Face Recognition and Perception

Latest papers

• Decoding the Functional Roles of Register and High-Norm Patch Tokens in Vision Transformers

  Neel Varma, Andrew Rufail, Dipika Khullar, Vasu Sharma · 5 October 2026

  Self-supervised Vision Transformers (ViTs), such as DINOv2, learn rich visual representations, but the functions of their internal tokens remain poorly understood. Recent architectures introduce dedicated register tokens to reduce high-norm out- lier patch tokens that emerge in background re- gions,…

• Beyond Local Linearity: Scale-Resolved Geometry of Learned Image Encoders

  Jakub Szymkowiak, Wojtek Pa{\l}ubicki, Kamil Adamczewski · 1 October 2026

  Understanding how learned representations respond to finite input changes is important for characterizing their sensitivity, invariances, and robustness. Yet existing geometric analyses are predominantly local and describe only infinitesimal perturbations. We introduce a scale-resolved statistic tha…

• Fisher-IRG: Fisher-Induced Local Invariant Representation Geometry across Language and Vision Models

  Abdullah All Tanvir, Xin Zhong · 1 October 2026

  Semantic-preserving transformations can induce substantial motion in learned representations, while small changes may strongly affect model predictions, raising a basic question: what local metric best captures semantically consequential variation? We propose Fisher-induced invariant representation …

• Future Video Generation Better Aligns with the Human Visual Cortex than Observed Video

  Chang-Bae Bang, Hyungjin Chung, Byung-Hoon Kim · 1 October 2026

  Studying the alignment between the internal representations of vision models and the responses of the visual cortex to the same observed visual stimuli has enabled us to better understand human visual processing. However, studies so far have largely overlooked the fact that the human brain not only …

• Similar Choices, Different Attention: Cross-Modal Associations in Humans and Vision-Language Models

  Sumin Hong, Katsumi Ibaraki, Renee Shi, David Chiang, Toby Jia-Jun Li · 30 September 2026

  Cross-modal associations are systematic pairings of features across modalities, such as the association of 'bouba' with round shapes and 'kiki' with sharp shapes. Prior work has compared humans and vision-language models (VLMs) on such associations, but often using different stimuli or tasks between…

• Cross-attention encoding models reveal dynamic spatiotemporal routing across human higher visual cortex

  Iishaan Inabathini, Margaret M. Henderson · 30 September 2026

  Understanding how the brain parses actions and events from time-varying natural inputs is a central challenge in neuroscience. Recent work has used deep neural network (DNN) models to build stimulus-computable fMRI encoding models that predict single-voxel responses to complex natural videos. Howeve…

• Which Attention Heads are like the Human Head? Not the Ones that Compute

  Christopher Pinier, Gustaw Opie{\l}ka, Hannes Rosenbusch, Taylor Webb, Michael D. Nunez, Claire E. Stevenson · 30 September 2026

  Brain-AI alignment is often interpreted as a sign that model and brain perform similar computations. Whether the aligned units are causally involved in model computation is rarely checked. On an abstract pattern-completion task (AAABAAA $\rightarrow$ B), we compare LLM attention-head representations…

• What Converges in the Platonic Representation Hypothesis? Structure over Geometry

  Junwon You, Mihyun Jang, Sangwoo Mo, Jae-Hun Jung · 24 September 2026

  The Platonic Representation Hypothesis suggests that increasingly capable models converge toward shared representations. Recent work narrows this claim to shared local neighborhood relationships, finding that capacity-dependent trends in several global similarity measures largely disappear after cal…

• Two Global Crops Suffice: Locating Semantic Emergence in DINO-Style Self-Supervised Learning

  Basavaraj Sunagad, Artur Jesslen, Adam Kortylewski · 24 September 2026

  Self-supervised vision transformers trained with DINO-style objectives exhibit striking emergent semantic representation quality across visual tasks, yet the mechanisms underlying this behavior remain unclear. We present a systematic empirical dissection of the DINO family and show that semantic rep…

• The Linear Representation Hypothesis Needs a Group Action

  Louie Hong Yao, Yuhao Li, Shengchao Liu · 24 September 2026

  To make claims about representations that generalize beyond a particular trained model, we need to specify when two representations should count as equivalent. The Linear Representation Hypothesis is often discussed without making this equivalence explicit. Different notions of equivalence preserve …

• Do Vision Model See Like the Brain? A Comparison Across EEG Encoding Model

  Shashank Baghel, Kshitij Dwivedi, Dinesh Singh, Sanjeev Nara · 23 September 2026

  Convolutional neural networks (CNNs) and vision transformers are both used to model the human visual system, but whether the two architectures diverge at a specific point in network depth is unclear. We compared six CNNs and two vision transformers by computing the Pearson correlation (r) between ea…

• Displacement Geometry Captures Platonic Shared Reality Across Models and Modalities

  Chenming Shang, Yujin Tang, Jun Jie Ou Yang, Ruize Xu, Adam Breuer, Nikhil Singh · 22 September 2026

  The Platonic Representation Hypothesis (PRH) claims that independently trained models converge on a shared statistical model of reality, yet recent work finds only weak pointwise similarity between models. In this paper, we show that what models share is not the location of samples in representation…

• Topographic Training Concentrates Causal Circuits Without Improving Neuron Monosemanticity

