pith. machine review for the scientific record. sign in

arxiv: 2605.08146 · v1 · submitted 2026-05-03 · 💻 cs.CV · cs.AI

Recognition: no theorem link

VT-Bench: A Unified Benchmark for Visual-Tabular Multi-Modal Learning

Kun-Yang Yu, Lan-Zhe Guo, Xin-Yue Zhang, Yu-Feng Li, Zhi Zhou, Zi-Jian Cheng, Zi-Yi Jia

Authors on Pith no claims yet

Pith reviewed 2026-05-12 01:27 UTC · model grok-4.3

classification 💻 cs.CV cs.AI
keywords visual-tabular learningmulti-modal benchmarkvision-language modelsdiscriminative predictiongenerative reasoningtabular datamulti-modal evaluation
0
0 comments X

The pith

VT-Bench is the first unified benchmark to standardize evaluation of models that combine images with tabular data.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper sets out to fill a gap in multi-modal AI by creating consistent tests for systems that process both visual inputs and structured tables. This combination of data types matters in fields such as healthcare and industry where decisions often rely on scans paired with patient records or sensor readings. The authors collect 14 datasets spanning nine domains and more than 756,000 samples to cover both prediction and reasoning tasks. They then run the same tasks across 23 models of different types to document where current methods fall short. A working benchmark would give researchers a shared way to measure and close those gaps.

Core claim

VT-Bench aggregates 14 datasets across 9 domains with over 756K samples to create the first standardized benchmark for vision-tabular discriminative prediction and generative reasoning. Evaluation across 23 models, from unimodal experts to specialized visual-tabular models, general vision-language models, and tool-augmented methods, shows substantial remaining challenges in learning from this data combination.

What carries the argument

VT-Bench, the benchmark that defines protocols and aggregates datasets for consistent testing of visual-tabular tasks.

Load-bearing premise

The 14 chosen datasets and the 23-model evaluation setup capture the main real-world difficulties of visual-tabular learning without major gaps or bias.

What would settle it

A new model that scores high on every VT-Bench task but shows no gains over baselines when tested on independent visual-tabular problems collected from the same domains would show the benchmark missed key difficulties.

Figures

Figures reproduced from arXiv: 2605.08146 by Kun-Yang Yu, Lan-Zhe Guo, Xin-Yue Zhang, Yu-Feng Li, Zhi Zhou, Zi-Jian Cheng, Zi-Yi Jia.

Figure 1
Figure 1. Figure 1: Two paradigms in vision–tabular multi-modal learning and the cross-modal grounding challenge in generative reasoning. As shown in [PITH_FULL_IMAGE:figures/full_fig_p001_1.png] view at source ↗
Figure 2
Figure 2. Figure 2: The comparison between VT-Bench and existing vision–tabular benchmarks. VT-Bench achieves stronger breadth by covering both discriminative prediction and generative reasoning paradigms while spanning diverse domains, and greater depth by evaluating key capabilities for vision–tabular learning. pairs, requiring structured retrieval followed by cross-modal medical reasoning. This design reflects real clinica… view at source ↗
Figure 3
Figure 3. Figure 3: Model-averaged accuracy on DVM-Car QA across Identification and four task types under varying sub-table sizes. prioritize learning discriminative and separable repre￾sentations to accommodate such heterogeneity, thereby ensuring more stable and robust fusion. Additional analyses of fusion architecture, training strat￾egy, and backbone selection for vision–tabular models are provided in the Section B. Findi… view at source ↗
Figure 4
Figure 4. Figure 4: Performance comparison between MMCL and its visual backbone (ResNet-50) across classification and regression tasks. The bar charts display the performance metrics (Accuracy for classification; RMSE for regression), while the red line plots the performance gain (Δ) of MMCL over the baseline. 0.45 0.50 0.55 0.60 0.65 0.70 Accuracy 1 2 3 4 5 6 7 8 9 10 11 12 13 14 Rank FT-Transformer LightGBM TabPFN v2 VIT-16… view at source ↗
Figure 6
Figure 6. Figure 6: Prompt template used for fine-tuning Qwen on the skin-cancer diagnostic task. The template instructs the model to predict the diagnostic category (BCC, SCC, MEL, NEV, ACK, or SEK) based on both tabular patient/lesion metadata and the corresponding dermatoscopic image. D.1.1. Public Datasets We introduce eight public datasets used in our benchmark. For all datasets, the reported sample sizes are computed af… view at source ↗
Figure 7
Figure 7. Figure 7: The two-stage prompt design for EHRXQA evaluation. Stage 1 acquires structured evidence via SQL under strict temporal constraints. Stage 2 integrates returned tabular evidence and CXR images for clinical reasoning. D.2.2. Multi-ModalQA. Multi-ModalQA (MMQA) (Talmor et al., 2021) is a multi-modal question answering benchmark that requires jointly using evidence from text, tables, and images. Unlike single-s… view at source ↗
Figure 8
Figure 8. Figure 8: The multi-modal reasoning prompt for MMQA. This template strictly enforces zero-shot constraints and concise output across text, tabular, and visual modalities. MMQA defines four unimodal sub-tasks: TextQ, TableQ, ImageQ, and ImageListQ, indicating that each question is answerable using evidence from the corresponding modality only. It further summarizes multi-step reasoning into three operations and accor… view at source ↗
Figure 9
Figure 9. Figure 9: Construction pipeline of DVM-Car QA. The pipeline includes three stages: (1) Data alignment & sampling, where each car image is matched to its table row and distractor rows are added so the target row is uniquely identifiable by a visual alignment key (e.g., Color=Red in the example); (2) Attribute selection & template instantiation, where attributes and target-relative constraints are sampled to generate … view at source ↗
Figure 10
Figure 10. Figure 10: The visual-tabular reasoning prompt for DVM-Car QA. This template evaluates the model’s ability to perform cross-modal grounding and attribute retrieval in a zero-shot setting. adaptive hyperparameter optimization based on the Optuna framework and following previous studies (Liu et al., 2024), fixing the batch size at 1024 and conducting 100 independent trials through train-validation splits to prevent te… view at source ↗
read the original abstract

