PyTorchKR Papers

최신 논문

총 91편
태그·기간 등 상세 필터

카테고리 탐색

arXiv:2611.18561v1q-bio.NC

FETTUCCINE: Fast and efficient brain-to-text decoding on mobile devices

Recent advances in speech neuroprostheses have enabled new communication avenues for people who have lost the ability to speak due to neurological illness or injury. These systems can decode neural activity during attempted speech into text by relying on language priors to achieve high decoding accuracy. This performance currently comes at the cost of using a compute-intensive language modeling stack, presenting a major bottleneck for real-world use. Further, current language models incur highly variable and disruptive inference latencies, limiting communication throughput and preventing users from reliably participating in natural conversation. We introduce FETTUCCINE, an end-to-end brain-to-text framework that leverages the speed and portability of automatic speech recognition (ASR) models to address the aforementioned practical challenges, while achieving usable (<10%) word error rates (WER), efficient adaptation to neural non-stationarities, and reliable performance on mobile devices. When evaluated using publicly available data from an intracortical speech neuroprosthesis user, FETTUCCINE outperforms previous end-to-end methods, achieving as low as 4.39% WER. Most notably, our models successfully run on a commercially-available mobile device with throughput reaching up to 370x real-time, providing the first demonstration of brain-to-text decoding on a mobile device. We also show that our models can be successfully finetuned to extend usable performance to future days. Beyond performance, our approach enables localization of the neural features most relevant for decoding via gradient-based saliency maps, which we show align with well-established physiological priors across different ASR model families. Taken together, our results show that FETTUCCINE overcomes core infrastructural and computational barriers, yielding a new class of portable brain-to-text communication.

arXiv:2611.17608v1cs.LG

Neural Simulation-Based Inference for Computational Cognitive Models: A Tutorial

Computational cognitive modeling is an increasingly essential methodology to elucidate the mechanisms underlying human and animal cognition. By fitting models to empirical data, researchers can perform parameter estimation, model comparison, and model-based neural analyses to assess competing theories, quantify individual differences, and investigate neural representations. Typically, fitting these models relies on likelihood-dependent methods (e.g., Maximum likelihood estimation or hierarchical Bayesian methods). However, for many reasonable cognitive models, computing the likelihood is computationally intractable, in which case these methods become inadequate. This substantially limits the range of theories that researchers can investigate. Simulation-based inference with neural networks (neural SBI) has emerged as a powerful toolkit to overcome this hurdle. By training deep neural networks on datasets generated through model simulations, neural SBI learns the relation between observable data and cognitive models. This approach enables all the applications of standard modeling while bypassing the likelihood computation, without constraints on empirical data size. Despite its successful adoption across diverse scientific fields, neural SBI remains underutilized in cognitive modeling, partly due to a lack of accessible, domain-tailored guidance. This tutorial addresses this gap by providing a clear workflow for applying neural SBI to cognitive models. We also provide practical use cases and recommendations for reducing the computational and simulation burden, facilitating efficient implementation in real-world research settings. By lowering the technical barriers to neural SBI, this tutorial aims to empower cognitive scientists to investigate richer theory spaces and ultimately propel scientific discovery.

arXiv:2611.17532v1cs.AI

Astrocyte Biocomputing: Astrocytic Contributions to Neural Network Computation

Conductors are critical for the performance of an orchestra even though they do not emit sound. Basic research and clinical studies in the last decade are revealing that astrocytes may be the "conductors" of the "orchestra" that is the brain network: astrocytes make up approximately $50\%$ of all brain cells but do not emit electrical signals. Nevertheless, they may play critical roles in important cognitive brain functions, specifically learning, memory, and information processing. Here we consider the implications of these discoveries for brain-inspired machine learning (ML), where analogy is typically drawn between neurons and their electrical interactions. We highlight specific algorithms for two key astrocyte characteristics. The first characteristic is the ability to link to and modulate thousands of synapses simultaneously. A model based on this characteristic yields faster training and makes the network more robust to noise, providing a supervised learning algorithm that can be applied to any existing neural network. The second characteristic we focus on is that the non-electrical communication among astrocytes includes slow, rhythmic dynamics. The rhythmic sharing algorithm we developed based on this premise yields rapid anomaly detection adaptation and prevents catastrophic forgetting. Overall, we find that astrocyte-derived algorithms outperform neurocentric algorithms significantly and remediate critical weaknesses of current state-of-the-art ML models.