  Gautam Ranka, Shubham Santosh Pandere, Aiden Dsouza · 22 September 2026

  Mechanistic interpretability of vision transformers seeks to decompose model computation into human-readable units, but learned representations entangle many concepts in each neuron. Feature superposition is widely treated as the central obstacle to this decomposition, yet most mitigations (sparse a…

• The Visual Target Matters: Learning across the Visual Hierarchy for Brain-to-Image Retrieval

  Ye Wang, HaoKun Ren, Hong Yu, Ruirui Li, Xiao Li, Ke Liu, Wei Wu · 22 September 2026

  Brain-to-image retrieval seeks to identify the visual stimulus that elicited a non-invasive neural response. Candidate images are typically represented by pretrained vision models, whose internal representations vary in abstraction across depth. Existing methods usually train the neural encoder to r…

• Certified Topological Interaction in Neural Representations: Exact Tests and the Statistic They Require

  Sushovan Majhi · 21 September 2026

  Class disentanglement--the separation of a representation's class-conditional point clouds along depth and over training--is measured by descriptive curves: the sentence such a study wants to write, layer l+1 is more disentangled than layer l, is an eyeball judgement with no null. We supply the infe…

• Perceptual Reality Transformer: What Must an Illustration Preserve?

  Baihan Lin · 16 September 2026

  How can models help people communicate unusual perceptual experiences without changing what they mean? A recognizable image is only part of the answer: accounts also express vividness, duration, uncertainty, and emotion. We introduce Perceptual Reality Transformer (PRT), an evidence-linked workflow …

• The Platonic brain bridge hypothesis: human brain networks as an architectural prior for omni models

  Pengfei Zhang, Biao Tian, Xiangang Li, Li Liu · 11 September 2026

  We propose the Platonic brain bridge hypothesis: omni models, which process video, audio and text jointly like the brain, converge on brain-like representations, and the correspondence is bidirectional. From model to brain, brain-likeness of seven omni models is stable across participants, and our e…

• Are You Thinking What I am Thinking? : Examining Conceptual Separation in Neural Architectures

  Jaee Ponde, Roshni Agarwal, Subhashis Banerjee · 2 September 2026

  Neural networks are increasingly employed to identify both well-defined and ambiguous concepts, yet output-level metrics reveal little about how those concepts are represented internally. Our study asks if these networks exhibit \textit{conceptual separation}: if examples of the same concept form co…

• More Data Cannot Break a Symmetry: Identifiability by Design

  Jing Xu, Christopher Kanan · 31 August 2026

  Unsupervised representational alignment recovers a stimulus-by-stimulus correspondence from geometry alone, but the automorphism group of the stimulus geometry bounds what any such alignment can identify, before data exist. The obvious diagnostic for this degeneracy, the cheapest non-identity relabe…

• Relational Knowledge Distillation Brings DNN Representations Close Enough to Humans to Be Aligned Without Supervision

  Yuria Shimizu, Soh Takahashi, Takato Horii, Masafumi Oizumi · 31 August 2026

  Linking the internal representations of deep neural networks (DNNs) to human mental representations is important for using DNNs as computational models of human vision. Existing DNN representations remain insufficiently similar to human mental representations, which are not directly observable and a…

• Primate vision reveals a missing principle for robust dynamic AI

  Matteo Dunnhofer, Christian Micheloni, Kohitij Kar · 26 August 2026

  How does an intelligent visual system combine what objects look like with how they move while remaining robust as appearance changes? We addressed this question by comparing human perception and neural activity in macaque inferior temporal cortex with representations from image- and video-based neur…

• A Human-Factors Guided Cognitive Model of Visuospatial Complexity in Embodied Active Vision

  Vasiliki Kondyli, Jakob Suchan, Mehul Bhatt · 26 August 2026

  We propose a novel framework for the analysis of multimodal data -- encompassing visual, auditory, and spatial stimuli -- foregrounding the role of complexity in embodied perception and interaction in dynamic, naturalistic settings. Grounded in theories of embodied cognition and active vision, we ar…

• Feature Evolution and Migration during Vision Transformer Training

  Joonas J\"arve, Halil Ibrahim Aysel, Tarun Khajuria, Meelis Kull · 21 August 2026

  We present a novel view on feature evolution in Vision Transformers (ViTs) by visualizing the training process over two dimensions -- network depth (layer) and training time (epochs). We employ Sparse Autoencoders (SAEs) to extract candidate sparse features from CLS-token representations and compare…

• Beyond Trial Averaging: Anchoring Neural and Visual Representations for Few-Repetition Brain-to-Image Retrieval

  Zhenyao Cui, Siyuan Kan, Dingkun Liu, Dongrui Wu · 20 August 2026

  Decoding visual information from brain signals probes neural representations and enables neuro-rehabilitation and dream decoding. Recent brain-to-image retrieval approaches have achieved promising performance, typically by averaging many (up to 80) neural trials per image, requiring repeated stimulu…

• Bidirectional representational alignment between biological and artificial neural networks

  Samuel Kostousov, Abhinn Kaushik, Brokoslaw Laschowski · 20 August 2026

  Recent work has shown that representational alignment between biological and artificial neural networks is asymmetric: model representations predict neural responses much better than neural responses predict model representations. This asymmetry raises the question of whether representational geomet…