Let’s be honest: labeling data is the absolute worst part of computer vision. For years, the standard playbook was to scrape millions of images, pay an army of annotators to draw bounding boxes, and feed them into a supervised Convolutional Neural Network. It worked, but it didn’t scale. Then self-supervised learning (SSL) came along, promising a world where models could learn from raw, unlabeled images. But early contrastive methods like SimCLR and MoCo were notoriously heavy, requiring massive batch […]

Ver mais

arXiv:2602.00924v1 Announce Type: new Abstract: Sparse auto-encoders (SAEs) have re-emerged as a prominent method for mechanistic interpretability, yet they face two significant challenges: the non-smoothness of the $L_1$ penalty, which hinders reconstruction and scalability, and a lack of alignment between learned features and human semantics. In this paper, we address these limitations by adapting unconstrained feature models-a mathematical framework from neural collapse theory-and by supervising the task. We supervise (decoder-only) SAEs to reconstruct feature vectors by jointly learning […]

Ver mais

Electronic control units (ECUs) embedded within modern vehicles generate a large number of asynchronous events known as diagnostic trouble codes (DTCs). These discrete events form complex temporal sequences that reflect the evolving health of the vehicle’s subsystems. In the automotive industry, domain experts manually group these codes into higher-level error patterns (EPs) using Boolean rules to characterize system faults and ensure safety. However, as vehicle complexity grows, this manual process becomes increasingly costly, error-prone, and difficult to scale. […]

Ver mais

arXiv:2602.06075v1 Announce Type: new Abstract: Current mobile GUI agent benchmarks systematically fail to assess memory capabilities, with only 5.2-11.8% memory-related tasks and no cross-session learning evaluation. We introduce MemGUI-Bench, a comprehensive memory-centric benchmark with pass@k and staged LLM-as-judge evaluation. Our contributions include: (1) a systematic memory taxonomy analyzing 11 agents across 5 architectures; (2) 128 tasks across 26 applications where 89.8% challenge memory through cross-temporal and cross-spatial retention; (3) MemGUI-Eval, an automated pipeline with Progressive Scrutiny and 7 […]

Ver mais

arXiv:2601.17027v1 Announce Type: new Abstract: While synthetic data has proven effective for improving scientific reasoning in the text domain, multimodal reasoning remains constrained by the difficulty of synthesizing scientifically rigorous images. Existing Text-to-Image (T2I) models often produce outputs that are visually plausible yet scientifically incorrect, resulting in a persistent visual-logic divergence that limits their value for downstream reasoning. Motivated by recent advances in next-generation T2I models, we conduct a systematic study of scientific image synthesis across generation paradigms, […]

Ver mais

Data-driven discovery of governing equations from time-series data provides a powerful framework for understanding complex biological systems. Library-based approaches that use sparse regression over candidate functions have shown considerable promise, but they face a critical challenge when candidate functions become strongly correlated: numerical ill-conditioning. Poor or restricted sampling, together with particular choices of candidate libraries, can produce strong multicollinearity and numerical instability. In such cases, measurement noise may lead to widely different recovered models, obscuring the true underlying […]

Ver mais

The shift from traditional search to AI-powered discovery is no longer future talk — it’s reshaping marketing right now. Brands that once optimized for Google rankings must now fight for citations and recommendations inside ChatGPT, Perplexity, and other generative engines. Fresh off research into the LLM marketing landscape, Olayimika Oyebanji sat down with ICODA co-founder and CEO Vlad Pivnev to discuss the real opportunities and hard challenges of Generative Engine Optimization, the limits of measurement in zero-click visibility, […]

Ver mais

Imitation learning (IL) provides a data-driven framework for approximating policies for large-scale combinatorial optimisation problems formulated as sequential decision problems (SDPs), where exact solution methods are computationally intractable. A central but underexplored aspect of IL in this context is the role of the emph{expert} that generates training demonstrations. Existing studies employ a wide range of expert constructions, yet lack a unifying framework to characterise their modelling assumptions, computational properties, and impact on learning performance. This paper introduces a […]

Ver mais

Get Started with Rust: Enums There are two ways to create custom data types in Rust: structs and enums. In contrast to structs, enums construct a type that has multiple variants and not multiple fields. While structs are a part of pretty much any programming language, enums are not so mainstream and are mostly seen in statically typed functional languages like Haskell or OCaml. But, as we’ll see, they are quite nice for domain modeling with types. This […]

Ver mais