Although deep neural networks perform extremely well in controlled environments, they fail in real-world scenarios where data isn’t available all at once, and the model must adapt to a new data distribution that may or may not follow the initial distribution. Previously acquired knowledge is lost during subsequent updates based on new data. a phenomenon commonly known as catastrophic forgetting. In contrast, the brain can learn without such catastrophic forgetting, irrespective of the number of tasks it encounters. […]

Ver mais

arXiv:2603.13674v1 Announce Type: cross Abstract: Most machine learning methods assume fixed probability distributions, limiting their applicability in nonstationary real-world scenarios. While continual learning methods address this issue, current approaches often rely on black-box models or require extensive user intervention for interpretability. We propose SyMPLER (Systems Modeling through Piecewise Linear Evolving Regression), an explainable model for time series forecasting in nonstationary environments based on dynamic piecewise-linear approximations. Unlike other locally linear models, SyMPLER uses generalization bounds from Statistical Learning […]

Ver mais

What if future AIs achieved enlightenment before world domination? Shanahan suggests a truly advanced AI might transcend the human ego, dropping our obsession with the “self.” Instead of triggering a runaway intelligence explosion, such a being could attain satori: a Zen-like peace that halts the singularity in its tracks.

Ver mais

The second birthday of ChatGPT was only a little over a month ago, and now we have transitioned into the next paradigm of models that can do complex reasoning. New years get people in a reflective mood, and I wanted to share some personal thoughts about how it has gone so far, and some of the things I’ve learned along the way. As we get closer to AGI, it feels like an important time to look at the […]

Ver mais

arXiv:2601.20867v1 Announce Type: new Abstract: Prompt tuning has achieved remarkable progress in vision-language models (VLMs) and is recently being adopted for audio-language models (ALMs). However, its generalization ability in ALMs remains largely underexplored. We observe that conventional prompt tuning for ALMs also suffers from the Base-New Tradeoff, and we identify that this issue stems from the disrupted semantic structure of the embedding space. To address this issue, we propose Semantically Expanded Prompt Tuning (SEPT)-a plug-and-play framework that explicitly […]

Ver mais

arXiv:2603.03375v1 Announce Type: new Abstract: In 2018, McInnes et al. introduced a dimensionality reduction algorithm called UMAP, which enjoys wide popularity among data scientists. Their work introduces a finite variant of a functor called the metric realization, based on an unpublished draft by Spivak. This draft contains many errors, most of which are reproduced by McInnes et al. and subsequent publications. This article aims to repair these errors and provide a self-contained document with the full derivation of […]

Ver mais

arXiv:2603.02329v1 Announce Type: new Abstract: Humans commonly identify 3D object affordance through observed interactions in images or videos, and once formed, such knowledge can be generically generalized to novel objects. Inspired by this principle, we advocate for a novel framework that leverages emerging multimodal large language models (MLLMs) for interaction intention-driven 3D affordance grounding, namely HAMMER. Instead of generating explicit object attribute descriptions or relying on off-the-shelf 2D segmenters, we alternatively aggregate the interaction intention depicted in the […]

Ver mais

If you have shipped a serious Angular app in the last few years, you probably have BehaviorSubjects, selector streams, and NgRx slices everywhere—and no one on the team is excited to refactor them. With Angular 19+, Signals are no longer experimental or “nice to have.” They are stable, performant, and increasingly treated as the default way to model local state. As a result, many Angular teams are actively revisiting long-standing RxJS and NgRx patterns—sometimes rewriting them entirely—while community discussions are filled […]

Ver mais

arXiv:2601.14258v1 Announce Type: new Abstract: Traditional text-to-motion frameworks often lack precise control, and existing approaches based on joint keyframe locations provide only positional guidance, making it challenging and unintuitive to specify body part orientations and motion timing. To address these limitations, we introduce the Salient Orientation Symbolic (SOS) script, a programmable symbolic framework for specifying body part orientations and motion timing at keyframes. We further propose an automatic SOS extraction pipeline that employs temporally-constrained agglomerative clustering for frame […]

Ver mais