Machine Learning · arXiv:2611.11081 v1 · submitted 8 Nov 2026 · 43 references
A Hierarchical Tokenization Framework for Voxel-Level fMRI Representation Learning
The paper says
“We introduce HBAR (Hierarchical Brain Activity Representation), a hierarchical tokenization framework for learning compact, multi-scale representations of neuroimaging data.”
more of the abstract
HBAR organizes voxel-level resting-state fMRI into a hierarchy spanning sub-parcel voxel groups, parcels, and large-scale functional networks, enabling up to 415x compression while preserving fine-grained spatial information beyond conventional parcellation. The framework supports fixed atlas-based, fully learned, and softly prior-guided hierarchies, allowing us to systematically study the role of structured priors in brain representation learning. On HCP-YA, at approximately 415x compression, HBAR achieves higher parcel and network correlations than rate-matched flat tokenizers, while at a lower 52x compression rate, shuffling the anatomical grouping reduces parcel correlation from 0.920 to 0.886. Demographic readouts with autoregressive training also reveal potential gains from the hierarchical structure. By combining sub-parcel inputs, compact discrete tokens, and multiscale brain structure, HBAR offers a practical framework for representation learning in high-dimensional neuroimaging data.
from the abstract
Pith says
Machine review · deepseek-v4-flash · 10 Nov 2026 · what was read was not recorded · not checked by a person
It can be wrong. Challenge this review or reply to it.
The passes disagreed. Reader: holds up. Skeptic: holds up only with conditions. Referee: major revision.
Solid engineering study of hierarchical fMRI tokenization, but evaluation confounded by asymmetric losses – the main claim needs a controlled baseline. This line is wrong
3 major objections · 7 minor
How often objections from reviews like this one are right: not yet measured
Not checked: figures, code, what the 43 references say.
The paper says, at §4.2 and Appendix C.3
The review did not quote this passage.
Pith says: Objection 1 of 3 · major
The central claim that HBAR’s hierarchical tokenization achieves higher parcel and network correlations than flat tokenizers at 415× compression is confounded by asymmetric training objectives. HBAR is trained with explicit parcel and network reconstruction losses (L_P, L_N in Eq. 2), while the flat baselines have no such coarse-scale supervision.
more of objection 1
Because the evaluation metric is the same atlas-based parcel/network correlation, the advantage may reflect the multi-scale objective, not the hierarchical aggregation per se. The shuffled grouping ablation at 52× (same loss structure, different grouping) partially addresses this, but no equivalent control exists at 415×. The authors should either provide an ablation where a flat baseline receives auxiliary coarse losses (e.g., parcel and network MSE from atlas pooling) or explicitly re-frame the claim to state that the advantage comes from the combination of hierarchy and multi-scale supervision, and discuss the confound clearly in the main text.
The paper says, at §Appendix B.2 and §4.3
The review did not quote this passage.
A classifier read this sentence of the paper as acknowledging the concern (probability 0.92):
“These changes in time representation, head capacity, and code allocation mean the 52×–415× comparison measures two complete trained systems rather than the isolated effect of temporal token count.”
Pith says: Objection 2 of 3 · major
The 52× and 415× models differ not only in temporal token count but also in decoder capacity, code dimensions, the presence of a direct middle-residual loss, and the temporal pooling architecture. As the authors acknowledge in Appendix B, these are “two complete trained systems rather than the isolated effect of temporal token count.”
more of objection 2
The paper should therefore avoid language that implies a pure rate ablation (e.g., “enabling up to 415× compression”) without reiterating this caveat more prominently in the abstract and introduction, so that readers do not overinterpret the 415× results relative to the 52× results.
The paper says, at §Appendix C.5, Table 4
The review did not quote this passage.
Pith says: Objection 3 of 3 · major
The loss-component ablation shows that removing the temporal-difference terms (L_Δ) increases reconstruction MSE by 20% and nearly triples the atlas latent MSE. This suggests that L_Δ shapes the latent structure significantly. However, the flat baselines also include L_Δ (voxel and chunk temporal-difference losses).
more of objection 3
This is consistent with the first major comment: the coarse-scale supervision matters. The authors should clarify in the main text that HBAR’s coarse-scale advantage over flat baselines is not solely due to the hierarchical grouping; the auxiliary losses likely contribute.