Multi-model learning has attracted great attention in visual-text tasks. However, visual-tabular data, which plays a pivotal role in high-stakes domains like healthcare and industry, remains underexplored. In this paper, we introduce \textit{VT-Bench}, the first unified benchmark for standardizing vision-tabular discriminative prediction and generative reasoning tasks. VT-Bench aggregates 14 datasets across 9 domains (medical-centric, while covering pets, media, and transportation) with over 756K samples. We evaluate 23 representative models, including unimodal experts, specialized visual-tabular models, general-purpose vision-language models (VLMs), and tool-augmented methods, highlighting substantial challenges of visual-tabular learning. We believe VT-Bench will stimulate the community to build more powerful multi-modal vision-tabular foundation models. Benchmark: https://github.com/Ziyi-Jia990/VT-Bench

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

2 major / 3 minor

Summary. The paper introduces VT-Bench as the first unified benchmark for visual-tabular multi-modal learning. It aggregates 14 existing datasets across 9 domains (primarily medical, with coverage of pets, media, and transportation) totaling over 756K samples, defines discriminative prediction and generative reasoning tasks, and reports baseline results from evaluating 23 models spanning unimodal experts, specialized visual-tabular models, general-purpose VLMs, and tool-augmented methods.

Significance. If the benchmark construction and task definitions hold up under scrutiny, VT-Bench would provide a much-needed standardized evaluation framework for an underexplored but high-stakes area of multi-modal learning. By releasing the benchmark via GitHub and demonstrating substantial performance gaps across model categories, the work could accelerate development of vision-tabular foundation models, analogous to the role of established benchmarks in vision-language research.

major comments (2)
  1. [§3 and §4] §3 (Dataset Aggregation) and §4 (Task Definitions): the manuscript must explicitly document the selection criteria for the 14 datasets, including any exclusion rules, domain balance metrics, and preprocessing pipelines. Without these, it is impossible to assess whether the benchmark fairly captures core visual-tabular challenges or introduces selection bias toward medical data.
  2. [§5] §5 (Model Evaluation): the reported results for the 23 models lack statistical controls such as multiple random seeds, confidence intervals, or significance tests for the claimed 'substantial challenges.' This weakens the ability to draw reliable conclusions about relative model performance across discriminative and generative tasks.
minor comments (3)
  1. [Abstract] Abstract: the phrasing 'medical-centric, while covering pets, media, and transportation' should be accompanied by a breakdown of sample counts or dataset counts per domain to clarify coverage.
  2. [Introduction / Conclusion] The GitHub link is provided but the manuscript should include a brief description of the repository contents (e.g., data loaders, evaluation scripts, task splits) to facilitate immediate use by the community.
  3. [§4] Notation for task types (discriminative vs. generative) should be defined consistently in the main text and tables to avoid ambiguity when comparing model categories.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for the constructive feedback and positive recommendation for minor revision. We address each major comment point-by-point below, agreeing where the manuscript can be strengthened through added documentation and statistical controls. All changes will be incorporated in the revised version.

