This 2nd episode on a 2 part series analyzes how GenAI has evolved to deliver automation through AI Agents and Agentic AI. It highlights the differences between both of them citing many sources from IBM, Anthropic McKinsey and Gartner amongst others as well as their best use cases and differences and also mentioning some of the risks. 1. Generative AI (GenAI) Generative AI refers to reactive systems that wait for user input, typically a prompt, to generate content1. […]

Ver mais

arXiv:2403.20200v4 Announce Type: replace-cross Abstract: High-dimensional linear regression has been thoroughly studied in the context of independent and identically distributed data. We propose to investigate high-dimensional regression models for independent but non-identically distributed data. To this end, we suppose that the set of observed predictors (or features) is a random matrix with a variance profile and with dimensions growing at a proportional rate. Assuming a random effect model, we study the predictive risk of the ridge estimator for […]

Ver mais

arXiv:2601.08073v1 Announce Type: new Abstract: For a (possibly partial) Boolean function $fcolon{0,1}^nto{0,1}$ as well as a query complexity measure $M$ which maps Boolean functions to real numbers, define the composition limit of $M$ on $f$ by $M^*(f)=lim_{ktoinfty} M(f^k)^{1/k}$. We study the composition limits of general measures in query complexity. We show this limit converges under reasonable assumptions about the measure. We then give a surprising result regarding the composition limit of randomized query complexity: we show $R_0^*(f)=max{R^*(f),C^*(f)}$. Among […]

Ver mais

Molecular property prediction constitutes a cornerstone of drug discovery and materials science, necessitating models capable of disentangling complex structure-property relationships across diverse molecular modalities. Existing approaches frequently exhibit entangled representations–conflating structural, chemical, and functional factors–thereby limiting interpretability and transferability. Furthermore, conventional methods inadequately exploit complementary information from graphs, sequences, and geometries, often relying on naive concatenation that neglects inter-modal dependencies. In this work, we propose DMMRL, which employs variational autoencoders to disentangle molecular representations into shared (structure-relevant) and […]

Ver mais

arXiv:2601.03447v1 Announce Type: new Abstract: Water level monitoring is critical for flood management, water resource allocation, and ecological assessment, yet traditional methods remain costly and limited in coverage. This work explores radar-based sensing as a low-cost alternative for water level estimation, leveraging its non-contact nature and robustness to environmental conditions. Commercial radar sensors are evaluated in real-world field tests, applying statistical filtering techniques to improve accuracy. Results show that a single radar sensor can achieve centimeter-scale precision with […]

Ver mais

arXiv:2601.17093v1 Announce Type: new Abstract: Comparing neural network representations is essential for understanding and validating models in scientific applications. Existing methods, however, often provide a limited view. We propose the Triangle of Similarity, a framework that combines three complementary perspectives: static representational similarity (CKA/Procrustes), functional similarity (Linear Mode Connectivity or Predictive Similarity), and sparsity similarity (robustness under pruning). Analyzing a range of CNNs, Vision Transformers, and Vision-Language Models using both in-distribution (ImageNetV2) and out-of-distribution (CIFAR-10) testbeds, our initial […]

Ver mais

arXiv:2603.07437v1 Announce Type: cross Abstract: We study the problem of state representation learning for control from partial and potentially high-dimensional observations. We approach this problem via cost-driven state representation learning, in which we learn a dynamical model in a latent state space by predicting cumulative costs. In particular, we establish finite-sample guarantees on finding a near-optimal representation function and a near-optimal controller using the learned latent model for infinite-horizon time-invariant Linear Quadratic Gaussian (LQG) control. We study two […]

Ver mais

Optimal power flow (OPF) is one of the fundamental tasks for power system operations. While machine learning (ML) approaches such as deep neural networks (DNNs) have been widely studied to enhance OPF solution speed and performance, their practical deployment faces two critical scaling questions: What is the minimum training data volume required for reliable results? How should ML models’ complexity balance accuracy with real-time computational limits? Existing studies evaluate discrete scenarios without quantifying these scaling relationships, leading to […]

Ver mais

arXiv:2604.02431v1 Announce Type: new Abstract: Retrieving relevant past interactions from long-term conversational memory typically relies on large dense retrieval models (110M-1.5B parameters) or LLM-augmented indexing. We introduce SelRoute, a framework that routes each query to a specialized retrieval pipeline — lexical, semantic, hybrid, or vocabulary-enriched — based on its query type. On LongMemEval_M (Wu et al., 2024), SelRoute achieves Recall@5 of 0.800 with bge-base-en-v1.5 (109M parameters) and 0.786 with bge-small-en-v1.5 (33M parameters), compared to 0.762 for Contriever with […]

Ver mais

In one of his earliest writings on the topic, Teilhard de Chardin explores humanity’s unique place in evolution. He argues that humans represent an entirely new phase of life on Earth—the , or sphere of conscious thought. While physically similar to other primates, humans are revolutionary in their ability to use tools, form global connections, and reflect on their own existence. This self-awareness comes with both great power and great risk, as humans can choose to either advance […]

Ver mais