7 minor objections
The paper says, at §Abstract and §1
Pith says: minor objection 1 of 7
Line “preserving fine-grained spatial information beyond conventional parcellation”: This could be misinterpreted as claiming that HBAR reconstructs signals at a finer granularity than the atlas itself. The paper later makes clear that sub-parcel voxel groups are within fixed parcels, so the representation is still bounded by the atlas. Please rephrase to avoid implying that HBAR discovers new sub-parcel structure beyond the atlas boundaries.
The paper says, at §3.3, “Voxel-level”
Pith says: minor objection 2 of 7
The description of “voxel groups of size K=16”: Are these groups formed by deterministic ordering of voxel indices within each parcel? The paper states “voxel coordinates are normalized and ordered deterministically” — please specify the sorting scheme explicitly (e.g., lexicographic order along x, y, z) and note that groups are not spatially contiguous in the 3D volume.
show 5 more
The paper says, at §Table 1 and §5.1
Pith says: minor objection 3 of 7
The presentation of Table 1 would benefit from grouping the 415× methods separately from the 52× methods more clearly, and from adding a note that the MS-VQVAE baseline is a two-level latent model without atlas priors. The current footnote about “Bold and underlining” is helpful but could be complemented by a small gap between the rate blocks.
The paper says, at §Appendix D, compression accounting
Pith says: minor objection 4 of 7
The paper notes that compression ratios assume ideal fixed-length bit packing without entropy coding. This is a standard assumption, but it should also appear in the main text (e.g., in Section 4 or Section 5) so that readers who skip appendices are aware that real-world storage costs may differ.
The paper says, at §Appendix E, reconstruction metrics
Pith says: minor objection 5 of 7
The evaluation uses Pearson correlation over flattened time×units. This metric can be sensitive to global scaling, though the oracle check shows near-perfect scale agreement. The paper could mention that this metric is used only for comparison and may not reflect signal-to-noise ratio or temporal fidelity equally across methods.
The paper says, at §Appendix G, spectral analysis
Pith says: minor objection 6 of 7
Table 7 shows that at 415× all models have error-to-input power ratios near 1 for frequencies above 0.10 Hz, indicating essentially no recovery of fast temporal dynamics. The authors note this limitation in the appendix text. Given how central the “415× compression with preserved multiscale signals” claim is, the spectral limitation should be mentioned briefly in the main paper’s results section (Section 5.1).
The paper says, at §6, Limitations
Pith says: minor objection 7 of 7
The limitation paragraph does not discuss the confound of asymmetric training objectives. Adding a sentence acknowledging that the comparison with flat tokenizers conflates hierarchical aggregation with multi-scale supervision would improve the paper’s fairness.
What would settle it
Train flat BSQ-415 with additional auxiliary losses on parcel-level and network-level MSE (same L_P and L_N as HBAR-415, using the DiFuMo-1024 and Yeo-17 targets) without changing the flat architecture. Compare parcel and network correlations on the test set. If the augmented flat baseline matches or exceeds HBAR-415, then the advantage stems from the multi-scale losses rather than from hierarchical tokenization. If HBAR-415 remains superior, the hierarchy itself contributes beyond the supervision.
from the skeptic's reading
How the review went
4 readings by deepseek-v4-flash · 10 Nov 2026
- Reader holds up
- Skeptic partly agrees: says it holds up only with conditions The coarse-scale evaluation metric (parcel/network correlation) is aligned with HBAR's training objectives but absent from flat baseline losses, so the reported advantage may reflect multi-scale supervision rather than hierarchical tokenization itself.
- Editor wrote the verdict above
- Referee major revision: 3 major objections, 7 minor
Not run on this paper: the simulated authors' defence.
Pith did not check this review's objections against the paper.