arXiv:2611.06700v3cs.LG

PINR-ESI: Physics-Informed Self-Supervised Implicit Neural Representation Framework for EEG Extended-Source Imaging

EEG extended-source imaging aims to localize active cortical regions and characterize their extent, yet supervised inverse networks typically depend on synthetic EEG-source pairs and may be sensitive to synthetic-to-real mismatch. We propose a physics-informed self-supervised implicit neural representation (INR) framework for spatial source reconstruction without paired source labels or simulation-based supervised pretraining. The lead-field matrix encodes the source-to-sensor volume-conduction model and constrains the INR through agreement between predicted and measured EEG. Cortical current density is represented as a continuous coordinate-based neural field. Forward EEG prediction samples the field at cortical vertices and applies local smoothing before lead-field mapping. A classical inverse estimate provides warm initialization and observation-specific spatial guidance through prior-guided support regularization. Simulations across varying SNRs, source extents, and source counts showed low spatial dispersion and good localization performance. Quantitative evaluation on clinical EEG recordings from epilepsy patients and qualitative analysis of scalp EEG during intracranial stimulation supported feasibility for real-world source imaging. These findings suggest the potential of physics-informed self-supervised INR for extended-source imaging.

arXiv:2610.10850v2cs.LG

Similar Predictive Fit but Different Latent Dynamics: Characterizing Learned Dynamical Structure in Personalized Models of Brain Disorders

As AI models move toward clinical decision-making and personalized treatment, understanding \emph{what} a model learns is important beyond predictive accuracy alone. We investigate whether personalized latent dynamics reveal clinically associated differences even when predictive fit is similar. A lightweight CNN--Transformer EEG foundation model pretrained on the Temple University EEG Corpus (TUEG) extracts segment-level representations. Using the Temple University Epilepsy Corpus (TUEP), representations are mapped to a shared latent-state space, and sparse multinomial logistic transition distributions (mLTD) are fit independently to each subject to obtain personalized transition-dependency graphs $W_n$. Analyses include $n{=}198$ subjects (99 epilepsy / 99 non-epilepsy). At $k{=}4$, epilepsy subjects exhibit substantially denser learned dependency structure ($p{=}1.1\times10^{-7}$), with the same pattern at $k{=}6$ (19.90 vs. 13.46; $p{=}5.2\times10^{-5}$). Graph-derived features provide moderate group discrimination under 5-fold subject-wise cross-validation (AUROC 0.68 at $k{=}4$; 0.65 at $k{=}6$). In contrast, held-out log-likelihood is nearly identical between groups at $k{=}4$ ($-0.992$ vs. $-0.991$; $p{=}0.95$), with similarly matched next-state prediction (AUROC 0.855 vs. 0.861; $p{=}0.54$). Thus, similar predictive fit does not imply similar learned dynamics: groups can be comparably predictable while differing substantially in the internal dynamical structure learned by personalized models. This distinction motivates evaluating learned structure alongside predictive performance in personalized clinical models.

arXiv:2610.05503v2cs.LG

Lightweight Semantic EEG Foundation Model for Frozen Cross-Disorder Transfer

Large-scale EEG foundation models have demonstrated promising transferability across neurological disorders, but often require millions of parameters and substantial computational resources. In this paper, we present the Universal Semantic EEG Foundation Model (USE-FM), a lightweight EEG foundation model that learns transferable neural representations through self-supervised signal reconstruction on the Temple University Hospital EEG Corpus (TUEG). After pretraining, the encoder is frozen and evaluated on two clinically distinct downstream tasks, abnormal EEG detection (TUAB) and epileptic seizure recognition (TUEP), using a unified frozen-transfer protocol against recent EEG foundation models, including LUNA-Base and CBraMod. With only 1.46 million parameters, approximately one-fifth the size of existing models, USE-FM achieves competitive overall performance, including strong sensitivity and F1-score on TUEP (SEN $75.00 \pm 14.14$, F1 $70.37 \pm 4.01$), while maintaining competitive performance on TUAB (AUC $85.24 \pm 5.61$). Beyond downstream classification, latent representation analysis using $k$-means clustering together with PCA and t-SNE demonstrates that USE-FM learns organized semantic EEG representations comparable to substantially larger foundation models. These results suggest that large-scale self-supervised pretraining enables lightweight architectures to learn transferable semantic EEG representations, providing a computationally efficient foundation for cross-disorder analysis and future clinical decision support in neurological disorders.