read point-by-point responses

  1. Referee: [§3 and §4] §3 (Dataset Aggregation) and §4 (Task Definitions): the manuscript must explicitly document the selection criteria for the 14 datasets, including any exclusion rules, domain balance metrics, and preprocessing pipelines. Without these, it is impossible to assess whether the benchmark fairly captures core visual-tabular challenges or introduces selection bias toward medical data.

    Authors: We agree that explicit documentation of benchmark construction is essential for transparency and to allow assessment of potential biases. Section 3 of the original manuscript provides an overview of the 14 datasets with Table 1 summarizing domains, sample counts, and sources, while §4 defines the tasks. However, we acknowledge the need for more detail on selection. In the revised manuscript, we will add a new subsection 'Dataset Selection and Preprocessing' in §3 that explicitly states: (1) Selection criteria included public availability of paired visual-tabular data, relevance to discriminative prediction or generative reasoning, minimum sample size (>1,000 for statistical reliability), and coverage of high-stakes domains; (2) Exclusion rules: datasets were excluded if they lacked one modality, contained only synthetic data, had restricted access, or were too small; (3) Domain balance: we will report metrics such as the proportion of samples per domain (medical: ~65%, pets: ~15%, media: ~10%, transportation: ~10%) and note that medical dominance reflects real-world prevalence of visual-tabular data (e.g., imaging + EHR) rather than arbitrary choice, while non-medical domains were deliberately included for diversity; (4) Preprocessing pipelines: uniform steps including image resizing to 224x224, tabular feature standardization, missing value imputation via mean/mode, and consistent train/validation/test splits (70/15/15). These additions will directly address concerns about fairness and selection bias without changing the benchmark composition. revision: yes

  2. Referee: [§5] §5 (Model Evaluation): the reported results for the 23 models lack statistical controls such as multiple random seeds, confidence intervals, or significance tests for the claimed 'substantial challenges.' This weakens the ability to draw reliable conclusions about relative model performance across discriminative and generative tasks.

    Authors: We appreciate the emphasis on statistical rigor for drawing reliable conclusions about model performance gaps. The original §5 reports single-run results across the 23 models to highlight clear trends (e.g., unimodal models struggling with cross-modal integration and VLMs showing limited tabular reasoning). To strengthen this, the revised manuscript will include: (1) averages and standard deviations over 3 random seeds for all models with stochastic components (e.g., fine-tuning or generation sampling); (2) 95% confidence intervals for primary metrics such as accuracy, F1-score (discriminative tasks), and BLEU/ROUGE (generative tasks); (3) paired statistical tests (e.g., t-tests) between model categories to quantify significance of the observed challenges. Due to substantial computational costs for re-evaluating all 23 models (particularly large VLMs and tool-augmented systems) across 14 datasets, we will apply full multi-seed analysis to representative subsets (baselines, top performers, and one from each category) and note this as a limitation for the remainder. These updates will better substantiate the claims of substantial challenges while remaining feasible for minor revision. revision: partial

Circularity Check

0 steps flagged

No significant circularity detected

full rationale

The paper constructs VT-Bench by aggregating 14 existing datasets into a unified benchmark and reporting baseline evaluations on 23 models for discriminative and generative tasks. No equations, derivations, fitted parameters, predictions, or load-bearing self-citations appear in the argument structure. The central claim is a constructive contribution (dataset aggregation and standardization) rather than a deductive result that reduces to its own inputs. Domain coverage and task definitions are explicitly stated without circular reduction.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

The paper aggregates existing datasets and evaluates off-the-shelf models without introducing new free parameters, axioms, or invented entities; the benchmark itself is the primary contribution.

pith-pipeline@v0.9.0 · 5478 in / 1029 out tokens · 51117 ms · 2026-05-12T01:27:29.175402+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

60 extracted references · 60 canonical work pages · 4 internal anchors

  1. [1]

    Multimodal Machine Learning: A Survey and Taxonomy , journal =

    Baltru. Multimodal Machine Learning: A Survey and Taxonomy , journal =. 2018 , volume =

    work page 2018

  2. [2]

