arXiv:2607. 25680v1 Announce Type: cross Abstract: We propose Rashomon Alignment (RA), a new measure to assess functional similarity between two models.
We propose Rashomon Alignment (RA), a new measure to assess functional similarity between two models. Existing functional similarity measures are distributional, quantifying differences between outputs of models applied to real-world data.
arXiv:2609.39848v1 Announce Type: new Abstract: Foundation models are increasingly adopted across a wide range of applications, often serving as core blocks within AI systems. Yet different foundatio...
arXiv:2608. 15402v1 Announce Type: new Abstract: Generative model alignment has received broad interest, and significant progress has been made in supervised fine-tuning and inference-time computation.
arXiv:2605. 24782v2 Announce Type: replace Abstract: While Vision Foundation Models (VFMs) excel at predictive tasks on satellite imagery, their performance can arise from visual correlations rather than underlying structural invariants, making even perception-based out-of-distribution accuracy a poor proxy for scientific utility.
Foundation models are increasingly adopted across a wide range of applications, often serving as core blocks within AI systems. Yet different foundation models may encode the same input from multiple...
arXiv:2505. 20142v2 Announce Type: replace Abstract: In deep learning, functional similarity evaluation quantifies the extent to which independently trained models learn similar input--output relationships.
arXiv:2606. 17022v1 Announce Type: cross Abstract: A central objective of machine learning is to identify structure and patterns in data.
arXiv:2607. 29008v1 Announce Type: cross Abstract: Modern opaque AI models prize performance over interpretability, which makes testing difficult.
arXiv:2606. 09653v1 Announce Type: new Abstract: Learned representations across models and modalities often exhibit striking structural similarities, suggesting shared underlying concept decompositions.
arXiv:2602. 06205v2 Announce Type: replace-cross Abstract: The Platonic Representation Hypothesis suggests that independently trained neural networks converge to increasingly similar latent spaces.
The paper introduces Geometric Anchor Preference Optimization (GAPO), a method that replaces the static reference policy in Direct Preference Optimization with a dynamic, geometry-aware anchor—a small adversarial perturbation of the current policy. GAPO uses this anchor to adaptively reweight preference pairs based on local sensitivity, and defines an Anchor Gap that approximates worst‑case local margin degradation. Experiments show that GAPO improves robustness to noisy supervision while matching or surpassing existing LLM alignment and reasoning benchmarks.
arXiv:2606. 27242v1 Announce Type: new Abstract: Training-free source selection for LLM families with shared vocabularies arises in scientific string domains such as SMILES, protein, and genomic sequences, where candidate corpora share a tokenizer but differ in prediction targets.