arXiv:2603.22292v1 Announce Type: new Abstract: Sequential decision making using Markov Decision Process underpins many realworld applications. Both model-based and model free methods have achieved strong results in these settings. However, real-world tasks must balance reward maximization with safety constraints, often conflicting objectives, that can lead to unstable min/max, adversarial optimization. A promising alternative is safety reachability analysis, which precomputes a forward-invariant safe state, action set, ensuring that an agent starting inside this set remains safe indefinitely. Yet, most […]

Ver mais

arXiv:2603.00643v1 Announce Type: new Abstract: This position paper argues that the evaluation of modern visual processing systems should no longer be driven primarily by single-metric image quality assessment benchmarks, particularly in the era of generative and perception-oriented methods. Image restoration exemplifies this divergence: while objective IQA metrics enable reproducible, scalable evaluation, they have increasingly drifted apart from human perception and user preferences. We contend that this mismatch risks constraining innovation and misguiding research progress across visual processing tasks. […]

Ver mais

For years, we’ve treated coding interviews as the gateway to software engineering. Solve a few algorithm problems under pressure, and you’re “in.” Struggle with them, and suddenly your ability as an engineer is questioned. But here’s the uncomfortable truth: LeetCode-style interviews have never been a reliable measure of engineering skill. At best, they’re a hit-or-miss signal. Sometimes you’re in the zone. Sometimes the pressure gets to you. Sometimes you’ve seen a similar problem before. Sometimes you blank out […]

Ver mais

Multimodal-attributed graphs (MMAGs) provide a unified framework for modeling complex relational data by integrating heterogeneous modalities with graph structures. While centralized learning has shown promising performance, MMAGs in real-world applications are often distributed across isolated platforms and cannot be shared due to privacy concerns or commercial constraints. Federated graph learning (FGL) offers a natural solution for collaborative training under such settings; however, existing studies largely focus on single-modality graphs and do not adequately address the challenges unique to […]

Ver mais

We describe the evolution of DEMOCRITUS, a system for inferring causality from language. Extracting causal claims from natural language is unstable under paraphrase granularity shifts, and context drift. A document collection may express the same causal statement in many surface forms, while neighboring studies may agree locally yet fail to glue globally because relation families or polarities change across regimes. This paper studies that problem through successive versions of DEMOCRITUS, an implemented system for compiling documents into local […]

Ver mais

arXiv:2602.09720v1 Announce Type: new Abstract: Data streams are rarely static in dynamic environments like Industry 4.0. Instead, they constantly change, making traditional offline models outdated unless they can quickly adjust to the new data. This need can be adequately addressed by continual learning (CL), which allows systems to gradually acquire knowledge without incurring the prohibitive costs of retraining them from scratch. Most research on continual learning focuses on classification problems, while very few studies address regression tasks. We […]

Ver mais

arXiv:2601.12156v1 Announce Type: new Abstract: The deployment of Artificial Intelligence on edge devices (TinyML) is often constrained by the high power consumption and latency associated with traditional Artificial Neural Networks (ANNs) and their reliance on intensive Matrix-Multiply (MAC) operations. Neuromorphic computing offers a compelling alternative by mimicking biological efficiency through event-driven processing. This paper presents the design and implementation of a cycle-accurate, hardware-oriented Spiking Neural Network (SNN) core implemented in SystemVerilog. Unlike conventional accelerators, this design utilizes a […]

Ver mais

arXiv:2602.17706v1 Announce Type: new Abstract: Modeling long-range dependencies in time series generation poses a fundamental trade-off between representational capacity and computational efficiency. Traditional temporal diffusion models suffer from local entanglement and the $mathcal{O}(L^2)$ cost of attention mechanisms. We address these limitations by introducing PaCoDi (Parallel Complex Diffusion), a spectral-native architecture that decouples generative modeling in the frequency domain. PaCoDi fundamentally alters the problem topology: the Fourier Transform acts as a diagonalizing operator, converting locally coupled temporal signals into […]

Ver mais