arXiv:2511.16976v2 Announce Type: replace-cross Abstract: Deep equilibrium models (DEQs) have recently emerged as a powerful paradigm for training infinitely deep weight-tied neural networks that achieve state of the art performance across many modern machine learning tasks. Despite their practical success, theoretically understanding the gradient descent dynamics for training DEQs remains an area of active research. In this work, we rigorously study the gradient descent dynamics for DEQs in the simple setting of linear models and single-index models, filling […]

Ver mais

arXiv:2012.07784v2 Announce Type: replace Abstract: Inference and forecast problems of the nonlinear dynamical system have arisen in a variety of contexts. Reservoir computing and deep sequential models, on the one hand, have demonstrated efficient, robust, and superior performance in modeling simple and chaotic dynamical systems. However, their innate deterministic feature has partially detracted their robustness to noisy system, and their inability to offer uncertainty measurement has also been an insufficiency of the framework. On the other hand, the […]

Ver mais

Relational Databases (RDBs) are the backbone of modern business, yet they lack foundation models comparable to those in text or vision. A key obstacle is that high-quality RDBs are private, scarce and structurally heterogeneous, making internet-scale pre-training infeasible. To overcome this data scarcity, We introduce $textbf{RDB-PFN}$, the first relational foundation model trained purely via $textbf{synthetic data}$. Inspired by Prior-Data Fitted Networks (PFNs) where synthetic data generated from Structural Causal Models (SCMs) enables reasoning on single tables, we design […]

Ver mais

arXiv:2602.06297v1 Announce Type: new Abstract: Given that machine learning algorithms are increasingly being deployed to aid in high stakes decision-making, uncertainty quantification methods that wrap around these black box models such as conformal prediction have received much attention in recent years. In sequential settings, where data are observed/generated in a streaming fashion, traditional conformal methods do not provide any guarantee without fixing the sample size. More importantly, traditional conformal methods cannot cope with sequentially updated predictions. As such, […]

Ver mais

Learning with shared representation is widely recognized as an effective way to separate commonalities from heterogeneity across various heterogeneous sources. Most existing work includes all related data sources via simultaneously training a common feature extractor and source-specific heads. It is well understood that data sources with low relevance or poor quality may hinder representation learning. In this paper, we further dive into the question of which data sources should be learned jointly by focusing on the traditionally deemed […]

Ver mais

arXiv:2602.18457v1 Announce Type: new Abstract: In recent years, synthetic media from deepfake videos have emerged as a new interesting technology, whether that refers to cloned voices, multilingual translation models, or more recent applications of avatar tutors into higher education. As such, these technologies are rapidly becoming part of the multilingual distance learning model and, more recently, MOOCs worldwide. This article is a scoping review that focuses on recent international literature published between 2020 and 2025 to explore the […]

Ver mais

AI generates code remarkably well. But here’s what it struggles with: understanding production reality. Production exists in pieces. Code describes what should happen; observability tools see signals; ticketing systems see problems; CI/CD sees changes. Every surface sees a slice of production. None maintains a coherent model of how the system actually works.  The same fragmentation exists across people and roles: SRE, support, QA, dev, PM. There is no central understanding of how production software works. Even within teams, […]

Ver mais

arXiv:2601.12243v1 Announce Type: new Abstract: Video summarization helps turn long videos into clear, concise representations that are easier to review, document, and analyze, especially in high-stakes domains like surgical training. Prior work has progressed from using basic visual features like color, motion, and structural changes to using pre-trained vision-language models that can better understand what’s happening in the video (semantics) and capture temporal flow, resulting in more context-aware video summarization. We propose a three-stage framework, PRISM: Procedural Representation […]

Ver mais

arXiv:2602.15082v1 Announce Type: new Abstract: Neural audio compression models have recently achieved extreme compression rates, enabling efficient latent generative modeling. Conversely, latent generative models have been applied to compression, pushing the limits of continuous and discrete approaches. However, existing methods remain constrained to low-resolution audio and degrade substantially at very low bitrates, where audible artifacts are prominent. In this paper, we present S-PRESSO, a 48kHz sound effect compression model that produces both continuous and discrete embeddings at ultra-low […]

Ver mais

Grokking, the abrupt transition from memorization to generalisation after extended training, suggests the presence of competing solution basins with distinct statistical properties. We study this phenomenon through the lens of Singular Learning Theory (SLT), a Bayesian framework that characterizes the geometry of the loss landscape via the local learning coefficient (LLC), a measure of the local degeneracy of the loss surface. SLT links lower-LLC basins to higher posterior mass concentration and lower expected generalisation error. Leveraging this theory, […]

Ver mais