Searcharxiv⌕ Search

arXiv subjects

Jiook Cha

Publications and source records attributed to Jiook Cha.

At least 19 recordsLinked to original sources
arXiv2026

PALM: Physically-Anchored Latent-timescale Mamba for Stable Representations under Distribution Shift

Scientific foundation models are built to reuse representations across datasets and acquisition protocols, yet their representations degrade under distribution shift. We trace one source of this failure to selective state-space models (SSMs). Their memory depends on the step Delta and the state matrix A only through their product, so data do not identify the physical timescale of memory, and under a shift the resulting memory no longer matches the signal's timescales. We call this failure memory-timescale misalignment. To resolve it, the split between Delta and A must be tied to physical units. We therefore propose Physically-Anchored Latent-timescale Mamba (PALM), which disentangles A from Delta by anchoring both to acquisition units: Delta through spectrum-estimated knee frequencies and A through a physical memory range. We evaluate PALM against parameter-matched baselines in two domains, under temporal-context truncation, low-resource transfer, and brain-state shift on fMRI and under held-out-station forecasting on Weather-5K. Under fMRI context truncation with run-level spectral calibration, PALM keeps its latent timescales in physical units and retains 11% higher representation similarity than Mamba2. At geographically isolated weather stations never seen during training, PALM achieves the lowest error on every variable and horizon, 15.2% below the best baseline on average, and outperforms zero-shot forecasting foundation models. Across both domains, the gains come from where the backbone places memory in physical time rather than from model size. We therefore argue that physically anchored latent timescales are a design requirement for scientific foundation models that must transfer across acquisition conditions.

cs.LG↗
arXiv2026

Structure, Dimensionality, and Distribution Shape - What Makes Pretraining Data Transferable, and Why the Input Pipeline Decides Which

What makes a pretraining corpus transferable? We describe a corpus by three properties: its structure, its dimensionality, and the distribution shape of each unit's values. We propose the Transfer-Invariance Principle: the same property can be irrelevant to transfer under one input transform and decisive under another, so the model's input transform, not the data modality, decides which properties can matter. To test it we build TransferForge, a generator that places a synthetic population at any prescribed structure, dimensionality, and distribution shape. KernelSynth, the synthetic prior of Chronos, cannot, because it draws independent series. When the model standardizes each input window (PatchTST on UCR), the distribution shape is inert and the structural setting governs. Synthetic pretraining then matches a real corpus of the same size and exceeds it once scaled. When the model encodes calcium fluorescence signals without normalization (POYO Plus), the shape becomes a governing constraint, and a shape-matched synthetic corpus replaces real pretraining with zero real neural activity. Flipping only the input normalization, with the model and data fixed, changes the effect of a shape manipulation by a factor of 5.3, so the pipeline, not the modality, sets the switch. The principle yields a recipe that chooses what to synthesize before any training. Pretraining data then becomes something to manufacture for the model, most valuably where real data is scarce, expensive, or private.

cs.LG↗
arXiv2026

Accurate MRI-free PET Quantification and Reliability Assessment via CT-to-MRI Synthesis and Conformal Prediction

Standardized uptake value ratio (SUVR) quantification of amyloid PET commonly relies on a subject-specific T1-weighted MRI, yet a usable MRI is not always available. We therefore combined CT-to-MRI synthesis with conformal prediction for MRI-free PET quantification with reliability assessment. A slice-consistent Brownian Bridge Diffusion Model was strengthened with multi-dataset training and data-source conditioning to enrich the anatomical prior learned from MRI, and with expanded multi-slice CT context to exploit the through-plane continuity of subject-specific anatomy in CT. Synthetic MRI was used for FreeSurfer-based anatomical parcellation and PET quantification, while deep-ensemble uncertainty was calibrated with conformal prediction to estimate a plausible range for the corresponding real MRI-based SUVR. On $^{11}$C-PiB PET from OASIS-3, the proposed method achieved the highest synthesis and parcellation fidelity among the compared methods. Mean cortical SUVR from the proposed synthetic MRI agreed closely with the real MRI-based reference (MAE $0.016 \pm 0.015$, Pearson $r = 0.9987$) and yielded the same amyloid-positivity classification as the real MRI in all 87 test subjects at the prespecified cut-off. Conformal prediction achieved empirical coverage close to the prespecified levels, and at 90% target coverage, 85 of 87 subjects had prediction intervals that supported an unambiguous amyloid-positivity decision. Zero-shot evaluation on an independent external cohort showed that the proposed CT-to-MRI model could support PET quantification without retraining, although conformal calibration required target-cohort recalibration to recover the intended coverage. These findings support CT-to-MRI-based MRI-free PET quantification as a promising approach for providing accurate SUVR measurements and an explicit assessment of their reliability.

