arXiv AI
Jul 29
Rashomon Alignment
arXiv:2607. 25680v1 Announce Type: cross Abstract: We propose Rashomon Alignment (RA), a new measure to assess functional similarity between two models.
Rashomon Alignment
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.
Related stories
arXiv Machine Learning
1d ago
Towards a theory of inference-time alignment with unknown rewards
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 Machine Learning
Jun 3
Grounding Functional Similarity by Invariance-Aware Model Stitching
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 Machine Learning
Aug 3
Persistent Convolution: A Topological Framework for AI Alignment Testing and Semantic Space Characterization
arXiv:2607. 29008v1 Announce Type: cross Abstract: Modern opaque AI models prize performance over interpretability, which makes testing difficult.
arXiv Machine Learning
Jun 4
The Perception-Physics Paradox: Probing Scientific Alignment with TC-Bench
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.
arXiv AI
Jul 7
Multi-Way Representation Alignment
arXiv:2602. 06205v2 Announce Type: replace-cross Abstract: The Platonic Representation Hypothesis suggests that independently trained neural networks converge to increasingly similar latent spaces.
arXiv Machine Learning
Jun 9
A Unifying Framework for Concept-Based Representational Similarity
arXiv:2606. 09653v1 Announce Type: new Abstract: Learned representations across models and modalities often exhibit striking structural similarities, suggesting shared underlying concept decompositions.
arXiv Machine Learning
Jun 16
Learning the Geometry of Data: A Mathematical Review of Shape Space Analysis
arXiv:2606. 17022v1 Announce Type: cross Abstract: A central objective of machine learning is to identify structure and patterns in data.
arXiv Machine Learning
Jun 26
The Geometry of Updates: Fisher Alignment at Vocabulary Scale
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.
arXiv Machine Learning
Jul 16
AvAtar: Learning to Align via Active Optimal Transport
arXiv:2605. 24395v2 Announce Type: replace Abstract: Alignment plays a fundamental role in many machine learning problems, such as multi-network analysis, multimodal learning, and point cloud registration.
arXiv AI
Jul 3
Navigating the Alignment-Calibration Trade-off: A Pareto-Superior Frontier via Model Merging
arXiv:2510. 17426v3 Announce Type: replace-cross Abstract: The "alignment tax" of post-training is typically framed as a drop in task accuracy.
arXiv Machine Learning
Aug 11
Machine Learning and Data Analysis Using Posets: A Survey
arXiv:2404. 03082v3 Announce Type: replace Abstract: Partially ordered sets (posets) are discrete mathematical structures that formalize the notion of comparison without forcing every pair of objects to be comparable.