pith. sign in

arxiv: 2605.08146 · v2 · pith:J5BMPQQUnew · submitted 2026-05-03 · 💻 cs.CV · cs.AI

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

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

Pith reviewed 2026-05-21 00:27 UTC · model grok-4.3

classification 💻 cs.CV cs.AI
keywords visual-tabular learningmulti-modal benchmarkdiscriminative predictiongenerative reasoningvision-language modelsmodel evaluationmulti-modal datasets
0
0 comments X

The pith

VT-Bench collects 14 visual-tabular datasets across nine domains to create the first standard test for models that combine images with tables.

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

The paper establishes a shared collection of visual and tabular datasets so that researchers can measure progress on tasks requiring both image understanding and table-based reasoning. These tasks matter in areas such as healthcare where scans must be interpreted alongside patient records, yet no prior common yardstick existed for comparing approaches. The work gathers the datasets, defines both prediction and reasoning versions of the tasks, and runs a broad set of current models on them. The results show that existing techniques still encounter clear difficulties when the two data types must be used together. A reader would care because a reliable benchmark makes it easier to develop and compare the multi-modal systems needed for real decisions in medicine and industry.

Core claim

VT-Bench is the first unified benchmark for standardizing vision-tabular discriminative prediction and generative reasoning tasks. It aggregates 14 datasets across 9 domains with over 756K samples and evaluates 23 representative models, including unimodal experts, specialized visual-tabular models, general-purpose vision-language models, and tool-augmented methods, to highlight substantial challenges of visual-tabular learning.

What carries the argument

VT-Bench, the aggregated collection of 14 datasets and defined tasks that standardizes testing of models required to process both visual inputs and tabular records at once.

If this is right

  • Researchers gain a single, reproducible way to compare unimodal, specialized, and vision-language models on the same visual-tabular problems.
  • The evaluation results identify concrete performance gaps that new model designs must close.
  • Development of foundation models able to handle combined vision and tabular data receives a clear target for improvement.
  • High-stakes applications in healthcare and industry obtain a pathway toward more reliable multi-modal systems.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • Similar aggregation efforts could be applied to other modality pairs such as audio with tables to test whether the same integration problems appear.
  • Adding datasets from additional domains over time would let the benchmark track whether progress generalizes beyond the initial nine areas.
  • The identified challenges suggest value in testing whether new fusion layers or reasoning modules improve results across the full set of tasks.

Load-bearing premise

The chosen datasets and domains supply a representative sample of visual-tabular difficulties without selection effects or domain artifacts shaping the measured challenges.

What would settle it

A new model achieving high scores on VT-Bench yet showing poor results on fresh visual-tabular cases drawn from a medical or industrial setting outside the nine included domains would show that the benchmark does not capture the full range of real 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 6
Figure 6. Figure 6: 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 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: Distribution of question types in the generative reasoning benchmarks, grouped by the modality of evidence required for answering: image-only, table-only, text-only (available only in MMQA), and their combinations. The left panel presents the distribution for each individual subset, while the right panel summarizes the overall distribution across all reasoning data. E.2. Discriminative Prediction Datasets … 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: 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. Adoption. The PetFinder adoption prediction dataset contains 14,652 pet profiles with structured metadata. For feature construction, we conv… 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 ↗
Figure 11
Figure 11. Figure 11: The multi-modal reasoning prompt for MMQA. This template strictly enforces zero-shot constraints and concise output across text, tabular, and visual modalities. table that contains 𝑛 candidate vehicles (𝑛 ∈ 10, 20, 50) described by 15 fixed attributes. Importantly, exactly one row in 𝑇 uniquely corresponds to the vehicle shown in 𝐼, which we refer to as the target row. The question 𝑞 is written in natural… view at source ↗
Figure 12
Figure 12. Figure 12: 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 13
Figure 13. Figure 13: 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. models with comparable predictive accuracy. TabTransformer TabTransformer(Huang et al., 2020b) adopts a Transformer-based architecture to contextualize categorical feature embeddings through self-attention, producing more informati… 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

3 major / 2 minor

Summary. The manuscript introduces VT-Bench as the first unified benchmark for visual-tabular multi-modal learning. It aggregates 14 datasets across 9 domains (described as medical-centric while covering pets, media, and transportation) totaling over 756K samples, defines discriminative prediction and generative reasoning tasks, and evaluates 23 models spanning unimodal experts, specialized visual-tabular models, VLMs, and tool-augmented approaches to demonstrate substantial challenges.