cs.CV↗
arXiv2026

Pretraining Shapes Spectral Structure: Architecture- and Strategy-Conditional Prediction of OOD Robustness in Foundation Models

Can we determine whether a foundation model will generalize out-of-distribution (OOD) before any target data is available? Existing diagnostics require source or target data, which rules them out before a target domain exists. Those that use the weights alone apply one statistic to every architecture, and do not separate robust models from fragile ones. We show the answer is encoded in the spectral structure of pretrained weights. Two forces shape that structure. Architecture determines how information is stored in weight matrices. Pretraining strategy determines what is rewarded. Together they set a spectral geometry that governs OOD robustness. We prove that the OOD accuracy gap is bounded by how tightly the source representations concentrate. A statistic computed from the pretrained weights alone serves as a proxy for that concentration. The direction of that proxy reverses between architecture families. We operationalize it: the direction is stable within one (architecture X strategy) combination, the finest grouping we test, which we call a cell. Pooled over 116 models spanning 7 modalities, a single statistic ranks OOD robustness weakly, because cells of opposite direction cancel. Within a cell, the statistic selected for it orders 92% of model pairs by OOD robustness in-sample. The selection does not leak the target: for each model family outside the matrix we logged the cell, metric and sign before running its OOD evaluation, and the predicted direction held in every case: EEG, genomic and protein. Acting on spectral concentration narrows the OOD gap by 24% at 87.5% ID retention. The diagnostic operates on released weights alone, so OOD robustness becomes checkable at model-selection time, before data or compute is committed to a target domain.

cs.LG↗
arXiv2026

Neural Data Needs Semantic Tokenization: Behavioral Events as Boundaries of Session-Transferable Tokens

Extracellular electrophysiology records a different set of neurons in every session. Neural foundation models embed each neuron and each session into their tokens, so every new session is an input they have never seen, and they fail to generalize to it. A tokenizer for new sessions needs a unit that every session shares and that carries behavior. Population activity offers such a unit. It evolves on a low-dimensional manifold that persists across neuronal turnover and across animals once sessions are aligned. This manifold changes regime at task events such as stimulus onset and movement onset. Within each regime the population occupies a state, the part of the manifold it spans between two events, and each state carries its own behavioral meaning. We propose Tokenization with States (TWS), which segments each trial, one repetition of the task, at these events and converts every state into tokens of population geometry, with no neuron or session embedding. On held-out International Brain Laboratory (IBL) sessions, TWS decodes movement even from regime boundaries that carry no information about the target, while a per-neuron foundation model pretrained on those sessions decodes at chance. Frozen after training on mice alone, TWS transfers to macaques and Utah arrays with only a linear probe. On reach direction, a target that its boundaries do not define, it achieves a Matthews correlation of 0.23, where the event time alone achieves $0.01$. For cross-session generalization, the token matters more than the model on top.

cs.LG↗
arXiv2026

BAT-CLIP: Trimodal Alignment of Brain, Audio and Text

Decoding and interpreting naturalistic speech from the brain increasingly relies on alignment to pretrained speech and language representation spaces. However, current CLIP-style brain-speech alignment ground neural activity to a single anchor modality-audio or text-despite the brain's inherently multimodal speech processing. This induces a trade-off: audio anchoring preserves temporal structure but weakens linguistic separability, while text anchoring captures semantics yet discards acoustic detail. We propose BAT-CLIP, the first CLIP-style trimodal alignment framework for iEEG that jointly aligns neural embeddings to both pretrained audio and text anchors in a shared, frozen audio-text manifold. On the naturalistic Podcast benchmark, BAT-CLIP yields more robust representations than bimodal CLIP baselines. We also highlight the importance of using self-supervised foundation models for CLIP training.

cs.SD↗
arXiv2026

SEED: Towards More Accurate Semantic Evaluation for Visual Brain Decoding

We present SEED (Semantic Evaluation for Visual Brain Decoding), a novel metric for evaluating the semantic decoding performance of visual brain decoding models. It integrates three complementary metrics, each capturing a different aspect of semantic similarity between images inspired by neuroscientific findings. Using carefully crowd-sourced human evaluation data, we demonstrate that SEED achieves the highest alignment with human evaluation, outperforming other widely used metrics. Through the evaluation of existing visual brain decoding models with SEED, we further reveal that crucial information is often lost in translation, even in the state-of-the-art models that achieve near-perfect scores on existing metrics. This finding highlights the limitations of current evaluation practices and provides guidance for future improvements in decoding models. Finally, to facilitate further research, we open-source the human evaluation data, encouraging the development of more advanced evaluation methods for brain decoding. Our code and the human evaluation data are available at https://github.com/Concarne2/SEED.

