arXiv:2601.07877v1 Announce Type: new Abstract: Emotion recognition from electroencephalography (EEG) signals remains challenging due to high inter-subject variability, limited labeled data, and the lack of interpretable reasoning in existing approaches. While recent multimodal large language models (MLLMs) have advanced emotion analysis, they have not been adapted to handle the unique spatiotemporal characteristics of neural signals. We present E^2-LLM (EEG-to-Emotion Large Language Model), the first MLLM framework for interpretable emotion analysis from EEG. E^2-LLM integrates a pretrained EEG encoder […]

Ver mais

arXiv:2601.17072v1 Announce Type: new Abstract: Almost every industry today confronts the potential role of artificial intelligence and machine learning in its future. While many studies examine AI in consumer marketing, less attention addresses AI’s role in creating and selecting trademarks that are distinctive, recognizable, and meaningful to consumers. Traditional economic approaches to trademarks focus almost exclusively on consumer-based, demand-side considerations regarding search. However, these approaches are incomplete because they fail to account for substantial costs faced not just […]

Ver mais

I started just now researching the field of machine learning applied to task scheduling. I have been trying to schedule up to 50 tasks using RL but had no success. My idea is then scale the approach for multi-agent task scheduling. My reward is based on the -agent total distance, as in some papers, and I’m using PPO. My observation space includes the distances between tasks, and position of the tasks. Do you have any suggestions on what […]

Ver mais

Label distribution learning (LDL) requires the learner to predict the degree of correlation between each sample and each label. To achieve this, a crucial task during learning is to leverage the correlation among labels. Deep Forest (DF) is a deep learning framework based on tree ensembles, whose training phase does not rely on backpropagation. DF performs in-model feature transform using the prediction of each layer and achieves competitive performance on many tasks. However, its exploration in the field […]

Ver mais

arXiv:2506.11743v2 Announce Type: replace-cross Abstract: Graph coarsening aims to diminish the size of a graph to lighten its memory footprint, and has numerous applications in graph signal processing and machine learning. It is usually defined using a reduction matrix and a lifting matrix, which, respectively, allows to project a graph signal from the original graph to the coarsened one and back. This results in a loss of information measured by the so-called Restricted Spectral Approximation (RSA). Most coarsening […]

Ver mais

So sharing some of our work we published at NeurIPS 2025 as a Spotlight. Weights and code are public (see ArXiv). TL;DR: Vision Transformers typically have artifacts in their dense features. While the exact reason is unknown, there is consensus that adding so called “register” tokens mitigates this issue. These tokens participate in the self-attention process, but are not used for the output. When introduced with DINOv2 models in ICLR 2024, this requires vision transformers to be trained […]

Ver mais

If you tell a friend they can now instantly create any app, they’ll probably say “Cool! Now I need to think of an idea.” Then they will forget about it, and never build a thing. The problem is not that your friend is horribly uncreative. It’s that most people’s problems are not software-shaped, and most won’t notice even when they are. […] Programmers are trained to see everything as a software-shaped problem: if you do a task three […]

Ver mais

Detecting anomalous trajectories in decentralized crypto networks is fundamentally challenged by extreme label scarcity and the adaptive evasion strategies of illicit actors. While Graph Neural Networks (GNNs) effectively capture local structural patterns, they struggle to internalize multi hop, logic driven motifs such as fund dispersal and layering that characterize sophisticated money laundering, limiting their forensic accountability under regulations like the FATF Travel Rule. To address this limitation, we propose Relational Domain Logic Integration (RDLI), a framework that embeds […]

Ver mais

arXiv:2602.06207v1 Announce Type: new Abstract: Wireless capsule endoscopy (WCE) has transformed gastrointestinal (GI) diagnostics by enabling noninvasive visualization of the digestive tract, yet its diagnostic yield remains constrained by the absence of biopsy capability, as histological analysis is still the gold standard for confirming disease. Conventional biopsy using forceps, needles, or rotating blades is invasive, limited in reach, and carries risks of perforation or mucosal trauma, while fluid- or microbiota-sampling capsules cannot provide structured tissue for pathology, leaving […]

Ver mais