Significance. A well-curated, standardized benchmark in this underexplored area could provide a valuable testbed for future work on multi-modal models in high-stakes domains. The public release of the benchmark and associated code is a concrete strength that supports reproducibility and community follow-up.

major comments (3)
  1. [§3] §3 (Benchmark Construction): The manuscript states the collection is 'medical-centric' but provides no quantitative breakdown of sample counts or task difficulty per domain, nor explicit inclusion/exclusion criteria or cross-domain calibration. This directly bears on the central claim that the benchmark 'highlights substantial challenges' in a generalizable way rather than domain-specific artifacts.
  2. [§4] §4 (Evaluation Protocol): Task standardization, preprocessing pipelines, and handling of missing tabular values or image resolutions are not described with sufficient detail to verify fairness across the 23 models. Without these, performance gaps cannot be confidently attributed to intrinsic visual-tabular difficulties.
  3. [§5] §5 (Results): Reported model performances lack error bars, statistical significance tests, or ablation on domain subsets. This weakens the claim that the benchmark reveals 'substantial challenges' that are representative rather than driven by the majority medical samples.
minor comments (2)
  1. [Abstract] The abstract could more precisely state the number of discriminative vs. generative tasks and the primary quantitative findings from the 23-model evaluation.
  2. [Figure 1] Figure 1 or the benchmark overview table should include per-domain sample counts and modality statistics for immediate clarity.

Simulated Author's Rebuttal

3 responses · 0 unresolved

We thank the referee for their thoughtful and constructive review. We have addressed each major comment by adding quantitative details, expanding methodological descriptions, and incorporating statistical analyses to strengthen the transparency and generalizability of VT-Bench.

read point-by-point responses

  1. Referee: [§3] §3 (Benchmark Construction): The manuscript states the collection is 'medical-centric' but provides no quantitative breakdown of sample counts or task difficulty per domain, nor explicit inclusion/exclusion criteria or cross-domain calibration. This directly bears on the central claim that the benchmark 'highlights substantial challenges' in a generalizable way rather than domain-specific artifacts.

    Authors: We agree that a quantitative breakdown strengthens the claims. In the revised manuscript, we have added Table 2 in §3 detailing sample counts, task types, and difficulty proxies (e.g., class imbalance ratios) for each domain. Inclusion criteria are now explicitly stated: datasets were chosen for paired image-tabular availability, public accessibility, and coverage of high-stakes applications, with exclusion of purely synthetic or single-modality sets. Cross-domain calibration is achieved via unified task templates (e.g., standardized input formatting for prediction and reasoning), while preserving domain-specific features to reflect real-world variability. This supports that challenges are not artifacts of medical dominance alone. revision: yes

  2. Referee: [§4] §4 (Evaluation Protocol): Task standardization, preprocessing pipelines, and handling of missing tabular values or image resolutions are not described with sufficient detail to verify fairness across the 23 models. Without these, performance gaps cannot be confidently attributed to intrinsic visual-tabular difficulties.

    Authors: We appreciate this point on reproducibility. Section 4 has been expanded with a dedicated subsection on preprocessing: all images are resized to 224×224 with consistent augmentations; missing tabular values are handled via median imputation for numerical features and mode for categorical, with explicit masking flags; task standardization includes fixed prompt templates for generative tasks and label encoding for discriminative ones. These details ensure consistent evaluation across unimodal, VLM, and tool-augmented models. revision: yes

  3. Referee: [§5] §5 (Results): Reported model performances lack error bars, statistical significance tests, or ablation on domain subsets. This weakens the claim that the benchmark reveals 'substantial challenges' that are representative rather than driven by the majority medical samples.

    Authors: We acknowledge the need for statistical rigor. The revised §5 now includes error bars (standard deviation over 5 random seeds) for all reported metrics, paired t-tests for significance between top models, and a new ablation table comparing performance on medical vs. non-medical domain subsets. Results confirm that substantial challenges (e.g., low generative accuracy) persist in both subsets, supporting generalizability beyond medical data dominance. revision: yes

Circularity Check

0 steps flagged

No circularity: empirical benchmark with no derivations or self-referential predictions

full rationale

VT-Bench is a curation and evaluation paper that aggregates 14 existing datasets across domains and runs 23 models on them to report performance. No equations, fitted parameters, or first-principles derivations appear in the abstract or described content. The central claim (that the benchmark highlights substantial challenges) is an empirical observation from the released testbed rather than a closed-loop result that reduces to its own inputs by construction. Dataset selection and domain coverage are open to criticism on representativeness, but that is a question of external validity, not circularity in any derivation chain.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

This is an empirical benchmark paper. No free parameters are fitted, no mathematical axioms are invoked, and no new entities are postulated. The work relies on existing public datasets and off-the-shelf models.

pith-pipeline@v0.9.0 · 5709 in / 1169 out tokens · 46407 ms · 2026-05-21T00:27:00.885075+00:00 · methodology

Review history (2 revisions) →

discussion (0)

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

Lean theorems connected to this paper

Citations machine-checked in the Pith Canon. Every link opens the source theorem in the public Lean library.

