Tool Masking: The Layer MCP ForgotTowards Data Scienceon September 5, 2025 at 12:00 pm Tool masking for AI improves AI agents: shape MCP tool surfaces to cut tokens and errors, boost speed and reliability. Start prompt engineering your tools
The post Tool Masking: The Layer MCP Forgot appeared first on Towards Data Science.
Tool masking for AI improves AI agents: shape MCP tool surfaces to cut tokens and errors, boost speed and reliability. Start prompt engineering your tools
The post Tool Masking: The Layer MCP Forgot appeared first on Towards Data Science. Read More
Keypoint-based Diffusion for Robotic Motion Planning on the NICOL Robotcs.AI updates on arXiv.orgon September 5, 2025 at 4:00 am arXiv:2509.04076v1 Announce Type: cross
Abstract: We propose a novel diffusion-based action model for robotic motion planning. Commonly, established numerical planning approaches are used to solve general motion planning problems, but have significant runtime requirements. By leveraging the power of deep learning, we are able to achieve good results in a much smaller runtime by learning from a dataset generated by these planners. While our initial model uses point cloud embeddings in the input to predict keypoint-based joint sequences in its output, we observed in our ablation study that it remained challenging to condition the network on the point cloud embeddings. We identified some biases in our dataset and refined it, which improved the model’s performance. Our model, even without the use of the point cloud encodings, outperforms numerical models by an order of magnitude regarding the runtime, while reaching a success rate of up to 90% of collision free solutions on the test set.
arXiv:2509.04076v1 Announce Type: cross
Abstract: We propose a novel diffusion-based action model for robotic motion planning. Commonly, established numerical planning approaches are used to solve general motion planning problems, but have significant runtime requirements. By leveraging the power of deep learning, we are able to achieve good results in a much smaller runtime by learning from a dataset generated by these planners. While our initial model uses point cloud embeddings in the input to predict keypoint-based joint sequences in its output, we observed in our ablation study that it remained challenging to condition the network on the point cloud embeddings. We identified some biases in our dataset and refined it, which improved the model’s performance. Our model, even without the use of the point cloud encodings, outperforms numerical models by an order of magnitude regarding the runtime, while reaching a success rate of up to 90% of collision free solutions on the test set. Read More
MTQA:Matrix of Thought for Enhanced Reasoning in Complex Question Answeringcs.AI updates on arXiv.orgon September 5, 2025 at 4:00 am arXiv:2509.03918v1 Announce Type: cross
Abstract: Complex Question Answering (QA) is a fundamental and challenging task in NLP. While large language models (LLMs) exhibit impressive performance in QA, they suffer from significant performance degradation when facing complex and abstract QA tasks due to insufficient reasoning capabilities. Works such as Chain-of-Thought (CoT) and Tree-of-Thought (ToT) aim to enhance LLMs’ reasoning abilities, but they face issues such as in-layer redundancy in tree structures and single paths in chain structures. Although some studies utilize Retrieval-Augmented Generation (RAG) methods to assist LLMs in reasoning, the challenge of effectively utilizing large amounts of information involving multiple entities and hops remains critical. To address this, we propose the Matrix of Thought (MoT), a novel and efficient LLM thought structure. MoT explores the problem in both horizontal and vertical dimensions through the “column-cell communication” mechanism, enabling LLMs to actively engage in multi-strategy and deep-level thinking, reducing redundancy within the column cells and enhancing reasoning capabilities. Furthermore, we develop a fact-correction mechanism by constructing knowledge units from retrieved knowledge graph triples and raw text to enhance the initial knowledge for LLM reasoning and correct erroneous answers. This leads to the development of an efficient and accurate QA framework (MTQA). Experimental results show that our framework outperforms state-of-the-art methods on four widely-used datasets in terms of F1 and EM scores, with reasoning time only 14.4% of the baseline methods, demonstrating both its efficiency and accuracy. The code for this framework is available at https://github.com/lyfiter/mtqa.