The review in full
The review in brief, machine-written
Thanks for pointing me to this one. The paper is a well-engineered study of hierarchical tokenization for fMRI, and the authors are admirably transparent about their limitations. The main claim is that fixed atlas-based hierarchical tokenization outperforms flat baselines at coarse scales under high compression, but the stress-test note hits the central experimental confound: HBAR is trained with parcel- and network-level reconstruction losses that the flat baselines simply do not receive. So the better parcel/network correlations at 415x may just reflect multi-scale supervision rather than the hierarchical architecture itself. The paper acknowledges the loss difference in Appendix C.3 but offers no control for it at the high compression rate where the biggest gains appear.
That said, this is a thorough piece of work. The systematic comparison of fixed, learned, and soft hierarchies is genuinely useful. The code is released. The experiments use three seeds, bootstrap confidence intervals, and paired tests. The authors explicitly document where comparisons are not pure rate ablations (52x vs 415x, Appendix B) and are honest about cohort and atlas limitations. The 52x shuffled grouping ablation partially addresses the loss confound by keeping the same loss structure, but the gap there is smaller (0.920 vs 0.886), and the key 415x results lack that control entirely.
The confound is load-bearing. Until a flat baseline is trained with the same coarse-scale losses (parcel and network MSE from atlas pooling), we cannot attribute HBAR's advantage at 415x to the hierarchical tokenization itself. The atlas used for grouping also sets the evaluation metrics, which is a mild circularity the paper acknowledges.
This paper is for neuroimagers working on representation learning, compression, or foundation models. It is not a breakthrough but a competent, useful study that deserves peer review – but a good reviewer will push hard on the confound. I would like to see the question addressed before citing it.
Yes, send it to review. The authors are serious thinkers and the work is reproducible; the main issue is fixable.
The strongest objection
The central claim that HBAR achieves higher parcel and network correlations than rate-matched flat tokenizers at 415× compression conflates hierarchical architecture with multi-scale supervision. HBAR is trained with explicit reconstruction losses at parcel and network levels (L_P, L_N in Eq. 2), while flat baselines have no such coarse-scale objectives. Consequently, when evaluated on the same atlas-based pooling used in training, HBAR is effectively tested on what it was directly optimized for, whereas flat tokenizers are evaluated on metrics they were never trained to improve. The paper acknowledges this loss difference (Appendix C.3) but does not control for it. The shuffled grouping ablation at 52× partially addresses this issue by keeping the same loss structure, showing a smaller parcel correlation drop from 0.920 to 0.886, but no equivalent control exists at 415× where the largest gains are reported. Without a flat baseline that also receives auxiliary coarse-scale losses (e.g., parcel and network MSE from atlas pooling), we cannot attribute HBAR's coarse-scale advantage to the hierarchical tokenization rather than to the presence of multi-scale supervision. The reader's weakest assumption (atlas validity) is related but distinct; the core experimental confound is the asymmetry in training objectives, not merely the correctness of the atlas.
The reader identified atlas validity as the weakest assumption, but the more immediate threat to the central claim is the failure to control for the multi-scale training objective. The paper transparently acknowledges the loss difference but does not treat it as a confound. The shuffled grouping ablation at 52× is a useful control for grouping specificity, yet it does not isolate the hierarchy from the loss; the flat baselines are missing the losses entirely. A simple control experiment (concrete test) would clarify the source of HBAR's advantage. If the augmented flat baseline performs similarly, the paper's conclusion would shift to 'multi-scale losses help, and hierarchy may provide additional modest benefit.' The paper otherwise is thorough and well-executed, so the manuscript should be accepted conditionally on this control being performed or on a clear qualification of the claim.
The referee's report
If the result holds, the paper provides a principled framework for constructing compact, multi-scale representations of high-dimensional neuroimaging data that respect known functional organization. The work is methodologically solid: it includes three-seed experiments, bootstrap confidence intervals, paired tests, and extensive ablation studies. The authors are transparent about several limitations (e.g., the 52× vs 415× comparison is not a pure rate ablation, compression ratios assume ideal bit packing, age prediction is limited by the narrow HCP-YA range). The code is released. The framework is flexible (fixed, learned, soft alignment) and could generalize to other structured scientific signals.
