For the last 20 years, the dogma of software engineering was simple: “Good code documents itself.” We were taught that comments are a “code smell” (Uncle Bob told us so). We were taught that if you need to explain it, you failed to name it properly. We were taught to DRY (Don’t Repeat Yourself) everything into oblivion. But in 2024, the game changed. You aren’t just writing code for your future self or your colleagues anymore. You are […]

Ver mais

arXiv:2601.07898v1 Announce Type: new Abstract: Large Language Models (LLMs) have recently developed new advanced functionalities. Their effectiveness relies on statistical learning and generalization capabilities. However, they face limitations in internalizing the data they process and struggle, for instance, to autonomously execute algorithms. In this paper, we investigate the possibility of extending these models’ capabilities to algorithm execution through specialized supervised training focused on reasoning decomposition. We introduce a training model called LLM-DAL (Large Language Model – Decompositional Algorithmic […]

Ver mais

Integration-by-parts (IBP) reduction of Feynman integrals to master integrals is a key computational bottleneck in precision calculations in high-energy physics. Traditional approaches based on the Laporta algorithm require solving large systems of equations, leading to memory consumption that grows rapidly with integral complexity. We present SAILIR (Self-supervised AI for Loop Integral Reduction), a new machine learning approach in which a transformer-based classifier guides the reduction of integrals one step at a time in a fully online fashion. The […]

Ver mais

arXiv:2511.08667v2 Announce Type: replace-cross Abstract: The first tabular foundation model, TabPFN, and its successor TabPFNv2 have impacted tabular AI substantially, with dozens of methods building on it and hundreds of applications across different use cases. This report introduces TabPFN-2.5, the next generation of our tabular foundation model, built for datasets with up to 50,000 data points and 2,000 features, a 20x increase in data cells compared to TabPFNv2. TabPFN-2.5 is now the leading method for the industry standard […]

Ver mais

Hey all, Our ML team spent some time this week getting training and deployments working for Gemma-4, and wanted to document all the things we ran into along the way. PEFT doesn’t recognize Gemma 4’s custom layers. Google wrapped vision/audio projections in a new ClippableLinear class that doesn’t inherit from nn.Linear, so PEFT refuses to attach LoRA, even for text-only fine-tuning. Fix: unwrap the wrappers after loading weights but before calling PEFT. SFTTrainer killed training silently. TRL hardcodes […]

Ver mais

Semi-supervised imitation learning (SSIL) consists in learning a policy from a small dataset of action-labeled trajectories and a much larger dataset of action-free trajectories. Some SSIL methods learn an inverse dynamics model (IDM) to predict the action from the current state and the next state. An IDM can act as a policy when paired with a video model (VM-IDM) or as a label generator to perform behavior cloning on action-free data (IDM labeling). In this work, we first […]

Ver mais

Cursor, the AI-powered code editor, is opening up the core technology behind its coding agents to developers everywhere. The Cursor team announced the public beta of the Cursor SDK — a TypeScript library that gives engineers programmatic access to the same runtime, harness, and models that power Cursor’s desktop app, CLI, and web interface. This signals a meaningful shift in how AI coding tools are being positioned: not just as interactive assistants sitting alongside a developer, but as […]

Ver mais

Decentralized federated learning (D-FL) enables privacy-preserving training without a central server, but multi-hop model exchanges and aggregation are often bottlenecked by communication resource constraints. To address this issue, we propose a joint routing-and-pruning framework that optimizes routing paths and pruning rates to maintain communication latency within prescribed limits. We analyze how the sum of model biases across all clients affects the convergence bound of D-FL and formulate an optimization problem that maximizes the model retention rate to minimize […]

Ver mais

Concept Bottleneck Models (CBMs) aim for ante-hoc interpretability by learning a bottleneck layer that predicts interpretable concepts before the decision. State-of-the-art approaches typically select which concepts to learn via human specification, open knowledge graphs, prompting an LLM, or using general CLIP concepts. However, concepts defined a-priori may not have sufficient predictive power for the task or even be learnable from the available data. As a result, these CBMs often significantly trail their black-box counterpart when controlling for information […]

Ver mais

arXiv:2603.13806v1 Announce Type: new Abstract: Sparse principal component analysis (SPCA) addresses the poor interpretability and variable redundancy often encountered by principal component analysis (PCA) in high-dimensional data. However, SPCA typically imposes uniform penalties on variables and does not account for differences in variable importance, which may lead to unstable performance in highly noisy or structurally complex settings. We propose SP-SPCA, a method that introduces a single equilibrium parameter into the regularization framework to adaptively adjust variable penalties. This […]

Ver mais