representational similarity analysis

Existing studies lack a quantitative, discriminability-oriented comparison of representational similarity measures (RSMs) across diverse model families (e.g., CNNs, Transformers, biologically inspired models). Method: We propose a unified discriminability evaluation framework grounded in signal detection theory (d′), silhouette coefficient, and ROC-AUC, integrating major RSMs—including Representational Similarity Analysis (RSA), linear predictivity, Procrustes alignment, and soft matching. Contribution/Results: Our analysis reveals, for the first time, a positive correlation between an RSM’s alignment constraint strength and its ability to separate models by architecture or training paradigm: soft matching achieves top discriminability, while non-fitting methods (e.g., RSA) also exhibit strong separation performance. The framework provides interpretable, reproducible criteria for selecting RSMs in cross-model comparisons and model–brain alignment studies.

This study addresses the challenge of estimating neural representational distance metrics under complex distributions and the absence of systematic design principles for novel metrics. To this end, this work introduces flow matching from generative modeling into neuroscience for the first time, establishing a unified theoretical framework. By leveraging deep generative models and velocity field constrained optimization, the proposed framework formulates diverse distance metrics as Jeffreys divergences under distinct velocity constraints, thereby enabling efficient processing of continuous variables and complex distributions. This approach significantly improves distance estimation accuracy in complex distributional settings, provides a systematic paradigm for designing new metrics, and advances our understanding of differences in neural coding.

This study addresses the challenge of comparing high-dimensional neural representations across neuroscience and artificial intelligence: specifically, how to select similarity measures that best reveal functional correspondences and divergences. We systematically evaluate eight mainstream representational similarity metrics—including linear CKA, Procrustes distance, CCA, inner-product kernel, and nearest-neighbor alignment—against behavioral functional alignment (e.g., recognition accuracy, generalization, robustness) as a ground-truth benchmark. Our evaluation spans both biological neural data and artificial neural network models. Results show that geometry-sensitive metrics—particularly linear CKA and Procrustes distance—consistently outperform predictive metrics, achieving superior alignment with human behavioral performance and effectively distinguishing trained versus untrained models. In contrast, linear predictivity exhibits only moderate behavioral alignment. This work establishes the first behavior-driven representational similarity benchmark, providing a principled, cross-domain methodology for mechanistic interpretation and comparative analysis of neural computation.

This work investigates the evolution of hidden-layer representation similarity in Transformer models and its implications for training and inference. We observe that inter-layer cosine similarity increases as layer distance decreases and correlates positively with prediction confidence. Building on this, we propose *Alignment Training*: an optimization framework that enforces inter-layer representation alignment to accelerate shallow-layer representation saturation, ensure monotonic improvement in layer-wise accuracy, and inherently reveal the minimal depth required for a given task. Our theoretical analysis is grounded in sample-level similarity metrics and a geometric manifold assumption. Notably, we provide the first formal proof that a single top-layer classifier suffices for multi-exit inference. Empirically, on both vision and NLP benchmarks, our method matches the accuracy of dedicated multi-classifier multi-exit architectures while substantially reducing inference latency and parameter redundancy.

This work investigates whether cross-dataset consistency in model representation similarity stems from intrinsic model properties or is confounded by biases inherent in common benchmark datasets. To address this, we conduct systematic representation comparison experiments across multimodal (image, image-text) and multitask (self-supervised, classification, image-text contrastive) models, using Centered Kernel Alignment (CKA) and linearly weighted similarity analysis on diverse domain-shifted datasets. Results demonstrate that training objective is the dominant factor governing cross-dataset representation similarity stability—significantly outweighing influences of data modality and network architecture. We propose the first evaluation framework explicitly designed for cross-dataset representational consistency. Furthermore, we reveal that self-supervised vision models exhibit the strongest generalization of representation similarity across datasets, and that the correlation between representation similarity and task performance is maximized on single-domain benchmarks.

Existing approaches to measuring functional similarity between models rely on the true data distribution, making it difficult to characterize alignment of decision boundaries across the entire input space. This work proposes Rashomon Alignment (RA), a novel framework that, for the first time, evaluates functional similarity between models from a geometric perspective over the full input space without dependence on any specific data distribution. By uniformly sampling the input space and employing geometric similarity metrics, RA enables a global analysis of decision boundary alignment. Experiments across more than 90 datasets demonstrate that geometric alignment provides a complementary perspective to distribution-based alignment, and that RA effectively supports model selection, ensemble construction, and enhanced interpretability.

This study addresses the limitation of text embeddings in capturing structural similarities and varying levels of abstraction among creative ideas. To overcome this, we propose a structured decomposition-based evaluation framework that deconstructs ideas into core components—such as purpose and mechanism—and constructs multi-layered concept graphs. By introducing shared structural representations and set-level mechanism coverage metrics, the framework enables component-wise overlap analysis to precisely quantify distinctions between core mechanisms and implementation details. Experimental results demonstrate that our approach improves alignment with expert judgments by 31%, significantly enhancing the evaluation of both similarity and diversity in large-scale ideation tasks.

This study addresses the challenge of evaluating cross-layer and cross-network similarity of internal neural representations across multiple scales. The authors propose a novel framework that integrates diffusion geometry with multi-view learning: by modeling the data manifold via a Markov transition matrix, they leverage its powers to construct multi-scale variants of Centered Kernel Alignment (CKA) and distance correlation. Furthermore, alternating diffusion is introduced to fuse information across layers, enabling a paradigm shift from local inter-layer comparisons to global inter-network assessments. Evaluated on the ReSi benchmark—spanning 14 architectures, 7 datasets, and 3 domains—the method achieves state-of-the-art performance in representation similarity and out-of-distribution generalization across both language and vision tasks.

This work addresses the limitations of distribution matching and representation selection in single-step image generation by proposing a novel paradigm that directly aligns the distributions of real and generated images within the frozen feature space of pretrained encoders. Systematic investigation reveals that the classical Maximum Mean Discrepancy (MMD), when properly estimated, is highly competitive; large-batch training (batch size > 2048) is crucial for performance; and balanced matching across multiple encoders significantly enhances generalization. The proposed method achieves state-of-the-art results in single-step generation on ImageNet (SW↓r14 = 1.30) and attains a 71.2% win rate in human preference evaluations via PickScore. Furthermore, it successfully distills the four-step FLUX.2 model into a stronger single-step variant that surpasses the original in both GenEval and PickScore metrics, requiring only 90 H200 GPU-hours.

Existing neural representational similarity measures focus solely on the extrinsic geometry of state space, limiting their ability to reveal the essential intrinsic differences among neural network solutions. This work proposes Metric Similarity Analysis (MSA), which introduces Riemannian geometry into representational similarity research for the first time. Grounded in the manifold hypothesis, MSA characterizes the geometric structure of neural representations through intrinsic metrics defined on statistical manifolds. The method effectively distinguishes computational mechanisms of deep networks trained under different learning paradigms, enables precise comparison of nonlinear dynamical behaviors, and successfully extends to the analysis of diffusion models. Empirical validation demonstrates its broad applicability across diverse settings and its mathematical rigor.