Pith's reading of the paper (a machine's summary, not the authors')
HBAR is a hierarchical tokenization framework for fMRI that compresses voxel-level brain activity up to 415 times while preserving multiscale structure. It organizes voxels into sub-parcel groups, parcels (DiFuMo-1024), and functional networks (Yeo-17), then learns discrete tokens at each level. At high compression, HBAR reconstructs parcel and network signals more accurately than rate-matched flat tokenizers. Using fixed anatomical atlases as priors improves reconstruction fidelity over fully learned hierarchies. The framework demonstrates that domain-specific organization can enhance representation learning in neuroimaging.
What carries the argument. Hierarchical tokenization via three-level aggregation (voxel chunks → DiFuMo-1024 parcels → Yeo-17 networks) with binary spherical quantization (BSQ) applied independently at each level. The hierarchy can be fixed (atlas-based), fully learned (cross-attention pooling), or softly aligned. BSQ discretizes features into binary codes, enabling high compression without codebook collapse.
Core claim. HBAR demonstrates that hierarchical tokenization guided by neuroanatomical priors can compress resting-state fMRI to 415× of its original size while preserving multiscale brain signals better than flat tokenizers. At 415× compression, HBAR achieves parcel correlation of 0.746 and network correlation of 0.895, compared to 0.691 and 0.803 for flat RVQ. At 52×, preserving the anatomical chunk-to-parcel grouping raises parcel correlation from 0.886 (shuffled) to 0.920. These results show that explicit hierarchical organization through functional atlases provides a strong inductive bias for compact representation learning in high-dimensional neural data.
The premise it rests on. The advantage of hierarchical tokenization depends on the atlas-based hierarchy (DiFuMo-1024 and Yeo-17) providing a meaningful and correct organization of brain function—if these atlases do not capture true functional structure, the benefit over flat tokenizers may diminish.
If the paper is right (Pith's inferences, not the authors')
At 415× compression, HBAR enables storage and analysis of large-scale fMRI datasets that were previously impractical due to data volume.
The hierarchical tokens can be used as inputs for autoregressive models, potentially capturing temporal dynamics of brain activity at multiple scales.
The framework's design principle—embedding domain-specific atlases into tokenization—can be applied to other structured scientific signals like genomics or spatial transcriptomics.
The finding that fixed anatomical priors outperform learned hierarchies suggests that reconstruction objectives alone are insufficient to recover canonical brain organization, guiding future model design.
HBAR's advantage at coarse scales implies that downstream tasks sensitive to network-level connectivity (e.g., brain network analysis) may benefit more from hierarchical tokens than voxel-level tasks.
The modest age prediction results, partly due to narrow age range, suggest that the framework should be evaluated on lifespan datasets where age-related changes are more pronounced.
The 52× vs 415× comparison is confounded by architectural differences (not just compression rate), so a cleaner ablation varying only temporal tokens would clarify the effect of compression.
Check this review
Pith stored no record of this review's passes and took no fingerprint of it. Reviews made by code from 13 Nov 2026 on carry both.
How often reviews like this one are right
Reviews like this one: written by deepseek-v4-flash, where what was read was not recorded.
How often objections from reviews like this one are right: not yet measured
Reviews by people
This review was written by a machine. No person has reviewed this paper on Pith yet. A scientist listed on Pith can review it for a fee, and their review is published here whatever it concludes.
The paper
Abstract
We introduce HBAR (Hierarchical Brain Activity Representation), a hierarchical tokenization framework for learning compact, multi-scale representations of neuroimaging data. HBAR organizes voxel-level resting-state fMRI into a hierarchy spanning sub-parcel voxel groups, parcels, and large-scale functional networks, enabling up to 415x compression while preserving fine-grained spatial information beyond conventional parcellation. The framework supports fixed atlas-based, fully learned, and softly prior-guided hierarchies, allowing us to systematically study the role of structured priors in brain representation learning. On HCP-YA, at approximately 415x compression, HBAR achieves higher parcel and network correlations than rate-matched flat tokenizers, while at a lower 52x compression rate, shuffling the anatomical grouping reduces parcel correlation from 0.920 to 0.886. Demographic readouts with autoregressive training also reveal potential gains from the hierarchical structure. By combining sub-parcel inputs, compact discrete tokens, and multiscale brain structure, HBAR offers a practical framework for representation learning in high-dimensional neuroimaging data.
