Hiring talented people with the right attitude and right skills is not enough, they also need the right environment to thrive—are leaders in the organization only focused on business deliverables or do they also invest in their team’s learning and growth? Do they encourage people to speak up and share their disagreements or do they shut down voices that differ with their own perspective? Are people in the team clear on their priorities and aligned with a long-term […]

Ver mais

Catastrophic forgetting during knowledge injection severely undermines the continual learning capability of large language models (LLMs). Although existing methods attempt to mitigate this issue, they often lack a foundational theoretical explanation. We establish a gradient-based theoretical framework to explain catastrophic forgetting. We first prove that strongly negative gradient similarity is a fundamental cause of forgetting. We then use gradient similarity to identify two types of neurons: conflicting neurons that induce forgetting and account for 50%-75% of neurons, and […]

Ver mais

Score-based generative models have recently achieved remarkable success. While they are usually parameterized by the score, an alternative way is to use a series of time-dependent energy-based models (EBMs), where the score is obtained from the negative input-gradient of the energy. Crucially, EBMs can be leveraged not only for generation, but also for tasks such as compositional sampling or building Boltzmann Generators via Monte Carlo methods. However, training EBMs remains challenging. Direct maximum likelihood is computationally prohibitive due […]

Ver mais

arXiv:2603.03418v1 Announce Type: new Abstract: Recently, DeepSeek has invented the manifold-constrained hyper-connection (mHC) approach which has demonstrated significant improvements over the traditional residual connection in deep learning models cite{xie2026mhc}. Nevertheless, this approach has not been tailor-designed for improving hyperspectral image (HSI) classification. This paper presents a clustering-guided mHC Mamba model (mHC-HSI) for enhanced HSI classification, with the following contributions. First, to improve spatial-spectral feature learning, we design a novel clustering-guided Mamba module, based on the mHC framework, that […]

Ver mais

arXiv:2601.19029v1 Announce Type: new Abstract: Automated piano performance evaluation traditionally relies on symbolic (MIDI) representations, which capture note-level information but miss the acoustic nuances that characterize expressive playing. I propose using pre-trained audio foundation models, specifically MuQ and MERT, to predict 19 perceptual dimensions of piano performance quality. Using synthesized audio from PercePiano MIDI files (rendered via Pianoteq), I compare audio and symbolic approaches under controlled conditions where both derive from identical source data. The best model, MuQ […]

Ver mais

How are you, hacker? 🪐 What’s happening in tech today, April 18, 2026? The HackerNoon Newsletter brings the HackerNoon homepage straight to your inbox. On this day, Osborne Computer introduced in 1983, and we present you with these top quality stories. From What Ghost Murmur Technology Actually Is (Its Not a Heartbeat Detector) to The Proof of Usefulness Algorithm: Is It Good? Do People Use It?, let’s dive right in. What Ghost Murmur Technology Actually Is (Its Not […]

Ver mais

arXiv:2601.00193v1 Announce Type: new Abstract: This paper proposes a temporal two-grid compact difference (TTCD) scheme for solving the Benjamin-Bona-Mahony-Burgers (BBMB) equation with initial and periodic boundary conditions. The method consists of three main steps: first, solving a nonlinear system on a coarse time grid of size $tau_c$; then obtaining a coarse approximation on the fine time grid of size $tau_f$ via linear Lagrange interpolation; and finally solving a linearized scheme on the fine grid to obtain the corrected […]

Ver mais

arXiv:2603.06723v1 Announce Type: new Abstract: Invisible watermarks, as an essential technology for image copyright protection, have been widely deployed with the rapid development of social media and AIGC. However, existing invisible watermark detection heavily relies on prior knowledge of specific algorithms, leading to limited detection capabilities for “unknown watermarks” in open environments. To this end, we propose a novel task named Universal Watermark Presence Detection (UWPD), which aims to identify whether an image carries a copyright mark without […]

Ver mais

arXiv:2602.23410v1 Announce Type: new Abstract: Brain foundation models have achieved remarkable advances across a wide range of neuroscience tasks. However, most existing models are limited to a single functional modality, restricting their ability to exploit complementary spatiotemporal dynamics and the collective data scale across imaging techniques. To address this limitation, we propose Brain-OF, the first omnifunctional brain foundation model jointly pretrained on fMRI, EEG and MEG, capable of handling both unimodal and multimodal inputs within a unified framework. […]

Ver mais

We study uniform computability properties of PAC learning using Weihrauch complexity. We focus on closed concept classes, which are either represented by positive, by negative or by full information. Among other results, we prove that proper PAC learning from positive information is equivalent to the limit operation on Baire space, whereas improper PAC learning from positive information is closely related to Weak Kőnig’s Lemma and even equivalent to it, when we have some negative information about the admissible […]

Ver mais