arXiv:2602.13315v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) have demonstrated impressive capabilities, yet they encounter significant computational bottlenecks due to the massive volume of visual tokens. Consequently, visual token pruning, which substantially reduces the token count, has emerged as a critical technique for accelerating MLLM inference. Existing approaches focus on token importance, diversity, or an intuitive combination of both, without a principled framework for their optimal integration. To address this issue, we first conduct a systematic […]

Ver mais

arXiv:2602.06155v1 Announce Type: cross Abstract: Diffusion models rely on a high-dimensional latent space of initial noise seeds, yet it remains unclear whether this space contains sufficient structure to predict properties of the generated samples, such as their classes. In this work, we investigate the emergence of latent structure through the lens of confidence scores assigned by a pre-trained classifier to generated samples. We show that while the latent space appears largely unstructured when considering all noise realizations, restricting […]

Ver mais

arXiv:2602.03169v1 Announce Type: new Abstract: Clustering functional data in the presence of phase variation is challenging, as temporal misalignment can obscure intrinsic shape differences and degrade clustering performance. Most existing approaches treat registration and clustering as separate tasks or rely on restrictive parametric assumptions. We present textbf{NeuralFLoC}, a fully unsupervised, end-to-end deep learning framework for joint functional registration and clustering based on Neural ODE-driven diffeomorphic flows and spectral clustering. The proposed model learns smooth, invertible warping functions and […]

Ver mais

arXiv:2601.18979v1 Announce Type: new Abstract: Extended Reality in early childhood education presents high-risk challenges due to children’s rapid developmental changes. While augmented and virtual reality offer immersive pedagogical benefits, they often impose excessive cognitive load or sensory conflict. We introduce the Augmented Human Development (AHD) framework to model these interactions through cognitive, sensory, environmental, and developmental parameters. To ground this framework, we conducted a Systematization of Knowledge (SoK) of 111 peer-reviewed studies involving children aged 3 – 8. […]

Ver mais

The pharmaceutical sector has historically been characterized by slow, costly, and uncertain innovation cycles. Creating a single drug can easily take more than a decade, and it requires billions of dollars in investment with no certain return. Novo Nordisk’s new deal with OpenAI represents a shift not only in tools but also mindset. Artificial intelligence is no longer being treated as an add-on, it’s becoming crucial to how new drugmakers do business.  This partnership comes at a time […]

Ver mais

arXiv:2507.06969v4 Announce Type: replace-cross Abstract: Differentially private (DP) mechanisms are difficult to interpret and calibrate because existing methods for mapping standard privacy parameters to concrete privacy risks — re-identification, attribute inference, and data reconstruction — are both overly pessimistic and inconsistent. In this work, we use the hypothesis-testing interpretation of DP ($f$-DP), and determine that bounds on attack success can take the same unified form across re-identification, attribute inference, and data reconstruction risks. Our unified bounds are (1) […]

Ver mais

Semantic associations such as the link between "bird" and "flew" are foundational for language modeling as they enable models to go beyond memorization and instead generalize and generate coherent text. Understanding how these associations are learned and represented in language models is essential for connecting deep learning with linguistic theory and developing a mechanistic foundation for large language models. In this work, we analyze how these associations emerge from natural language data in attention-based language models through the […]

Ver mais

arXiv:2602.22217v1 Announce Type: new Abstract: Retrieval-Augmented Generation (RAG) has established itself as the standard paradigm for grounding Large Language Models (LLMs) in domain-specific, up-to-date data. However, the prevailing architecture for RAG has evolved into a complex, distributed stack requiring cloud-hosted vector databases, heavy deep learning frameworks (e.g., PyTorch, CUDA), and high-latency embedding inference servers. This “infrastructure bloat” creates a significant barrier to entry for edge computing, air-gapped environments, and privacy-constrained applications where data sovereignty is paramount. This paper […]

Ver mais

Federated Learning (FL) enables collaborative model training across multiple clients without sharing their private data. However, data heterogeneity across clients leads to client drift, which degrades the overall generalization performance of the model. This effect is further compounded by overemphasis on poorly performing clients. To address this problem, we propose FedVG, a novel gradient-based federated aggregation framework that leverages a global validation set to guide the optimization process. Such a global validation set can be established using readily […]

Ver mais