The paper's own sentences, arranged, kept beside the review and separate from it. Each label is drawn from a closed vocabulary; the number beside it is the probability the classifier gave that label. No sentence in this record was written by a model.
abstract compiled · 2026-11-10
The authors' main claim, as the classifier picked it out 0.80
“By combining sub-parcel inputs, compact discrete tokens, and multiscale brain structure, HBAR offers a practical framework for representation learning in high-dimensional neuroimaging data.”
How the main claim is stated: asserted 0.94
What the abstract itself states, as probabilities: claims first 0.06 · states limitation 0.14 · human participants 0.90 · controlled comparison 0.83 · randomized assignment 0.02 · states quantitative result 0.99 · compares with prior results 0.92 · mentions code or data availability 0.03
The abstract, sentence by sentence
This table labels the abstract only (arXiv listing abstract v1). The number is the probability the classifier gave the label.
| Sentence | Role | The authors' own work | States the main conclusion | Strength |
|---|---|---|---|---|
| We introduce HBAR (Hierarchical Brain Activity Representation), a hierarchical tokenization framework for learning compact, multi-scale representations of neuroimaging data. | contribution 0.99 | 0.90 | 0.12 | asserted 0.99 |
| HBAR organizes voxel-level resting-state fMRI into a hierarchy spanning sub-parcel voxel groups, parcels, and large-scale functional networks, enabling up to 415x compression while preserving fine-grained spatial information beyond conventional parcellation. | method 0.83 | 0.88 | 0.24 | asserted 0.99 |
| The framework supports fixed atlas-based, fully learned, and softly prior-guided hierarchies, allowing us to systematically study the role of structured priors in brain representation learning. | method 0.86 | 0.70 | 0.06 | asserted 0.99 |
| On HCP-YA, at approximately 415x compression, HBAR achieves higher parcel and network correlations than rate-matched flat tokenizers, while at a lower 52x compression rate, shuffling the anatomical grouping reduces parcel correlation from 0.920 to 0.886. | result 1.00 | 0.96 | 0.34 | asserted 1.00 |
| Demographic readouts with autoregressive training also reveal potential gains from the hierarchical structure. | result 0.91 | 0.87 | 0.08 | hedged possibility 0.98 |
| By combining sub-parcel inputs, compact discrete tokens, and multiscale brain structure, HBAR offers a practical framework for representation learning in high-dimensional neuroimaging data. | interpretation 0.63 | 0.46 | 0.58 | asserted 0.94 |
What kind of paper the classifier reports this is: method or tool 1.00 · evidence from analysis of existing data 0.69
What was examined, and what was not
Sources read
- arXiv listing abstract v1
Not examined
- full text
- figures and tables
- references and citing sentences
- relations to other papers
Levels run
- P abstract
Not run
- S sections
- T body sentences
- C citations
- R cross-paper relations
How the labels were made
Compiled by classifier-1.13.0 via TypeSafe API, question bank abstract-p1-20260923, 2026-11-10: 1 request, 5,124 input tokens.
Every quoted sentence on this record is the authors'. Every label is from Pith's closed vocabulary, with the probability shown beside it. This record as JSON
Figures (2)
Figures are the authors', reproduced from the paper.
