arXiv:2602.14244v1 Announce Type: new Abstract: Federated Learning provides a privacy-preserving paradigm for distributed learning, but suffers from statistical heterogeneity across clients. Personalized Federated Learning (PFL) mitigates this issue by considering client-specific models. A widely adopted approach in PFL decomposes neural networks into a shared feature extractor and client-specific heads. While effective, this design induces a fundamental tradeoff: deep or expressive shared components hinder personalization, whereas large local heads exacerbate overfitting under limited per-client data. Most existing methods rely […]

Ver mais

arXiv:2601.09716v1 Announce Type: new Abstract: Natural Language Processing (NLP) is rapidly transforming research methodologies across disciplines, yet African languages remain largely underrepresented in this technological shift. This paper provides the first comprehensive overview of NLP progress and challenges for the six national languages officially recognized by the Senegalese Constitution: Wolof, Pulaar, Sereer, Joola, Mandingue, and Soninke. We synthesize linguistic, sociotechnical, and infrastructural factors that shape their digital readiness and identify gaps in data, tools, and benchmarks. Building on […]

Ver mais

It is posited that the two balanced ternary systems, (-1, 0, 1) and (-i, 0, i), are positioned on the line of real numbers and on the axis of complex numbers, respectively. In the event that the system is reduced to a single entity, the digits of the resulting system will be as follows: { -1, -i, 0, i, 1} The set (-1, -i, 0, i, 1) is transformed into a base five system. In this article and […]

Ver mais

Combinatorial optimization augmented machine learning (COAML) has recently emerged as a powerful paradigm for integrating predictive models with combinatorial decision-making. By embedding combinatorial optimization oracles into learning pipelines, COAML enables the construction of policies that are both data-driven and feasibility-preserving, bridging the traditions of machine learning, operations research, and stochastic optimization. This paper provides a comprehensive overview of the state of the art in COAML. We introduce a unifying framework for COAML pipelines, describe their methodological building blocks, […]

Ver mais

arXiv:2602.04021v1 Announce Type: cross Abstract: We present GROOVE, a semi-supervised multi-modal representation learning approach for high-content perturbation data where samples across modalities are weakly paired through shared perturbation labels but lack direct correspondence. Our primary contribution is GroupCLIP, a novel group-level contrastive loss that bridges the gap between CLIP for paired cross-modal data and SupCon for uni-modal supervised contrastive learning, addressing a fundamental gap in contrastive learning for weakly-paired settings. We integrate GroupCLIP with an on-the-fly backtranslating autoencoder […]

Ver mais

arXiv:2602.07613v1 Announce Type: cross Abstract: Balancing covariates is critical for credible and efficient randomized experiments. Rerandomization addresses this by repeatedly generating treatment assignments until covariate balance meets a prespecified threshold. By shrinking this threshold, it can achieve arbitrarily strong balance, with established results guaranteeing optimal estimation and valid inference in both finite-sample and asymptotic settings across diverse complex experimental settings. Despite its rigorous theoretical foundations, practical use is limited by the extreme inefficiency of rejection sampling, which becomes […]

Ver mais

arXiv:2602.17838v1 Announce Type: new Abstract: As developers increasingly rely on LLM-generated code summaries for documentation, testing, and review, it is important to study whether these summaries accurately reflect what the program actually does. LLMs often produce confident descriptions of what the code looks like it should do (intent), while missing subtle edge cases or logic changes that define what it actually does (behavior). We present a mutation-based evaluation methodology that directly tests whether a summary truly matches the […]

Ver mais

arXiv:2601.22179v1 Announce Type: new Abstract: Within the domain of data mining, one critical objective is the discovery of sequential rules with high utility. The goal is to discover sequential rules that exhibit both high utility and strong confidence, which are valuable in real-world applications. However, existing high-utility sequential rule mining algorithms suffer from redundant utility computations, as different rules may consist of the same sequence of items. When these items can form multiple distinct rules, additional utility calculations […]

Ver mais

Figma is integrating OpenAI’s coding assistant Codex a week after it announced a similar integration with Anthropic’s Claude Code.

Ver mais

Animation is too hard. To make a 30-second clip, you usually need to learn Blender, hire voice actors, frame keyframes, and render for twelve hours. I wanted to make memes, shitposts, and storytelling clips, and I wanted them done in the time it takes to drink a coffee. So, I built the Stickverse. It is a scrappy, Python-based animation pipeline that turns a raw text story into a fully voiced, lip-synced (well, “lip-flapped”) video. It uses Google’s Gemini […]

Ver mais