantic representations of molecules and implicitly embeds property requirements into textual descriptions, thereby mitigating error propagation during diffusion process. By fusing physically and chemically detailed textual semantics with specialized molecular representations, TransDLM effectively integrates diverse information sources to guide precise optimization, which enhances the model’s ability to balance structural retention and property enhancement. Additionally, the success of a case study further demonstrates TransDLM’s ability to solve practical problems. Experimentally, our approach surpasses state-of-the-art methods in maintaining molecular structural similarity and enhancing chemical properties on the benchmark dataset. Read More