References (43)
- [1] Mohammad Hassan Abbasi and Ehsan Adeli. fMRI Processing Pipeline: A lightweight, end-to- end framework for BIDS-compatible fMRI preprocessing and quality control, 2025 on Pith
- [2] Mohammad Adiban, Kalin Stefanov, Sabato Marco Siniscalchi, and Giampiero Salvi. Hi- erarchical Residual Learning Based Vector Quantized Variational Autoencoder for Image Reconstruction and Generation. 8 2022 on Pith
- [3] Zechen Bai, Jianxiong Gao, Ziteng Gao, Pichao Wang, Zheng Zhang, Tong He, and Mike Zheng Shou. Factorized Visual Tokenization and Generation. 11 2024 on Pith
- [4] Thomas Blumensath, Saad Jbabdi, Matthew F. Glasser, David C. Van Essen, Kamil Ugurbil, Timothy E.J. Behrens, and Stephen M. Smith. Spatially constrained hierarchical parcellation of the brain with resting-state fMRI.NeuroImage, 76:313–324, 8 2013. ISSN 10538119. doi: 10.1016/j... on Pithdoi:10.1016/j.neuroimage.2013.03.024
- [5] Zalán Borsos, Raphaël Marinier, Damien Vincent, Eugene Kharitonov, Olivier Pietquin, Matt Sharifi, Dominik Roblek, Olivier Teboul, David Grangier, Marco Tagliasacchi, and Neil Zeghi- dour. AudioLM: a Language Modeling Approach to Audio Generation. 7 2023 on Pith
- [6] Josue Ortega Caro, Antonio H. de O. Fonseca, Christopher Averill, Syed A. Rizvi, Matteo Rosati, James L. Cross, Prateek Mittal, Emanuele Zappala, Daniel Levine, Rahul M. Dhodapkar, Insu Han, Amin Karbasi, Chadi G. Abdallah, and David van Dijk. BrainLM: A foundation model for b... on Pith
- [8] Zijian Dong, Ruilin Li, Yilei Wu, Thuan Tinh Nguyen, Joanna Su Xian Chong, Fang Ji, Nathanael Ren Jie Tong, Christopher Li Hsian Chen, and Juan Helen Zhou. Brain-JEPA: Brain Dynamics Foundation Model with Gradient Positioning and Spatiotemporal Masking. 9 2024 on Pith
- [9] Patrick Esser, Robin Rombach, and Björn Ommer. Taming Transformers for High-Resolution Image Synthesis. 6 2021 on Pith
- [10] Oscar Esteban, Christopher J. Markiewicz, Ross W. Blair, Craig A. Moodie, A. Ilkay Isik, Asier Erramuzpe, James D. Kent, Mathias Goncalves, Elizabeth DuPre, Madeleine Snyder, Hiroyuki Oya, Satrajit S. Ghosh, Jessey Wright, Joke Durnez, Russell A. Poldrack, and Krzysztof J. Gor... on Pithdoi:10.1038/s41592-018-0235-4
- [11] Rahul Garg, Guillermo A. Cecchi, and A. Ravishankar Rao. Full-brain auto-regressive modeling (FARM) using fMRI.NeuroImage, 58(2):416–441, 9 2011. ISSN 10538119. doi: 10.1016/j. neuroimage.2011.02.074 on Pithdoi:10.1016/j
- [12] Eloy Geenjaar, Tonya White, and Vince Calhoun. Variational voxelwise rs-fMRI representation learning: Evaluation of sex, age, and neuropsychiatric signatures. 8 2021 on Pith
- [13] Tong He, Ru Kong, Avram J. Holmes, Minh Nguyen, Mert R. Sabuncu, Simon B. Eick- hoff, Danilo Bzdok, Jiashi Feng, and B.T. Thomas Yeo. Deep neural networks and ker- nel regression achieve comparable accuracies for functional connectivity prediction of be- havior and demographic... on Pithdoi:10.1016/j.neuroimage.2019.116276
- [14] Andrew Jaegle, Felix Gimeno, Andrew Brock, Andrew Zisserman, Oriol Vinyals, and Joao Carreira. Perceiver: General Perception with Iterative Attention. 6 2021 on Pith
- [15] Diederik P Kingma and Max Welling. Auto-Encoding Variational Bayes. 12 2022 on Pith