    Proceedings of the 32nd International Conference on Machine Learning (ICML 2015) , address =

    Xu, Kelvin and Ba, Jimmy and Kiros, Ryan and Cho, Kyunghyun and Courville, Aaron and Salakhudinov, Ruslan and Zemel, Rich and Bengio, Yoshua , title =. Proceedings of the 32nd International Conference on Machine Learning (ICML 2015) , address =. 2015 , pages =

    work page 2015

  3. [3]

    Proceedings of the 15th IEEE International Conference on Computer Vision (ICCV 2015) , address =

    Antol, Stanislaw and Agrawal, Aishwarya and Lu, Jiasen and Mitchell, Margaret and Batra, Dhruv and Zitnick, C Lawrence and Parikh, Devi , title =. Proceedings of the 15th IEEE International Conference on Computer Vision (ICCV 2015) , address =. 2015 , pages =

    work page 2015

  4. [4]

    Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2015) , address =

    Vinyals, Oriol and Toshev, Alexander and Bengio, Samy and Erhan, Dumitru , title =. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2015) , address =. 2015 , pages =

    work page 2015

  5. [5]

    Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2024) , address =

    Yue, Xiang and Ni, Yuansheng and Zhang, Kai and Zheng, Tianyu and Liu, Ruoqi and Zhang, Ge and Stevens, Samuel and Jiang, Dongfu and Ren, Weiming and Sun, Yuxuan and others , title =. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2024) , address =. 2024 , pages =

    work page 2024

  6. [6]

    Proceedings of the 18th European Conference on Computer Vision (ECCV 2024) , address =

    Liu, Yuan and Duan, Haodong and Zhang, Yuanhan and Li, Bo and Zhang, Songyang and Zhao, Wangbo and Yuan, Yike and Wang, Jiaqi and He, Conghui and Liu, Ziwei and others , title =. Proceedings of the 18th European Conference on Computer Vision (ECCV 2024) , address =. 2024 , pages =

    work page 2024

  7. [7]

    Proceedings of the 38th International Conference on Machine Learning (ICML 2021) , address =

    Radford, Alec and Kim, Jong Wook and Hallacy, Chris and Ramesh, Aditya and Goh, Gabriel and Agarwal, Sandhini and Sastry, Girish and Askell, Amanda and Mishkin, Pamela and Clark, Jack and others , title =. Proceedings of the 38th International Conference on Machine Learning (ICML 2021) , address =. 2021 , pages =

    work page 2021

  8. [8]

    Proceedings of the 40th International Conference on Machine Learning (ICML 2023) , address =

    Li, Junnan and Li, Dongxu and Savarese, Silvio and Hoi, Steven , title =. Proceedings of the 40th International Conference on Machine Learning (ICML 2023) , address =. 2023 , pages =

    work page 2023

  9. [9]

    Advances in Neural Information Processing Systems , year =

    Liu, Haotian and Li, Chunyuan and Wu, Qingyang and Lee, Yong Jae , title =. Advances in Neural Information Processing Systems , year =

    work page

  10. [10]

    Proceedings of the 39th International Conference on Machine Learning (ICML 2022) , address =

    Li, Junnan and Li, Dongxu and Xiong, Caiming and Hoi, Steven , title =. Proceedings of the 39th International Conference on Machine Learning (ICML 2022) , address =. 2022 , pages =

    work page 2022

  11. [11]

    Advances in Neural Information Processing Systems , year =

    Lu, Jiasen and Batra, Dhruv and Parikh, Devi and Lee, Stefan , title =. Advances in Neural Information Processing Systems , year =

    work page

  12. [12]

    Multimodal Biomedical

    Acosta, Juli. Multimodal Biomedical. Nature Medicine , year =

    work page

  13. [13]

    Data Intelligence , year =

    Yang, Jiaxi and Chen, Kui and Ding, Kai and Na, Chongning and Wang, Meng , title =. Data Intelligence , year =

    work page

  14. [14]

    NPJ Digital Medicine , year =

    Huang, Shih-Cheng and Pareek, Anuj and Seyyedi, Saeed and Banerjee, Imon and Lungren, Matthew P , title =. NPJ Digital Medicine , year =

    work page

  15. [15]

    Proceedings of the 10th IEEE International Conference on Big Data (Big Data 2022) , address =