arXiv:2609.08070v3cs.NE

Local Spike Timing Enables Gradient-based Learning in Neural Microcircuits

The brain uses discrete spikes for dynamic computation, yet in the fields of computational neuroscience and brain-inspired computing, how neural microcircuits (NMCs) solve temporal credit assignment using local spike timing remains a fundamental open question. Dominant spiking neural network (SNN) approaches circumvent this by approximating backpropagation through surrogate gradients, decoupling learning from biological spike timing. In order to integrate seemingly incompatible spike timing and continuous gradients, we reformulate temporal credit assignment as a state separation problem: extracting task-required components induced by historical perturbations directly from the current neural state. This enables an online feedback learning framework for NMCs through a gradient tunneling (GT) algorithm and the lead-lag expansion technique that derives credit assignment from local synaptic spike timing, while remaining compatible with ANN-SNN hybrid architectures. Experimentally, GT-trained NMCs excel at long-timescale evidence integration and noise-robust memory retention, and perform comparably to leading SNN online learning methods on real-world benchmarks with far fewer parameters. The proposed framework addresses the two-decade-old NMC feedback learning problem and suggests a computational theory for the brain's temporal credit assignment mechanisms.

arXiv:2604.21909v3cs.CV

Directional Confusions Reveal Divergent Inductive Biases Through Rate-Distortion Geometry in Human and Machine Vision

Humans and modern vision models can reach similar classification accuracy while making systematically different kinds of mistakes -- differing not in how often they err, but in who gets mistaken for whom and in which direction. We show that these directional confusions reveal distinct inductive biases that are invisible to accuracy alone. Using matched human and deep vision model responses on a natural-image categorization task under 12 perturbation types, we quantify asymmetry in confusion matrices and link it to the shape of the information-error trade-off. We characterize this trade-off geometry using three signatures extracted from the rate-distortion (RD) frontier: slope beta, curvature kappa and efficiency (AUC). We find that humans exhibit broad but weak asymmetries, whereas deep vision models show sparser, stronger directional collapses. Robustness training reduces global asymmetry but fails to recover the human-like breadth-strength profile of graded similarity. Mechanistic simulations further show that different asymmetry organizations shift the RD frontier in opposite directions, even when matched for performance. Together, these results position directional confusions and RD geometry as compact, interpretable signatures of inductive bias under distribution shift.

arXiv:2603.09600v3q-bio.NC

A Variational Latent Equilibrium for Learning in Neuronal Circuits

Brains remain unrivaled in their ability to recognize and generate complex spatiotemporal patterns. While AI is able to reproduce some of these capabilities, deep learning algorithms remain largely at odds with our current understanding of brain circuitry and dynamics. This is prominently the case for backpropagation through time (BPTT), the go-to algorithm for learning complex temporal dependencies. In this work we propose a general formalism to approximate BPTT in a controlled, biologically plausible manner. Our approach builds on, unifies and extends several previous approaches to local, time-continuous, phase-free spatiotemporal credit assignment based on principles of energy conservation and extremal action. Our starting point is a prospective energy function of neuronal states, from which we calculate real-time error dynamics for time-continuous neuronal networks. With this, as a first contribution we provide a simple and straightforward derivation of the adjoint method dynamical equations, the time-continuous equivalent to BPTT. Importantly, additional approximations are necessary to avoid unphysical temporal non-localities. One such approximation was recently proposed in Generalized Latent Equilibrium (GLE), but enforcing temporal locality of the backpropagating dynamics induces an error in the gain that becomes problematic when processing complex signals. Thus, our second contribution is to design a learning rule for the backward weights to find a fully local (in space and time) set of equations for neuron and synapse dynamics that corrects for this gain difference. With this inclusion of backward weight learning, our theory provides a rigorous framework for spatiotemporal deep learning in the brain, while simultaneously advancing a blueprint for physical circuits capable of carrying out these computations.

arXiv:2611.18105v1q-bio.NC

An In-Silico Audit of Topographic Organization in a Multimodal Brain-Response Model