arXiv:2509.03918v1 Announce Type: cross
Abstract: Complex Question Answering (QA) is a fundamental and challenging task in NLP. While large language models (LLMs) exhibit impressive performance in QA, they suffer from significant performance degradation when facing complex and abstract QA tasks due to insufficient reasoning capabilities. Works such as Chain-of-Thought (CoT) and Tree-of-Thought (ToT) aim to enhance LLMs’ reasoning abilities, but they face issues such as in-layer redundancy in tree structures and single paths in chain structures. Although some studies utilize Retrieval-Augmented Generation (RAG) methods to assist LLMs in reasoning, the challenge of effectively utilizing large amounts of information involving multiple entities and hops remains critical. To address this, we propose the Matrix of Thought (MoT), a novel and efficient LLM thought structure. MoT explores the problem in both horizontal and vertical dimensions through the “column-cell communication” mechanism, enabling LLMs to actively engage in multi-strategy and deep-level thinking, reducing redundancy within the column cells and enhancing reasoning capabilities. Furthermore, we develop a fact-correction mechanism by constructing knowledge units from retrieved knowledge graph triples and raw text to enhance the initial knowledge for LLM reasoning and correct erroneous answers. This leads to the development of an efficient and accurate QA framework (MTQA). Experimental results show that our framework outperforms state-of-the-art methods on four widely-used datasets in terms of F1 and EM scores, with reasoning time only 14.4% of the baseline methods, demonstrating both its efficiency and accuracy. The code for this framework is available at https://github.com/lyfiter/mtqa. Read More
Designing Gaze Analytics for ELA Instruction: A User-Centered Dashboard with Conversational AI Supportcs.AI updates on arXiv.orgon September 5, 2025 at 4:00 am arXiv:2509.03741v1 Announce Type: cross
Abstract: Eye-tracking offers rich insights into student cognition and engagement, but remains underutilized in classroom-facing educational technology due to challenges in data interpretation and accessibility. In this paper, we present the iterative design and evaluation of a gaze-based learning analytics dashboard for English Language Arts (ELA), developed through five studies involving teachers and students. Guided by user-centered design and data storytelling principles, we explored how gaze data can support reflection, formative assessment, and instructional decision-making. Our findings demonstrate that gaze analytics can be approachable and pedagogically valuable when supported by familiar visualizations, layered explanations, and narrative scaffolds. We further show how a conversational agent, powered by a large language model (LLM), can lower cognitive barriers to interpreting gaze data by enabling natural language interactions with multimodal learning analytics. We conclude with design implications for future EdTech systems that aim to integrate novel data modalities in classroom contexts.
arXiv:2509.03741v1 Announce Type: cross
Abstract: Eye-tracking offers rich insights into student cognition and engagement, but remains underutilized in classroom-facing educational technology due to challenges in data interpretation and accessibility. In this paper, we present the iterative design and evaluation of a gaze-based learning analytics dashboard for English Language Arts (ELA), developed through five studies involving teachers and students. Guided by user-centered design and data storytelling principles, we explored how gaze data can support reflection, formative assessment, and instructional decision-making. Our findings demonstrate that gaze analytics can be approachable and pedagogically valuable when supported by familiar visualizations, layered explanations, and narrative scaffolds. We further show how a conversational agent, powered by a large language model (LLM), can lower cognitive barriers to interpreting gaze data by enabling natural language interactions with multimodal learning analytics. We conclude with design implications for future EdTech systems that aim to integrate novel data modalities in classroom contexts. Read More
Boosting Your Anomaly Detection With LLMsTowards Data Scienceon September 4, 2025 at 1:00 pm The 7 emerging application patterns you should know
The post Boosting Your Anomaly Detection With LLMs appeared first on Towards Data Science.
The 7 emerging application patterns you should know
The post Boosting Your Anomaly Detection With LLMs appeared first on Towards Data Science. Read More
Switzerland releases 100% open AI modelAI Newson September 4, 2025 at 9:39 am A group of Swiss institutions has released a new open AI model, designed to serve as a foundation for future research and applications. Built by EPFL, ETH Zurich, and the Swiss National Supercomputing Centre (CSCS), the model is called Apertus – Latin for “open.” The name reflects its core principle: every part of its design
The post Switzerland releases 100% open AI model appeared first on AI News.