- [16] Thomas N. Kipf and Max Welling. Semi-Supervised Classification with Graph Convolutional Networks. 2 2017 on Pith
- [17] H. W. Kuhn. The Hungarian method for the assignment problem.Naval Research Logistics Quarterly, 2(1-2):83–97, 3 1955. ISSN 0028-1441. doi: 10.1002/nav.3800020109 on Pithdoi:10.1002/nav.3800020109
- [18] Y . Lecun, L. Bottou, Y . Bengio, and P. Haffner. Gradient-based learning applied to document recognition.Proceedings of the IEEE, 86(11):2278–2324, 1998. ISSN 00189219. doi: 10.1109/ 5.726791 on Pith
- [19] Doyup Lee, Chiheon Kim, Saehoon Kim, Minsu Cho, and Wook-Shin Han. Autoregressive Image Generation using Residual Quantization. 3 2022 on Pith
- [20] Fabian Mentzer, David Minnen, Eirikur Agustsson, and Michael Tschannen. Finite Scalar Quantization: VQ-V AE Made Simple. 10 2023 on Pith
- [21] Yuto Nishimura, Masataka Sawayama, Ayumu Yamashita, Hideki Nakayama, and Kaoru Amano. BrainCodec: Neural fMRI codec for the decoding of cognitive brain states. 10 2024 on Pith
show 23 more
- [22] Aaron van den Oord, Oriol Vinyals, and Koray Kavukcuoglu. Neural Discrete Representation Learning. 5 2018 on Pith
- [23] François Paugam, Basile Pinsard, Guillaume Lajoie, and Pierre Bellec. A benchmark of individual auto-regressive models in a massive fMRI dataset.Imaging Neuroscience, 2, 7 2024. ISSN 2837-6056. doi: 10.1162/imag{\_}a{\_}00228 on Pithdoi:10.1162/imag
- [24] Aditya Ramesh, Mikhail Pavlov, Gabriel Goh, Scott Gray, Chelsea V oss, Alec Radford, Mark Chen, and Ilya Sutskever. Zero-Shot Text-to-Image Generation. In Marina Meila and Tong Zhang, editors,Proceedings of the 38th International Conference on Machine Learning, volume 139 ofPr... on Pith
- [25] Ali Razavi, Aaron van den Oord, and Oriol Vinyals. Generating Diverse High-Fidelity Images with VQ-V AE-2. 6 2019 on Pith
- [26] Fengyuan Shi, Zhuoyan Luo, Yixiao Ge, Yujiu Yang, Ying Shan, and Limin Wang. Scalable Image Tokenization with Index Backpropagation Quantization. 3 2025 on Pith
- [27] Yifei Sun, Daniel Chahine, Qinghao Wen, Tianming Liu, Xiang Li, Yixuan Yuan, Fernando Calamante, and Jinglei Lv. V oxel-Level Brain States Prediction Using Swin Transformer. 6 2025 on Pith
- [28] B. T. Thomas Yeo, Fenna M. Krienen, Jorge Sepulcre, Mert R. Sabuncu, Danial Lashkari, Marisa Hollinshead, Joshua L. Roffman, Jordan W. Smoller, Lilla Zöllei, Jonathan R. Polimeni, Bruce Fischl, Hesheng Liu, and Randy L. Buckner. The organization of the human cerebral cortex es... on Pithdoi:10.1152/jn.00338.2011
- [29] Keyu Tian, Yi Jiang, Zehuan Yuan, Bingyue Peng, and Liwei Wang. Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction. 6 2024 on Pith
- [30] David C. Van Essen, Stephen M. Smith, Deanna M. Barch, Timothy E.J. Behrens, Essa Yacoub, and Kamil Ugurbil. The WU-Minn Human Connectome Project: An overview.NeuroImage, 80:62–79, 10 2013. ISSN 10538119. doi: 10.1016/j.neuroimage.2013.05.041 on Pithdoi:10.1016/j.neuroimage.2013.05.041
- [31] Cheng Wang, Yu Jiang, Zhihao Peng, Chenxin Li, Changbae Bang, Lin Zhao, Wanyi Fu, Jinglei Lv, Jorge Sepulcre, Carl Yang, Lifang He, Tianming Liu, Xue-Jun Kong, Quanzheng Li, Daniel S. Barron, Anqi Qiu, Randy Hirschtick, Byung-Hoon Kim, Hongbin Han, Xiang Li, and Yixuan Yuan. T... on Pith