    Huang, Jingmin and Chen, Bowei and Luo, Lan and Yue, Shigang and Ounis, Iadh , title =. Proceedings of the 10th IEEE International Conference on Big Data (Big Data 2022) , address =. 2022 , pages =

    work page 2022

  16. [16]

    and Wilson, Keith T

    Cui, Can and Yang, Haichun and Wang, Yaohong and Zhao, Shilin and Asad, Zuhayr and Coburn, Lori A. and Wilson, Keith T. and Landman, Bennett A. and Huo, Yuankai , title =. Progress in Biomedical Engineering , year =

    work page

  17. [17]

    Medical Image Analysis , year =

    Duenias, Daniel and Nichyporuk, Brennan and Arbel, Tal and Raviv, Tammy Riklin and others , title =. Medical Image Analysis , year =

    work page

  18. [18]

    Proceedings of the 18th IEEE/CVF International Conference on Computer Vision (ICCV 2021) , address =

    Holste, Gregory and Partridge, Savannah C and Rahbar, Habib and Biswas, Debosmita and Lee, Christoph I and Alessio, Adam M , title =. Proceedings of the 18th IEEE/CVF International Conference on Computer Vision (ICCV 2021) , address =. 2021 , pages =

    work page 2021

  19. [19]

    Long-term Cancer Survival Prediction Using Multimodal Deep Learning , journal =

    Vale-Silva, Lu. Long-term Cancer Survival Prediction Using Multimodal Deep Learning , journal =. 2021 , volume =

    work page 2021

  20. [20]

    Proceedings of the 25th International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI 2022) , address =

    Zheng, Hanci and Lin, Zongying and Zhou, Qizheng and Peng, Xingchen and Xiao, Jianghong and Zu, Chen and Jiao, Zhengyang and Wang, Yan , title =. Proceedings of the 25th International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI 2022) , address =. 2022 , pages =

    work page 2022

  21. [21]

    Combining

    P. Combining. Proceedings of the 24th International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI 2021) , address =. 2021 , pages =

    work page 2021

  22. [22]

    2024 , booktitle =

    Jiang, Jun-Peng and Ye, Han-Jia and Wang, Leye and Yang, Yang and Jiang, Yuan and Zhan, De-Chuan , title =. 2024 , booktitle =

    work page 2024

  23. [23]

    Proceedings of the 36th IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2023) , address =

    Hager, Paul and Menten, Martin J and Rueckert, Daniel , title =. Proceedings of the 36th IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2023) , address =. 2023 , pages =

    work page 2023

  24. [24]

    Proceedings of the 18th European Conference on Computer Vision (ECCV 2024) , address =

    Du, Siyi and Zheng, Shaoming and Wang, Yinsong and Bai, Wenjia and O’Regan, Declan P and Qin, Chen , title =. Proceedings of the 18th European Conference on Computer Vision (ECCV 2024) , address =. 2024 , pages =

    work page 2024

  25. [25]

    Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing (EMNLP 2023) , address =

    Luo, Haohao and Shen, Ying and Deng, Yang , title =. Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing (EMNLP 2023) , address =. 2023 , pages =

    work page 2023

  26. [26]

    Advances in Neural Information Processing Systems , year =

    Bae, Seongsu and Kyung, Daeun and Ryu, Jaehee and Cho, Eunbyeol and Lee, Gyubok and Kweon, Sunjun and Oh, Jungwoo and Ji, Lei and Chang, Eric and Kim, Tackeun and others , title =. Advances in Neural Information Processing Systems , year =

    work page

  27. [27]

    Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL 2021) , address =

    Talmor, Alon and Yoran, Ori and Catav, Amnon and Lahav, Dan and Wang, Yizhong and Asai, Akari and Ilharco, Gabriel and Hajishirzi, Hannaneh and Berant, Jonathan , title =. Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL 2021) , address =. 2021 , pages =

    work page 2021

  28. [28]

    Proceedings of the 23rd International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI 2020) , address =

    Duanmu, Hongyi and Huang, Pauline Boning and Brahmavar, Srinidhi and Lin, Stephanie and Ren, Thomas and Kong, Jun and Wang, Fusheng and Duong, Tim Q , title =. Proceedings of the 23rd International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI 2020) , address =. 2020 , pages =

    work page 2020

  29. [29]

    Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2016) , address =

    He, Kaiming and Zhang, Xiangyu and Ren, Shaoqing and Sun, Jian , title =. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2016) , address =. 2016 , pages =

    work page 2016

  30. [30]