A group of Swiss institutions has released a new open AI model, designed to serve as a foundation for future research and applications. Built by EPFL, ETH Zurich, and the Swiss National Supercomputing Centre (CSCS), the model is called Apertus – Latin for “open.” The name reflects its core principle: every part of its design
The post Switzerland releases 100% open AI model appeared first on AI News. Read More
Synthesia’s AI clones are more expressive than ever. Soon they’ll be able to talk back.MIT Technology Reviewon September 4, 2025 at 10:05 am Earlier this summer, I walked through the glassy lobby of a fancy office in London, into an elevator, and then along a corridor into a clean, carpeted room. Natural light flooded in through its windows, and a large pair of umbrella-like lighting rigs made the room even brighter. I tried not to squint as I…
Earlier this summer, I walked through the glassy lobby of a fancy office in London, into an elevator, and then along a corridor into a clean, carpeted room. Natural light flooded in through its windows, and a large pair of umbrella-like lighting rigs made the room even brighter. I tried not to squint as I… Read More
Multi-level SSL Feature Gating for Audio Deepfake Detectioncs.AI updates on arXiv.orgon September 4, 2025 at 4:00 am arXiv:2509.03409v1 Announce Type: cross
Abstract: Recent advancements in generative AI, particularly in speech synthesis, have enabled the generation of highly natural-sounding synthetic speech that closely mimics human voices. While these innovations hold promise for applications like assistive technologies, they also pose significant risks, including misuse for fraudulent activities, identity theft, and security threats. Current research on spoofing detection countermeasures remains limited by generalization to unseen deepfake attacks and languages. To address this, we propose a gating mechanism extracting relevant feature from the speech foundation XLS-R model as a front-end feature extractor. For downstream back-end classifier, we employ Multi-kernel gated Convolution (MultiConv) to capture both local and global speech artifacts. Additionally, we introduce Centered Kernel Alignment (CKA) as a similarity metric to enforce diversity in learned features across different MultiConv layers. By integrating CKA with our gating mechanism, we hypothesize that each component helps improving the learning of distinct synthetic speech patterns. Experimental results demonstrate that our approach achieves state-of-the-art performance on in-domain benchmarks while generalizing robustly to out-of-domain datasets, including multilingual speech samples. This underscores its potential as a versatile solution for detecting evolving speech deepfake threats.
arXiv:2509.03409v1 Announce Type: cross
Abstract: Recent advancements in generative AI, particularly in speech synthesis, have enabled the generation of highly natural-sounding synthetic speech that closely mimics human voices. While these innovations hold promise for applications like assistive technologies, they also pose significant risks, including misuse for fraudulent activities, identity theft, and security threats. Current research on spoofing detection countermeasures remains limited by generalization to unseen deepfake attacks and languages. To address this, we propose a gating mechanism extracting relevant feature from the speech foundation XLS-R model as a front-end feature extractor. For downstream back-end classifier, we employ Multi-kernel gated Convolution (MultiConv) to capture both local and global speech artifacts. Additionally, we introduce Centered Kernel Alignment (CKA) as a similarity metric to enforce diversity in learned features across different MultiConv layers. By integrating CKA with our gating mechanism, we hypothesize that each component helps improving the learning of distinct synthetic speech patterns. Experimental results demonstrate that our approach achieves state-of-the-art performance on in-domain benchmarks while generalizing robustly to out-of-domain datasets, including multilingual speech samples. This underscores its potential as a versatile solution for detecting evolving speech deepfake threats. Read More
AI FOMO, Shadow AI, and Other Business ProblemsTowards Data Scienceon September 4, 2025 at 12:22 am What’s the state of AI in business these days, and how much does it cost us?
The post AI FOMO, Shadow AI, and Other Business Problems appeared first on Towards Data Science.
What’s the state of AI in business these days, and how much does it cost us?
The post AI FOMO, Shadow AI, and Other Business Problems appeared first on Towards Data Science. Read More
Useful Python Libraries You Might Not Have Heard Of: FreezegunTowards Data Scienceon September 4, 2025 at 12:30 am Bring time to a standstill in your Python tests
The post Useful Python Libraries You Might Not Have Heard Of: Freezegun appeared first on Towards Data Science.
Bring time to a standstill in your Python tests
The post Useful Python Libraries You Might Not Have Heard Of: Freezegun appeared first on Towards Data Science. Read More