TRIBE v2 (d'Ascoli et al., 2026) predicts fMRI responses across the cortical surface from video, audio and text. Its authors validated it with category-selective localizers (faces, places, bodies, words) and language contrasts, but not with the classic topographic organization of sensory cortex: retinotopy, tonotopy, and motion selectivity in area MT+. There is a clear architectural reason to expect retinotopy to fail: TRIBE's video features are averaged over space before the response head, which should discard visual-field position. I present mapping stimuli, a fitting pipeline adapted from standard fMRI mapping analyses, and a stand-in model with known ground truth that serves as a positive and negative control, and apply them to TRIBE v2's predictions, comparing the fitted maps with human atlases using spin tests. TRIBE v2 shows a sharp split. There is no contralateral hemifield response and no polar-angle map, robustly across stimulus controls. There is no tonotopic gradient in primary auditory cortex: best frequencies span an interquartile range of only 0.14 octaves across core and belt, and the null persists with loudness-equalized tones. An eccentricity-like gradient appears only when the ring geometry changes, consistent with global image statistics rather than a positional code. In contrast, motion selectivity is strong and precisely localized: 22% of the 1% most motion-selective vertices fall in MT+, which covers 0.42% of cortex. In-silico experiments that depend on feature identity appear viable with TRIBE v2, while those that depend on visual-field or frequency position are not supported by the current model.

arXiv:2611.14498v2cs.CV

Measuring Robustness and Efficiency in a Connectome-Constrained Fly Visual System Model: Linking an Adversarial and a Perceptual Illusion

Biological visual systems compute reliably under tight metabolic and wiring constraints, whereas artificial vision systems consume far more energy and can be sensitive to adversarial perturbations. Whether networks with brain-like wiring are more robust at lower computational cost is unclear. We address this by benchmarking a task-optimized, continuous-time recurrent neural network of the fly visual system constrained by its synaptic connectome (FlyNet) against artificial neural networks. We compare it against CNNs, RAFT, and continuous-time recurrent neural networks without detailed connectome constraints (sCTRNN, CTRNN) on a collision-detection task within a differentiable 3D rendering pipeline. FlyNet is adversarially vulnerable but, relative to its compute, more robust to common video corruptions than RAFT, while using up to five orders of magnitude fewer FLOPs. The CTRNNs remain more robust than FlyNet across almost all tested perturbations, suggesting that connectome constraints benefit efficiency, through their low edge count, over robustness. Recurrence improves robustness to white-box attacks in RAFT and temporal context improves robustness to common corruptions. FlyNet's position and velocity representations degrade under adversarial textures but recover under counterfactual textures that restore correct classification while staying equally far from training, ruling out unfamiliar textures as the cause of failure. The reverse-phi illusion similarly disrupts these representations and inverts the same low-level motion statistic as the adversarial textures. Optimizing this input statistic alone, without access to the network, suffices to induce classification failure, attributing both perturbations to the same circuit vulnerability. Connectome-constrained models can thus surface adversarial failure mechanisms as testable hypotheses about biological perceptual vulnerabilities.

arXiv:2611.03841v1q-bio.NC

Evolved Spiking Neural Networks for EEG Seizure Detection: Calcium Dynamics and Delay Mechanics

Neuroevolution can discover compact network designs that are hard to specify by hand. The EONS framework evolves the topology, weights, thresholds and delays of neuromorphic spiking networks without gradients. We tested whether giving integrate-and-fire (IF) neurons an activity-dependent calcium current (Ca-IF neurons) improves evolved networks for EEG seizure detection, with calcium parameters fixed, shared across a network, or evolved for each neuron. On 10 held-out CHB-MIT patients never seen in training, per-neuron calcium raised the record-level Matthews correlation coefficient (MCC) from 0.592 to 0.726 over 20 independent runs (p = 0.008) and lowered the false-alarm rate from 0.17 to 0.10. Fixed or per-network calcium gave no significant benefit. IF networks with evolved synaptic delays of 1-3 ticks gave a similar gain (p = 0.005), whereas axonal delays did not. On Siena, with unchanged settings, per-neuron calcium gained +0.096 MCC over IF in one patient-disjoint split (p = 0.011) and +0.059 in the other (p = 0.052). These results suggest that calcium and delays may make the evolutionary search more effective, and motivate testing on more data and in neuromorphic hardware.

arXiv:2609.13219v2q-bio.NC

Planning as Dynamics Relaxation: Hippocampal Recurrent Network Realizes Optimal Goal-Directed Navigation