What do these tags mean?
matches
The paper's claim is directly supported by a theorem in the formal canon.
supports
The theorem supports part of the paper's argument, but the paper may add assumptions or extra steps.
extends
The paper goes beyond the formal theorem; the theorem is a base layer rather than the whole result.
uses
The paper appears to rely on the theorem as machinery.
contradicts
The paper's claim conflicts with a theorem or certificate in the canon.
unclear
Pith found a possible connection, but the passage is too broad, indirect, or ambiguous to say the theorem truly supports the claim.

Reference graph

Works this paper leans on

67 extracted references · 67 canonical work pages · 8 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

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

    work page internal anchor Pith review Pith/arXiv 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]

    Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) , year =

    Zheng, Mingyu and Feng, Xinwei and Si, Qingyi and She, Qiaoqiao and Lin, Zheng and Jiang, Wenbin and Wang, Weiping , title =. Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) , year =

    work page

  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]

    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 =. Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers) , year =

    work page

  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]

    Kim, Yoonsik and Yim, Moonbin and Song, Ka Yeon , journal=

    work page

  49. [50]

    Singh, Anshul and Biemann, Chris and Strich, Jan , journal=

    work page

  50. [51]

    Findings of the Association for Computational Linguistics: EMNLP 2024 , year =

    Mathur, Suyash Vardhan and Bafna, Jainit Sushil and Kartik, Kunal and Khandelwal, Harshita and Shrivastava, Manish and Gupta, Vivek and Bansal, Mohit and Roth, Dan , title =. Findings of the Association for Computational Linguistics: EMNLP 2024 , year =

    work page 2024

  51. [52]

    Radfusion: Benchmarking performance and fairness for multimodal pulmonary embolism detection from

    Zhou, Yuyin and Huang, Shih-Cheng and Fries, Jason Alan and Youssef, Alaa and Amrhein, Timothy J and Chang, Marcello and Banerjee, Imon and Rubin, Daniel and Xing, Lei and Shah, Nigam and others , journal=. Radfusion: Benchmarking performance and fairness for multimodal pulmonary embolism detection from

    work page

  52. [53]

    Bycroft, Clare and Freeman, Colin and Petkova, Desislava and Band, Gavin and Elliott, Lloyd T and Sharp, Kevin and Motyer, Allan and Vukcevic, Damjan and Delaneau, Olivier and O’Connell, Jared and others , journal=. The. 2018 , publisher=

    work page 2018

  53. [54]

    Qwen3-VL Technical Report

    S. Bai and Y. Cai and R. Chen and K. Chen and others , title =. arXiv preprint arXiv:2511.21631 , year =

    work page internal anchor Pith review Pith/arXiv arXiv

  54. [55]

    Abhimanyu Dubey and Akhil Jauhri and Abhinav Pandey and Abhishek Kadian and Alon Altermatt and others , year =. The. 2407.21783 , archiveprefix =

    work page internal anchor Pith review Pith/arXiv arXiv

  55. [56]

    Pixtral 12B

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

    work page internal anchor Pith review Pith/arXiv arXiv

  56. [57]

    2025 , note =

    OpenAI , title =. 2025 , note =

    work page 2025

  57. [58]

    2025 , howpublished =

    work page 2025

  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

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

    work page internal anchor Pith review Pith/arXiv arXiv

  61. [62]

    International Conference on Machine Learning , pages=

    Compositional Condition Question Answering in Tabular Understanding , author=. International Conference on Machine Learning , pages=

    work page

  62. [63]

    Advances in Neural Information Processing Systems , pages=

    Multimodal tabular reasoning with privileged structured information , author=. Advances in Neural Information Processing Systems , pages=

    work page

  63. [64]

    Ji, An-Yang and Jiang, Jun-Peng and Zhan, De-Chuan and Ye, Han-Jia , journal=

    work page

  64. [65]

    Ma, Haoxuan and Lai, Guannan and Ye, Han-Jia , journal=

    work page

  65. [66]

    Exploring

    Xia, Shi-Yu and Zhu, Wenxuan and Yang, Xu and Geng, Xin , booktitle =. Exploring

    work page

  66. [67]

    ArXiv , year=

    Learngene: Inheriting Condensed Knowledge from the Ancestry Model to Descendant Models , author=. ArXiv , year=

    work page

  67. [68]

    arXiv preprint arXiv:2603.21928 , year=

    The Golden Subspace: Where Efficiency Meets Generalization in Continual Test-Time Adaptation , author=. arXiv preprint arXiv:2603.21928 , year=

    work page arXiv