11 articles mentioning Ising-Calibration-1-35B-A3B
arXiv:2610.22713v1 Announce Type: new Abstract: The Long-Range Ising Model benchmark (LRIM) guarantees long-range dependence by construction: each label is the node's spin times the spin field convolved with a power-law coupling, so any model's distance from the target is measurable. We prove that a
arXiv:2607.23634v2 Announce Type: replace-cross Abstract: Attention enables context modeling via query-key scoring with softmax normalization. Driven by industrial long-context demands, mainstream research has converged toward sparsity and efficiency, yet softmax's independence assumption persists.
arXiv:2510.13210v2 Announce Type: replace Abstract: We compare Ising ({-1, +1}) and QUBO ({0, 1}) encodings for Boltzmann machine learning under controlled protocols that fix the sampler, optimizer, and learning-rate design within each comparison. Exploiting the identity that the Fisher information
arXiv:2505.07163v2 Announce Type: replace-cross Abstract: Ising solvers have a finite spin budget. Quadratization uses auxiliary spins to replace higher-order interactions by pairwise ones. We show that removing spins while allowing more complex interactions can fit larger problems within the same s
arXiv:2609.08797v2 Announce Type: replace-cross Abstract: The Potts model extends the Ising model to multinomial data. We introduce a Rater Ising-Potts model that uses agreement indicators between pairs of ratings and category labels, with weights derived from LLM embeddings. The model does not pres
arXiv:2609.08873v1 Announce Type: cross Abstract: Sparsity is a powerful structural resource in optimization and statistics. We develop frameworks for leveraging sparsity in sampling problems over the Hamming slice $\mathcal{X}_k^d:=\{\mathbf{x}\in\{\pm 1\}^d:|\{i:\mathbf{x}_i=1\}|=k\}$, in high-dim
arXiv:2506.18240v5 Announce Type: replace-cross Abstract: Training quantized neural networks remains fundamentally challenging due to non-convex loss landscapes and discrete parameter spaces. We introduce an exact Quadratic Constrained Binary Optimization (QCBO) framework with provable guarantees. W
arXiv:2607.10285v2 Announce Type: replace Abstract: We study how unsupervised autoencoders trained on microscopic spin configurations from the Ising model learn macroscopic, theory-relevant variables underlying the data-generating process. We quantify learning across multiple spatial (coarse-grainin
arXiv:2603.00408v3 Announce Type: replace Abstract: We present an Ising-compatible framework for formal neural-network robustness verification under bounded input perturbations. For piecewise-linear activations, the Exact Logarithmic PWL Model (Log-PWL) provides an exact, sound, and complete formula
arXiv:2607.23634v1 Announce Type: new Abstract: Attention enables context modeling via query-key scoring with softmax normalization. Driven by industrial long-context demands, mainstream research has converged toward sparsity and efficiency--yet softmax's independence assumption persists. For scient