cs.CV↗
arXiv2026

Image Classification on IBM Quantum Computers

Quantum machine learning on real noisy intermediate-scale quantum (NISQ) hardware has remained largely confined to binary or few-class tasks, limited by the cost of on-hardware training and the underuse of large devices at inference. We present a unified framework that classifies ten-class MNIST end-to-end on a $127$-qubit IBM Eagle processor, with three central contributions. First, a two-phase protocol decouples a gradient-based classical optimization of the encoder and readout from a gradient-free optimization of the quantum parameters, removing the parameter-shift gradient cost that makes on-hardware training impractical. Second, we introduce Quantum Multi-Programming to a trained quantum classifier for the first time, packing multiple circuit copies onto one device to deliver parallel inference at no mean-accuracy cost while cutting quantum-processor job submissions proportionally. Third, a controlled comparison shows that on-hardware fine-tuning yields no measurable accuracy gain, motivating a practical NISQ workflow: train on a classical simulator and reserve the hardware for inference only. Benchmarked against a matched-capacity classical network, the quantum module shows no per-parameter accuracy advantage at this scale; we therefore frame the work as a feasibility-and-workflow demonstration for multi-class quantum image classification on current hardware.

quant-ph↗
arXiv2026

DIVER-1: Scaling Intracranial EEG Foundation Models for Transferable Representations

Intracranial EEG (iEEG) provides direct, millisecond-scale recordings of human neural activity, but reusable representation learning is difficult because electrode layouts, anatomical coverage, referencing schemes, and recording conditions vary across patients and centers. We introduce DIVER-1, a self-supervised iEEG foundation model for variable-input recordings that combines any-variate electrode-time attention, spatio-temporal resampling, input-conditioned positional embeddings, and multi-domain masked reconstruction without assuming a fixed electrode montage. We pretrain two variants, DIVER-1-0.1s and DIVER-1-1s, on 5,310 hours of ECoG and SEEG spanning 352k channel-hours, roughly 54x the BrainTreeBank-based pretraining volume. We evaluate DIVER-1 on two held-out benchmarks: Neuroprobe for naturalistic cognitive decoding and MAYO for seizure detection. On leakage-aware Neuroprobe, DIVER-1-0.1s outperforms prior evaluated iEEG foundation models despite using no BrainTreeBank recordings, the corpus underlying Neuroprobe, during pretraining; it also exceeds the linear spectrogram decoder in mean AUROC and remains competitive with stronger nonlinear baselines, a level prior evaluated iEEG foundation models did not reach. DIVER-1-1s also achieves the top AUROC on MAYO seizure detection. Finally, we conduct, to our knowledge, the first controlled compute-aware scaling study for self-supervised iEEG pretraining, sweeping data scale, subject count, training duration, and model size up to 1.8B parameters. Our results indicate a data-constrained regime: expanding unique recordings and training sufficiently long are more reliable scaling axes than increasing parameter count alone. Code is available at link.

cs.LG↗
arXiv2026

Repurposing Image Diffusion Models for Training-Free Music Style Transfer on Mel-spectrograms

Music style transfer blends source structure with reference style to enable personalized music creation. However, existing zero-shot methods often struggle to capture fine-grained audio nuances, relying on coarse text descriptions or requiring expensive task-specific training. We propose Stylus, a training-free framework that repurposes pretrained image diffusion models for music style transfer in the Mel-spectrogram domain. By treating audio as structured time-frequency images, Stylus manipulates self-attention by injecting style keys and values while preserving source structural queries. To ensure high fidelity, we introduce a phase-preserving reconstruction strategy to mitigate spectrogram inversion artifacts, alongside a classifier-free-guidance-inspired control for adjustable stylization. Extensive evaluations including 2,925 human ratings demonstrate that Stylus outperforms state-of-the-art baselines, achieving 34.1% higher content preservation and 25.7% better perceptual quality. Our work validates that generic image priors can be effectively leveraged for the training-free transformation of structured Mel-spectrograms. Code and materials are available at https://github.com/Sooyyoungg/Stylus.git.

