arXiv:2603.03843v1 Announce Type: new Abstract: We consider stochastic non-stationary linear bandits where the linear parameter connecting contexts to the reward changes over time. Existing algorithms in this setting localize the policy by gradually discarding or down-weighting past data, effectively shrinking the time horizon over which learning can occur. However, in many settings historical data may still carry partial information about the reward model. We propose to leverage such data while adapting to changes, by assuming the reward model […]

Ver mais

This work presents a finite element-guided physics-informed operator learning framework for multiphysics problems with coupled partial differential equations (PDEs) on arbitrary domains. Implemented with Folax, a JAX-based operator-learning platform, the proposed framework learns a mapping from the input parameter space to the solution space with a weighted residual formulation based on the finite element method, enabling discretization-independent prediction beyond the training resolution without relying on labaled simulation data. The present framework for multiphysics problems is verified on nonlinear […]

Ver mais

There’s a growing realization across the AI ecosystem that models are no longer the bottleneck. The real constraint is everything around them: data access, governance, orchestration, and the ability to turn outputs into actions. That’s where most enterprise AI projects stall, not because the model isn’t capable, but because it isn’t meaningfully connected to the business. Domo’s latest set of releases quietly tackles that problem head-on. Underneath the surface, what looks like an AI Agent Builder announcement is […]

Ver mais

arXiv:2603.09987v1 Announce Type: new Abstract: Feature Transformation (FT) is a core data-centric AI task that improves feature space quality to advance downstream predictive performance. However, discovering effective transformations remains challenging due to the large space of feature-operator combinations. Existing solutions rely on discrete search or latent generation, but they are frequently limited by sample inefficiency, invalid candidates, and redundant generations with limited coverage. Large Language Models (LLMs) offer strong priors for producing valid transformations, but current LLM-based FT […]

Ver mais

arXiv:2602.12323v1 Announce Type: new Abstract: The widespread availability of fine-tuned LoRA modules for open pre-trained models has led to an interest in methods that can adaptively merge LoRAs to improve performance. These methods typically include some way of selecting LoRAs from a pool and tune merging coefficients based on a task-specific dataset. While adaptive merging methods have demonstrated improvements in some settings, no past work has attempted to recycle LoRAs found “in the wild” on model repositories like […]

Ver mais

arXiv:2602.17849v1 Announce Type: new Abstract: Training and serving Large Language Models (LLMs) relies heavily on parallelization and collective operations, which are frequently bottlenecked by network bandwidth. Lossless compression using e.g., Huffman codes can alleviate the issue, however, Huffman codes suffer from slow, bit-sequential decoding and high hardware complexity due to deep tree traversals. Universal codes e.g., Exponential-Golomb codes are faster to decode but do not exploit the symbol frequency distributions. To address these limitations, this paper introduces Dual […]

Ver mais

arXiv:2405.04636v4 Announce Type: replace-cross Abstract: Constructing confidence intervals that are simultaneously valid across a class of estimates is central to tasks such as multiple mean estimation, generalization guarantees, and adaptive experimental design. We frame this as an “error estimation problem,” where the goal is to determine a high-probability upper bound on the maximum error for a class of estimates. We propose an entirely data-driven approach that derives such bounds for both finite and infinite class settings, naturally adapting […]

Ver mais

Autonomous machine learning agents have revolutionized scientific discovery, yet they remain constrained by a Generate-Execute-Feedback paradigm. Previous approaches suffer from a severe Execution Bottleneck, as hypothesis evaluation relies strictly on expensive physical execution. To bypass these physical constraints, we internalize execution priors to substitute costly runtime checks with instantaneous predictive reasoning, drawing inspiration from World Models. In this work, we formalize the task of Data-centric Solution Preference and construct a comprehensive corpus of 18,438 pairwise comparisons. We demonstrate […]

Ver mais

When I first heard “cloud commitment insurance,” I nodded politely and had absolutely no idea what anyone was talking about. Insurance? For cloud commitments? What gets insured — the server? The discount? The contract? And who’s the insurance company here? I had several sessions with the Archera team trying to wrap my head around it. Here’s the thing that made it so confusing: their product is genuinely simple. So simple that the simplicity itself became the barrier. There […]

Ver mais

Simulating the long-time evolution of Hamiltonian systems is limited by the small timesteps required for stable numerical integration. To overcome this constraint, we introduce a framework to learn Hamiltonian Flow Maps by predicting the mean phase-space evolution over a chosen time span $Δt$, enabling stable large-timestep updates far beyond the stability limits of classical integrators. To this end, we impose a Mean Flow consistency condition for time-averaged Hamiltonian dynamics. Unlike prior approaches, this allows training on independent phase-space […]

Ver mais