    2021 , booktitle =

    Dosovitskiy, Alexey and Beyer, Lucas and Kolesnikov, Alexander and Weissenborn, Dirk and Zhai, Xiaohua and Unterthiner, Thomas and Dehghani, Mostafa and Minderer, Matthias and Heigold, Georg and Gelly, Sylvain and Uszkoreit, Jakob and Houlsby, Neil , title =. 2021 , booktitle =

    work page 2021

  31. [31]

    Proceedings of the 34th International Conference on Machine Learning (ICML 2017) , address =

    Sundararajan, Mukund and Taly, Ankur and Yan, Qiqi , title =. Proceedings of the 34th International Conference on Machine Learning (ICML 2017) , address =. 2017 , pages =

    work page 2017

  32. [32]

    and Zhu, Yuke and others , title =

    Liang, Paul Pu and Lyu, Yiwei and Fan, Xiang and Wu, Zetian and Cheng, Yun and Wu, Jason and Chen, Leslie and Wu, Peter and Lee, Michelle A. and Zhu, Yuke and others , title =. Advances in Neural Information Processing Systems , year =

    work page

  33. [33]

    arXiv preprint arXiv:2412.16243 , year =

    Tang, Zhiqiang and Zhong, Zihan and He, Tong and Friedland, Gerald , title =. arXiv preprint arXiv:2412.16243 , year =

    work page arXiv

  34. [34]

    Johnson, Alistair E. W. and Bulgarelli, Lucas and Shen, Lu and Gayles, Alvin and Shammout, Ayad and Horng, Steven and Pollard, Tom J. and Hao, Sicheng and Moody, Benjamin and Gow, Brian and others , title =. Scientific Data , year =

    work page

  35. [35]

    Johnson, Alistair E. W. and Pollard, Tom J. and Berkowitz, Seth J. and Greenbaum, Nathaniel R. and Lungren, Matthew P. and Deng, Chih-ying and Mark, Roger G. and Horng, Steven , title =. Scientific Data , year =

    work page

  36. [36]

    NeuroImage , year =

    Spasov, Simeon and Passamonti, Luca and Duggento, Andrea and Lio, Pietro and Toschi, Nicola and others , title =. NeuroImage , year =

    work page

  37. [37]

    Advances in Neural Information Processing Systems , year =

    Ke, Guolin and Meng, Qi and Finley, Thomas and Wang, Taifeng and Chen, Wei and Ma, Weidong and Ye, Qiwei and Liu, Tie-Yan , title =. Advances in Neural Information Processing Systems , year =

    work page

  38. [38]

    TabTransformer: Tabular data modeling using contextual embeddings.arXiv preprint arXiv:2012.06678,

    Huang, Xin and Khetan, Ashish and Cvitkovic, Milan and Karnin, Zohar , title =. arXiv preprint arXiv:2012.06678 , year =

    work page arXiv 2012

  39. [39]

    Accurate Predictions on Small Data with a Tabular Foundation Model , journal =

    Hollmann, Noah and M. Accurate Predictions on Small Data with a Tabular Foundation Model , journal =. 2025 , volume =

    work page 2025

  40. [40]

    Qwen3 Technical Report

    Yang, An and Li, Anfeng and Yang, Baosong and Zhang, Beichen and Hui, Binyuan and Zheng, Bo and Yu, Bowen and Gao, Chang and others , title =. arXiv preprint arXiv:2505.09388 , year =

    work page internal anchor Pith review Pith/arXiv arXiv

  41. [41]

    arXiv preprint arXiv:2406.08100 , year =

    Zheng, Mingyu and Feng, Xinwei and Si, Qingyi and She, Qiaoqiao and Lin, Zheng and Jiang, Wenbin and Wang, Weiping , title =. arXiv preprint arXiv:2406.08100 , year =

    work page arXiv

  42. [42]

    The Carbon Footprint of Machine Learning Training Will Plateau, Then Shrink , journal =

    Patterson, David and Gonzalez, Joseph and H. The Carbon Footprint of Machine Learning Training Will Plateau, Then Shrink , journal =. 2022 , volume =

    work page 2022

  43. [43]

    GLM-4.5V and GLM-4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning

    Hong, Wenyi and Yu, Wenmeng and Gu, Xiaotao and Wang, Guo and Gan, Guobing and Tang, Haomiao and Cheng, Jiale and others , title =. arXiv preprint arXiv:2507.01006 , year =

    work page internal anchor Pith review Pith/arXiv arXiv

  44. [44]

    InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models

    Zhu, Jinguo and Wang, Weiyun and Chen, Zhe and Liu, Zhaoyang and Ye, Shenglong and Gu, Lixin and others , title =. arXiv preprint arXiv:2504.10479 , year =

    work page internal anchor Pith review Pith/arXiv arXiv

  45. [46]

    Informatics in Medicine Unlocked , year =

    Mienye, Ibomoiye Domor and Obaido, George and Jere, Nobert and Mienye, Ebikella and Aruleba, Kehinde and Emmanuel, Ikiomoye Douglas and Ogbuokiri, Blessing , title =. Informatics in Medicine Unlocked , year =

    work page

  46. [47]

    In Proceedings of the IEEE/CVF Confer- ence on Computer Vision and Pattern Recognition, pages 9556–9567

    Zhu, Fengbin and Lei, Wenqiang and Huang, Youcheng and Wang, Chao and Zhang, Shuo and Lv, Jiancheng and Feng, Fuli and Chua, Tat-Seng , title =. arXiv preprint arXiv:2105.07624 , year =

    work page arXiv

  47. [48]

    Proceedings of the 30th ACM International Conference on Multimedia (MM 2022) , address =

    Zhu, Fengbin and Lei, Wenqiang and Feng, Fuli and Wang, Chao and Zhang, Haozhou and Chua, Tat-Seng , title =. Proceedings of the 30th ACM International Conference on Multimedia (MM 2022) , address =. 2022 , pages =

    work page 2022

  48. [49]

    Tablevqa-bench: A visual question answering benchmark on multiple table domains, 2024

    Tablevqa-bench: A visual question answering benchmark on multiple table domains , author=. arXiv preprint arXiv:2404.19205 , year=

    work page arXiv

  49. [50]

    arXiv preprint arXiv:2506.11684 , year=

    MTabVQA: Evaluating Multi-Tabular Reasoning of Language Models in Visual Space , author=. arXiv preprint arXiv:2506.11684 , year=

    work page arXiv

  50. [51]

    arXiv preprint arXiv:2408.13860 , year=

    Knowledge-aware reasoning over multimodal semi-structured tables , author=. arXiv preprint arXiv:2408.13860 , year=

    work page arXiv

  51. [52]

    arXiv preprint arXiv:2111.11665 , year=

    Radfusion: Benchmarking performance and fairness for multimodal pulmonary embolism detection from ct and ehr , author=. arXiv preprint arXiv:2111.11665 , year=

    work page arXiv

  52. [53]

    Nature , volume=

    The UK Biobank resource with deep phenotyping and genomic data , author=. Nature , volume=. 2018 , publisher=

    work page 2018

  53. [54]

    Qwen3-VL Technical Report

    S. Bai and Y. Cai and R. Chen and K. Chen and others. Qwen3-VL Technical Report. arXiv preprint arXiv:2511.21631. 2025

    work page internal anchor Pith review Pith/arXiv arXiv 2025

  54. [55]

    2024 , eprint =

    The Llama 3 Herd of Models , author =. 2024 , eprint =

    work page 2024

  55. [56]

    Pixtral 12b.arXiv preprint arXiv:2410.07073,

    P. Agrawal and others , title =. arXiv preprint arXiv:2410.07073 , year =

    work page arXiv

  56. [57]

    2025 , note =

    OpenAI , title =. 2025 , note =

    work page 2025

  57. [58]

    Gemini 3 Flash: Model Card , year =

    work page

  58. [59]

    arXiv preprint arXiv:2505.21771 , year =

    Prasham Yatinkumar Titiya and Jainil Trivedi and Chitta Baral and Vivek Gupta , title =. arXiv preprint arXiv:2505.21771 , year =

    work page arXiv

  59. [60]

    Proceedings of the 2023 conference on empirical methods in natural language processing , pages=

    Jiang, Jinhao and Zhou, Kun and Dong, Zican and Ye, Keming and Zhao, Xin and Wen, Ji-Rong , title=. Proceedings of the 2023 conference on empirical methods in natural language processing , pages=

    work page 2023

  60. [61]

    Thyme: Think beyond images.arXiv preprint arXiv:2508.11630, 2025

    Thyme: Think beyond images , author=. arXiv preprint arXiv:2508.11630 , year=

    work page arXiv