cs.SD↗
arXiv2026

Decoding Dynamic Visual Experience from Calcium Imaging via Cell-Pattern-Aware Pretraining

Neural recordings exhibit a distinctive form of heterogeneity rooted in differences in cell types, intrinsic circuit dynamics, and stochastic stimulus-response variability that goes beyond ordinary dataset variability, mixing statistically regular neurons with highly stochastic, stimulus-contingent ones within the same dataset. This heterogeneity poses a challenge for self-supervised learning (SSL) -- learnable statistical regularity -- thereby destabilizing representation learning and limiting reliable scaling. We introduce POYO-CAP (Cell-pattern Aware Pretraining), a biologically grounded hybrid pretraining strategy that first trains with masked reconstruction plus lightweight auxiliary supervision on statistically regular neurons -- identified via skewness and kurtosis -- and then fine-tunes on more stochastic populations. On the Allen Brain Observatory dataset, this curriculum yields 12--13\% relative improvements over from-scratch training and enables smooth, monotonic scaling with model size, whereas baselines trained on mixed populations plateau or destabilize. By making statistical predictability an explicit data-selection criterion, POYO-CAP turns neural heterogeneity into a scalable learning advantage for robust neural decoding.

q-bio.NC↗
arXiv2026

Latent-Space Causal Discovery from Indirect Neuroimaging Observations

Neuroimaging does not observe causal variables directly: hemodynamics and volume conduction distort signals so that statistical dependence need not reflect latent neural influence. Before estimating graphs, one must specify under what assumptions delayed directed structure can be studied from such indirect observations. We formalize a conditional setting - recoverable inversion under modality physics together with nonstationary latent dynamics - and derive an inversion-error propagation bound under explicit assumptions. Building on this framing, we propose INCAMA (INdirect CAusal MAmba): physics-aware inversion coupled with a delay-aware Mamba encoder that uses mechanism shifts as informative variation for directed graph scoring. We use controlled simulations for quantitative validation and HCP motor-task fMRI as a zero-shot external transfer check based on anatomical and task-network consistency. Across TVB simulations, INCAMA improves directed-structure recovery by 2-3x in F1 over observation-space and two-stage baselines, and on HCP motor-task fMRI it produces sparse directed estimates concentrated in canonical visuo-motor pathways.

q-bio.NC↗
arXiv2026

Can Natural Image Autoencoders Compactly Tokenize fMRI Volumes for Long-Range Dynamics Modeling?

Modeling long-range spatiotemporal dynamics in functional Magnetic Resonance Imaging (fMRI) remains a key challenge due to the high dimensionality of the four-dimensional signals. Prior voxel-based models, although demonstrating excellent performance and interpretation capabilities, are constrained by prohibitive memory demands and thus can only capture limited temporal windows. To address this, we propose TABLeT (Two-dimensionally Autoencoded Brain Latent Transformer), a novel approach that tokenizes fMRI volumes using a pre-trained 2D natural image autoencoder. Each 3D fMRI volume is compressed into a compact set of continuous tokens, enabling long-sequence modeling with a simple Transformer encoder with limited VRAM. Across large-scale benchmarks including the UK-Biobank (UKB), Human Connectome Project (HCP), and ADHD-200 datasets, TABLeT outperforms existing models in multiple tasks, while demonstrating substantial gains in computational and memory efficiency over the state-of-the-art voxel-based method given the same input. Furthermore, we develop a self-supervised masked token modeling approach to pre-train TABLeT, which improves the model's performance for various downstream tasks. Our findings suggest a promising approach for scalable and interpretable spatiotemporal modeling of brain activity. Our code is available at https://github.com/beotborry/TABLeT.

cs.CV↗
arXiv2026

Q-DIVER: Integrated Quantum Transfer Learning and Differentiable Quantum Architecture Search with EEG Data

Integrating quantum circuits into deep learning pipelines remains challenging due to heuristic design limitations. We propose Q-DIVER, a hybrid framework combining a large-scale pretrained EEG encoder (DIVER-1) with a differentiable quantum classifier. Unlike fixed-ansatz approaches, we employ Differentiable Quantum Architecture Search to autonomously discover task-optimal circuit topologies during end-to-end fine-tuning. On the PhysioNet Motor Imagery dataset, our quantum classifier achieves predictive performance comparable to classical multi-layer perceptrons (Test F1: 63.49\%) while using approximately \textbf{50$\times$ fewer task-specific head parameters} (2.10M vs. 105.02M). These results validate quantum transfer learning as a parameter-efficient strategy for high-dimensional biological signal processing.