Neural correlates of the cognitive map are well documented, yet how a neural circuit turns a stored map into an obstacle-avoiding route remains unclear. Here we show that a hippocampal network with appropriate recurrent connections achieves optimal goal-directed navigation through its own relaxation dynamics. The recurrent weights represent the transition probabilities between the locations the neurons encode, walls are reflected by vanishing weights, and behavioral-timescale synaptic plasticity (BTSP) writes this connectivity during goal-free exploration. When a goal is recalled, a top-down current clamps the goal neuron and the population relaxes into a goal-locked activity field. We prove that this field is the desirability field of a linearly-solvable Markov decision process: the relaxed state is the exact optimum of a stated control problem, the KL-regularized objective of Todorov, and the optimal next-step distribution is carried by the branch synaptic currents. The identity extends to directed transitions, and a weak-cost limit returns the Green's function of the recurrent Laplacian. A place-tuned readout converts the field's log-gradient into a direction of travel, and the same synapses answer a predictive query when the source is placed at the current location. Simulations on mazes with complex obstacles show near-shortest routes, an identity that survives a thousand-fold range of recall amplitude, the loss of 80% of place cells, and tens of thousands of states, low-rank updates of every plan after a local change, and a transient that is anytime: the local action is ready long before the field converges. We hope this offers a general circuit principle for planning in abstract cognitive maps beyond spatial navigation.

arXiv:2609.10947v4q-bio.NC

The Platonic brain bridge hypothesis: brain networks as architectural priors for multimodal large language models

Multimodal large language models predict brain activity, but alignment has remained a measurement, not a design tool. We propose the Platonic brain bridge hypothesis: omni models, which jointly process video, audio and text, share brain-like representations usable in both directions. From model to brain, seven omni models show stable brain-likeness across participants, and our encoding experts lead the Algonauts 2025 out-of-distribution leaderboard by mean score. From brain to model, we make three contributions. Brain-MoE ties the experts of a frozen model to the seven cortical networks, raises held-out accuracy in all 15 model-benchmark pairs and exceeds capacity-matched random experts in 14. Brain-AVQA, to our knowledge the first audiovisual benchmark with cortical-network labels for every question, supplies the pretraining questions. Brain-Scope finds sparse features that predict brain responses, steer routing and, when removed, weaken brain prediction. Human brain organization is therefore a usable architectural prior for multimodal large language models.

arXiv:2602.02605v3cs.NE

Fine-Tuning Language Models to Know What They Know

Evaluating true metacognition in Large Language Models (LLMs) is difficult due to biases and heuristics. This paper presents a framework to measure and enhance LLM metacognition while controlling for these biases. A measurement method using the $d'_{\rm type2}$ metric is established to isolate metacognitive ability. The Evolution Strategy for Metacognitive Alignment (ESMA) is proposed, demonstrating robust generalization across unseen datasets, languages, and newly acquired knowledge. Gradual parameter updates reveal that these improvements are driven by a sparse set of parameters, opening a potential avenue for targeted metacognitive optimization.

arXiv:2507.04575v2q-bio.NC

Lilith: Developmental Modular LLMs with Chemical Signaling

Current paradigms in Artificial Intelligence rely on layers of feedforward networks which model brain activity at the neuronal level. We conjecture that expanding to the level of multiple brain regions with chemical signaling may be a productive step toward understanding the emergence of consciousness. We propose LILITH, a novel architecture that combines developmental training of modular language models with brain-inspired token-based communication protocols, mirroring chemical signaling in the brain. Our approach models distinct brain regions as specialized LLM modules including thinking, memory, sensory, and regulatory components that communicate through emergent token-based signaling protocols analogous to neurotransmitter networks. Unlike traditional pre-trained systems, LILITH would employ developmental training where untrained LLM architectures learn through simulated life experiences, developing communication pathways and cognitive abilities through environmental interaction and evolutionary optimization. This framework would enable direct empirical investigation of consciousness emergence using Integrated Information Theory metrics while providing unprecedented insight into inter-module signaling patterns during development. By optimizing for consciousness emergence rather than task performance, LILITH could provide insight into different emergent phenomena at multiple levels of neural correlates, contrasting neuronal-level processing with multi-region coordination dynamics. The goal of this paper is to put the idea forward while recognizing the substantial challenges in implementing such a system.