- [32] Mo Wang, Junfeng Xia, Wenhao Ye, Enyu Liu, Kaining Peng, Jianfeng Feng, Quanying Liu, and Hongkai Wen. SLIM-Brain: A Data- and Training-Efficient Foundation Model for fMRI Data Analysis. 1 2026 on Pith
- [33] Susanne Weis, Kaustubh R Patil, Felix Hoffstaedter, Alessandra Nostro, B T Thomas Yeo, and Simon B Eickhoff. Sex Classification by Resting State Brain Connectivity.Cerebral Cortex, 30 (2):824–835, 3 2020. ISSN 1047-3211. doi: 10.1093/cercor/bhz129 on Pithdoi:10.1093/cercor/bhz129
- [34] Rundong Xue, Hao Hu, Zeyu Zhang, Xiangmin Han, Juan Wang, Yue Gao, and Shaoyi Du. DHGFormer: Dynamic Hierarchical Graph Transformer for Disorder Brain Disease Diagnosis. pages 268–278. 2026. doi: 10.1007/978-3-032-05162-2{\_}26 on Pithdoi:10.1007/978-3-032-05162-2
- [35] Yanwu Yang and Thomas Wolfers. Hierarchical Characterization of Brain Dynamics via State Space-based Vector Quantization. 6 2025 on Pith
- [36] Yanwu Yang, Chenfei Ye, Guinan Su, Ziyao Zhang, Zhikai Chang, Hairui Chen, Piu Chan, Yue Yu, and Ting Ma. BrainMass: Advancing Brain Network Analysis for Diagnosis With Large- Scale Self-Supervised Learning.IEEE Transactions on Medical Imaging, 43(11):4004–4016, 11 2024. ISSN ... on Pithdoi:10.1109/tmi.2024.3414476
- [37] Xuanhua Yin, Runkai Zhao, Lina Yao, and Weidong Cai. BrainVista: Modeling Naturalistic Brain Dynamics as Multimodal Next-Token Prediction. 2 2026 on Pith
- [38] Rex Ying, Jiaxuan You, Christopher Morris, Xiang Ren, William L. Hamilton, and Jure Leskovec. Hierarchical Graph Representation Learning with Differentiable Pooling. 2 2019 on Pith
- [39] Lijun Yu, José Lezama, Nitesh B. Gundavarapu, Luca Versari, Kihyuk Sohn, David Minnen, Yong Cheng, Vighnesh Birodkar, Agrim Gupta, Xiuye Gu, Alexander G. Hauptmann, Boqing Gong, Ming-Hsuan Yang, Irfan Essa, David A. Ross, and Lu Jiang. Language Model Beats Diffusion – Tokenize... on Pith
- [40] Qihang Yu, Mark Weber, Xueqing Deng, Xiaohui Shen, Daniel Cremers, and Liang-Chieh Chen. An Image is Worth 32 Tokens for Reconstruction and Generation. 6 2024 on Pith
- [41] Yue Zhao, Yuanjun Xiong, and Philipp Krähenbühl. Image and Video Tokenization with Binary Spherical Quantization. 6 2024 on Pith
- [42] Yue Zhao, Hanwen Jiang, Zhenlin Xu, Chutong Yang, Ehsan Adeli, and Philipp Krähenbühl. Spherical Leech Quantization for Visual Tokenization and Generation. 12 2025 on Pith
- [43] Lei Zhu, Fangyun Wei, Yanye Lu, and Dong Chen. Scaling the Codebook Size of VQGAN to 100,000 with a Utilization Rate of 99%. 6 2024 on Pith
- [44] Qi Zhu, Shengrong Li, Xiangshui Meng, Qiang Xu, Zhiqiang Zhang, Wei Shao, and Daoqiang Zhang. Spatio-Temporal Graph Hubness Propagation Model for Dynamic Brain Network Classification.IEEE Transactions on Medical Imaging, 43(6):2381–2394, 6 2024. ISSN 0278-0062. doi: 10.1109/TM... on Pithdoi:10.1109/tmi.2024.3363014
Challenges and discussion
Disagree with the review, or know something it missed? Leave a comment, or challenge this review formally: a challenge becomes a permanent entry in this paper's record, and its decision is published here.
Come back by email
A short list of the week's newly reviewed papers. Nothing is sent until you confirm from your inbox, and every email has a link that stops it. No account.
No comments yet.
Sign in to comment