quant-ph↗
arXiv2026

Hybrid Quantum Temporal Convolutional Networks

Quantum machine learning models for sequential data face scalability challenges with complex multivariate signals. We introduce the Hybrid Quantum Temporal Convolutional Network (HQTCN), which combines classical temporal windowing with a quantum convolutional neural network core. By applying a shared quantum circuit across temporal windows, HQTCN captures long-range dependencies while achieving significant parameter reduction. Evaluated on synthetic NARMA sequences and high-dimensional EEG time-series, HQTCN performs competitively with classical baselines on univariate data and outperforms all baselines on multivariate tasks. The model demonstrates particular strength under data-limited conditions, maintaining high performance with substantially fewer parameters than conventional approaches. These results establish HQTCN as a parameter-efficient approach for multivariate time-series analysis.

cs.LG↗
arXiv2025

Scalable Diffusion Transformer for Conditional 4D fMRI Synthesis

Generating whole-brain 4D fMRI sequences conditioned on cognitive tasks remains challenging due to the high-dimensional, heterogeneous BOLD dynamics across subjects/acquisitions and the lack of neuroscience-grounded validation. We introduce the first diffusion transformer for voxelwise 4D fMRI conditional generation, combining 3D VQ-GAN latent compression with a CNN-Transformer backbone and strong task conditioning via AdaLN-Zero and cross-attention. On HCP task fMRI, our model reproduces task-evoked activation maps, preserves the inter-task representational structure observed in real data (RSA), achieves perfect condition specificity, and aligns ROI time-courses with canonical hemodynamic responses. Performance improves predictably with scale, reaching task-evoked map correlation of 0.83 and RSA of 0.98, consistently surpassing a U-Net baseline on all metrics. By coupling latent diffusion with a scalable backbone and strong conditioning, this work establishes a practical path to conditional 4D fMRI synthesis, paving the way for future applications such as virtual experiments, cross-site harmonization, and principled augmentation for downstream neuroimaging models.

cs.CV↗
arXiv2025

Macro2Micro: A Rapid and Precise Cross-modal Magnetic Resonance Imaging Synthesis using Multi-scale Structural Brain Similarity

The human brain is a complex system requiring both macroscopic and microscopic components for comprehensive understanding. However, mapping nonlinear relationships between these scales remains challenging due to technical limitations and the high cost of multimodal Magnetic Resonance Imaging (MRI) acquisition. To address this, we introduce Macro2Micro, a deep learning framework that predicts brain microstructure from macrostructure using a Generative Adversarial Network (GAN). Based on the hypothesis that microscale structural information can be inferred from macroscale structures, Macro2Micro explicitly encodes multiscale brain information into distinct processing branches. To enhance artifact elimination and output quality, we propose a simple yet effective auxiliary discriminator and learning objective. Extensive experiments demonstrated that Macro2Micro faithfully translates T1-weighted MRIs into corresponding Fractional Anisotropy (FA) images, achieving a 6.8\% improvement in the Structural Similarity Index Measure (SSIM) compared to previous methods, while retaining the individual biological characteristics of the brain. With an inference time of less than 0.01 seconds per MR modality translation, Macro2Micro introduces the potential for real-time multimodal rendering in medical and research applications. The code will be made available upon acceptance.

eess.IV↗
arXiv2025

CausalMamba: Scalable Conditional State Space Models for Neural Causal Inference

We introduce CausalMamba, a scalable framework that addresses fundamental limitations in fMRI-based causal inference: the ill-posed nature of inferring neural causality from hemodynamically distorted BOLD signals and the computational intractability of existing methods like Dynamic Causal Modeling (DCM). Our approach decomposes this complex inverse problem into two tractable stages: BOLD deconvolution to recover latent neural activity, followed by causal graph inference using a novel Conditional Mamba architecture. On simulated data, CausalMamba achieves 37% higher accuracy than DCM. Critically, when applied to real task fMRI data, our method recovers well-established neural pathways with 88% fidelity, whereas conventional approaches fail to identify these canonical circuits in over 99% of subjects. Furthermore, our network analysis of working memory data reveals that the brain strategically shifts its primary causal hub-recruiting executive or salience networks depending on the stimulus-a sophisticated reconfiguration that remains undetected by traditional methods. This work provides neuroscientists with a practical tool for large-scale causal inference that captures both fundamental circuit motifs and flexible network dynamics underlying cognitive function.

cs.CV↗