arXiv:2611.17011v1q-bio.NC

Random Exploration is Random

Decision making often requires balancing exploitation of familiar options with exploration of uncertain alternatives. One strategy for exploration is random exploration, in which choices become more variable and less tied to the option that currently appears best. However, it remains unclear whether this variability reflects genuine stochasticity or instead a deterministic structure that traditional cognitive models fail to capture. We examined this question using the Horizon Task in an aggregated dataset of 1,392 participants completing over 1,270,695 trials. In this task, exploration becomes more valuable when participants have more future choices, and choice variability increases under longer horizons. We tested whether more expressive neural network models could recover deterministic structure from this additional variability. Although neural networks provided better overall fits to behavior than the traditional model, long-horizon choices remained consistently less predictable than short-horizon choices. These findings show that limited model expressiveness cannot fully account for the increased variability associated with random exploration, suggesting random exploration truly is substantially random.

arXiv:2611.16057v1q-bio.NC

Pyramidal Columns Acting as Attention Heads

Can the functional architecture of a Transformer attention head be given a biological construction? More specifically, could a suitable group of pyramidal columns in posterior temporal language regions (PTLRs) constitute the biological construction of a neuromorphic mechanical realization of an attention head, under a mathematical instantiation that need not coincide with its standard Transformer instantiation? This paper investigates this hypothesis by examining possible correspondences between the functional organization of attention heads and neurophysiological mechanisms operating within and across pyramidal columns involved in human language processing. Our analysis builds on a mechanical-structural description of Transformer attention heads as systems of simple neural networks linked through output-input and output-weight interconnections. We examine the functional organization of an attention head and the input-dependent transformations it produces, and ask how the corresponding processing relations could be constructed in biological neural tissue. We then identify candidate neural mechanisms of signal transmission and modulation within and across pyramidal columns that may jointly support such a construction. On this basis, we propose that a suitably organized group of pyramidal columns in PTLRs could constitute a biological construction of a neuromorphic mechanical realization of an attention head. Whether the required functional organization actually exists in PTLRs remains an open empirical question. The hypothesis does not require the biological system to reproduce the standard mathematical instantiation of Transformer attention: the same functional architecture may be mechanically realized and mathematically instantiated in a different way, consistent with its biological construction.

arXiv:2611.16555v1cs.NE

Similarity-Guided Optimization Strategies for Approximate Network Symmetry Detection

Symmetry in complex networks is a structural property with broad implications for network function, dynamics, and robustness. While classical approaches rely on exact automorphisms and thus remain highly sensitive to small perturbations, recent work of Liu has introduced approximate formulations that relax the strict invariance condition and recast symmetry detection as an optimization problem over permutations. We investigate how node-level similarity information can be used to bias the search toward structurally plausible vertex correspondences, with network centralities serving as one interpretable instance. Building on this perspective, we adapt simulated annealing, genetic algorithms, tabu search, particle swarm optimization, differential evolution and the quadratic symmetry approximator to this problem, add similarity guidance to each, and introduce Bilinear Approximate Symmetry Inference (BASIN), which learns a soft assignment matrix via bilinear embeddings. Using a unified evaluation pipeline, we compare their guided and unguided variants, BASIN and a random baseline on four synthetic graph families, structural brain connectomes, and three empirical networks with known automorphism groups. Node-similarity guidance is decisive where a planted orbit exists that the unguided search misses, and algorithm-dependent elsewhere, on synthetic and empirical networks alike. Overall, tabu search achieves the strongest performance; its guided variant (SGTS) has the lowest median score among the guided variants in all 44 synthetic conditions, while BASIN is the better of the continuous relaxations on rewired lateral graphs. The effect of node-similarity guidance is therefore regime-dependent rather than uniformly positive.

arXiv:2611.15046v1q-bio.NC

Prototypes of the Mind: A Unified Framework for Probing the Visual Brain

Deep learning has driven substantial progress in modeling fMRI responses, yet most existing approaches are optimized for a single objective---such as neural encoding, stimulus decoding, or post hoc interpretation---making it difficult to obtain a coherent account of neural representations. We introduce a unified framework that connects vision foundation models to brain activity while supporting neural analysis from multiple complementary perspectives. Our approach replaces black-box features with a sparse, interpretable representation composed of visual prototypes, and links these prototypes to voxel responses through a linear readout. This design makes the model transparent at both levels: prototype activations expose the visual concepts present in the stimulus, while the learned linear weights characterize each voxel's selectivity. Using this interface, we identify which visual concepts drive neural responses and where they appear in the image, reveal cortical organization through voxel tuning in prototype space, and perform controlled stimulus synthesis to probe cortical selectivity through targeted interventions. Together, these results establish prototype-based representations as a unified and interpretable foundation for studying visual representations in the human brain.