arXiv:2602.11292v1 Announce Type: new Abstract: We prove a complete complexity classification theorem for the planar eight-vertex model. For every parameter setting in ${mathbb C}$ for the eight-vertex model, the partition function is either (1) computable in P-time for every graph, or (2) #P-hard for general graphs but computable in P-time for planar graphs, or (3) #P-hard even for planar graphs. The classification has an explicit criterion. In (2), we discover new P-time computable eight-vertex models on planar graphs […]

Ver mais

arXiv:2603.03299v1 Announce Type: new Abstract: Large language models (LLMs) have been noted to fabricate scholarly citations, yet the scope of this behavior across providers, domains, and prompting conditions remains poorly quantified. We present one of the largest citation hallucination audits to date, in which 10 commercially deployed LLMs were prompted across four academic domains, generating 69,557 citation instances verified against three scholarly databases (namely, CrossRef, OpenAlex, and Semantic Scholar). Our results show that the observed hallucination rates span […]

Ver mais

While Large Language Models (LLMs) excel at function-level code generation, project-level tasks such as generating functional and visually aesthetic multi-page websites remain highly challenging. Existing works are often limited to single-page static websites, while agentic frameworks typically rely on multi-turn execution with proprietary models, leading to substantial token costs, high latency, and brittle integration. Training a small LLM end-to-end with reinforcement learning (RL) is a promising alternative, yet it faces a critical bottleneck in designing reliable and computationally […]

Ver mais

Machine learning and artificial intelligence is a field that drives major innovations across different industries. It is predicted that in 2023, the AI market will reach $500 billion, and in 2030, $1,597.1 billion in size. This means that machine learning technologies will continue to be in high demand in the near future. However, the machine learning industry evolves very rapidly: new technologies and scientific research define how new products and services are built. At the end of 2022, […]

Ver mais

arXiv:2505.21791v4 Announce Type: replace Abstract: Overparameterized neural networks can interpolate a given dataset in many different ways, prompting the fundamental question: which among these solutions should we prefer, and what explicit regularization strategies will provably yield these solutions? This paper addresses the challenge of finding the sparsest interpolating ReLU network–i.e., the network with the fewest nonzero parameters or neurons–a goal with wide-ranging implications for efficiency, generalization, interpretability, theory, and model compression. Unlike post hoc pruning approaches, we propose […]

Ver mais

arXiv:2602.20223v1 Announce Type: new Abstract: Recently, TabPFN has gained attention as a foundation model for tabular data. However, it struggles to integrate heterogeneous modalities such as images and text, which are common in domains like healthcare and marketing, thereby limiting its applicability. To address this, we present the Multi-Modal Prior-data Fitted Network (MMPFN), which extends TabPFN to handle tabular and non-tabular modalities in a unified manner. MMPFN comprises per-modality encoders, modality projectors, and pre-trained foundation models. The modality […]

Ver mais

We introduce Metric-Aware Principal Component Analysis (MAPCA), a unified framework for scale-invariant representation learning based on the generalised eigenproblem max Tr(W^T Sigma W) subject to W^T M W = I, where M is a symmetric positive definite metric matrix. The choice of M determines the representation geometry. The canonical beta-family M(beta) = Sigma^beta, beta in [0,1], provides continuous spectral bias control between standard PCA (beta=0) and output whitening (beta=1), with condition number kappa(beta) = (lambda_1/lambda_p)^(1-beta) decreasing monotonically to […]

Ver mais

arXiv:2406.07746v3 Announce Type: replace Abstract: We propose a computationally efficient algorithm that achieves anytime regret of order $mathcal{O}(sqrt{t})$, with explicit dependence on the system dimensions and on the solution of the Discrete Algebraic Riccati Equation (DARE). Our approach builds on the SDP-based framework of cite{cohen2019learning}, using an appropriately tuned regularization and a sufficiently accurate initial estimate to construct confidence ellipsoids for control design. A carefully designed input-perturbation mechanism is incorporated to ensure anytime performance. We develop two variants […]

Ver mais