arXiv:2511.08399v2 Announce Type: replace Abstract: Most multimodal models treat every negative pair alike, ignoring the ambiguous negatives that differ from the positive by only a small detail. We propose Boundary-Aware Curriculum with Local Attention (BACL), a lightweight add-on that turns…
arXiv:2601.07878v1 Announce Type: new Abstract: The benefits of most large language models come with steep and often hidden economic and environmental costs due to their resource usage inefficiency during deployment. Model quantization improves energy and memory efficiency through representing model…
arXiv:2412.19217v4 Announce Type: replace Abstract: The rapid expansion of citizen science initiatives has led to a significant growth of biodiversity databases, and particularly presence-only (PO) observations. PO data are invaluable for understanding species distributions and their dynamics, but their use…
arXiv:2601.07876v1 Announce Type: new Abstract: This work introduces NOVAK, a modular gradient-based optimization algorithm that integrates adaptive moment estimation, rectified learning-rate scheduling, decoupled weight regularization, multiple variants of Nesterov momentum, and lookahead synchronization into a unified, performance-oriented framework. NOVAK adopts…
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…
arXiv:2601.07873v1 Announce Type: new Abstract: Knowledge editing aims to efficiently modify the internal knowledge of large language models (LLMs) without compromising their other capabilities. The prevailing editing paradigm, which appends an update matrix to the original parameter matrix, has been…
arXiv:2601.07870v1 Announce Type: new Abstract: Periodic activations such as sine preserve high-frequency information in implicit neural representations (INRs) through their oscillatory structure, but often suffer from gradient instability and limited control over multi-scale behavior. We introduce the Hyperbolic Oscillator with…
arXiv:2601.07868v1 Announce Type: new Abstract: Dominant sequence models like the Transformer represent structure implicitly through dense attention weights, incurring quadratic complexity. We propose RewriteNets, a novel neural architecture built on an alternative paradigm: explicit, parallel string rewriting. Each layer in…
arXiv:2601.08705v1 Announce Type: cross Abstract: Multi-behavior recommendation faces a critical challenge in practice: auxiliary behaviors (e.g., clicks, carts) are often noisy, weakly correlated, or semantically misaligned with the target behavior (e.g., purchase), which leads to biased preference learning and suboptimal…
arXiv:2601.07886v1 Announce Type: new Abstract: In this paper, we develop a multivariate framework for approximation by max-min neural network operators. Building on the recent advances in approximation theory by neural network operators, particularly, the univariate max-min operators, we propose and…
