Vision-Language Models

Probing, grounding, and extending vision-language models for spatial, temporal, and safety-aware reasoning.

(Pathak et al., 2025) (Kumar et al., 2025) (Grover et al., 2026) (Garg et al., 2025) (Schiappa et al., 2024) (Azad et al., 2025) (Grover et al., 2024) (Abdullah et al., 2025) (Aparcedo et al., 2026) (Wang et al., 2026) (Baranwal et al., 2025)

References

2026

CoSPlan: Corrective Sequential Planning via Scene Graph Incremental Updates

Shresth Grover, Priyank Pathak, Akash Kumar, and Yogesh S. Rawat

In European Conference on Computer Vision (ECCV), 2026

ECCV arXiv Bib Supp Code Website

@inproceedings{grover2026cosplan,
  title = {CoSPlan: Corrective Sequential Planning via Scene Graph Incremental Updates},
  author = {Grover, Shresth and Pathak, Priyank and Kumar, Akash and Rawat, Yogesh S.},
  booktitle = {European Conference on Computer Vision (ECCV)},
  year = {2026},
}

VISTA: A Benchmark for Spatio-Temporal Interaction Understanding in Videos

Alejandro Aparcedo, Akash Kumar, Aaryan Garg, Dalton Pham, Wen-Kai Chen, Anirudh Bharadwaj, Aman Chadha, and Yogesh Rawat

In IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2026

CVPRW Bib HTML Website

@inproceedings{aparcedo2026vista,
  title = {VISTA: A Benchmark for Spatio-Temporal Interaction Understanding in Videos},
  author = {Aparcedo, Alejandro and Kumar, Akash and Garg, Aaryan and Pham, Dalton and Chen, Wen-Kai and Bharadwaj, Anirudh and Chadha, Aman and Rawat, Yogesh},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)},
  pages = {8411--8422},
  year = {2026},
}

VLA-Thinker: Boosting Vision-Language-Action Models through Thinking-with-Image Reasoning

Chaoyang Wang, Wenrui Bao, Sicheng Gao, Bingxin Xu, Yu Tian, Yogesh S Rawat, Yunhao Ge, and Yuzhang Shang

arXiv preprint arXiv:2603.14523, 2026

arXiv Bib

@article{wang2026vla,
  title = {VLA-Thinker: Boosting Vision-Language-Action Models through Thinking-with-Image Reasoning},
  author = {Wang, Chaoyang and Bao, Wenrui and Gao, Sicheng and Xu, Bingxin and Tian, Yu and Rawat, Yogesh S and Ge, Yunhao and Shang, Yuzhang},
  journal = {arXiv preprint arXiv:2603.14523},
  year = {2026},
}

2025

LR0.FM: Low-Resolution Zero-Shot Classification Benchmark for Foundation Models

Priyank Pathak, Shyam Marjit, Shruti Vyas, and Yogesh S. Rawat

In International Conference on Learning Representations (ICLR), 2025

ICLR Bib HTML Code Poster Slides Website

@inproceedings{pathak2025lr0fm,
  title = {LR0.FM: Low-Resolution Zero-Shot Classification Benchmark for Foundation Models},
  author = {Pathak, Priyank and Marjit, Shyam and Vyas, Shruti and Rawat, Yogesh S.},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2025},
}

Contextual Self-paced Learning for Weakly Supervised Spatio-Temporal Video Grounding

Akash Kumar, Zsolt Kira, and Yogesh Singh Rawat

In International Conference on Learning Representations (ICLR), 2025

ICLR Bib HTML Supp Code Website

@inproceedings{kumar2025cospal,
  title = {Contextual Self-paced Learning for Weakly Supervised Spatio-Temporal Video Grounding},
  author = {Kumar, Akash and Kira, Zsolt and Rawat, Yogesh Singh},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2025},
}

STPro: Spatial and Temporal Progressive Learning for Weakly Supervised Spatio-Temporal Grounding

Aaryan Garg, Akash Kumar, and Yogesh Rawat

In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025

CVPR arXiv Bib PDF Supp Code Website

@inproceedings{garg2025stpro,
  title = {STPro: Spatial and Temporal Progressive Learning for Weakly Supervised Spatio-Temporal Grounding},
  author = {Garg, Aaryan and Kumar, Akash and Rawat, Yogesh},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
}

Understanding Depth and Height Perception in Large Visual-Language Models

Shehreen Azad, Yash Jain, Rishit Garg, Yogesh S Rawat, and Vibhav Vineet

In IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2025

CVPRW arXiv Bib Code Website

@inproceedings{azad2024geometer,
  title = {Understanding Depth and Height Perception in Large Visual-Language Models},
  author = {Azad, Shehreen and Jain, Yash and Garg, Rishit and Rawat, Yogesh S and Vineet, Vibhav},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)},
  year = {2025},
}

iSafetyBench: A video-language benchmark for safety in industrial environment

Raiyaan Abdullah, Yogesh Singh Rawat, and Shruti Vyas

In IEEE/CVF International Conference on Computer Vision Workshops (ICCVW), 2025

ICCVW arXiv Bib Code Website

@inproceedings{abdullah2025isafetybench,
  title = {iSafetyBench: A video-language benchmark for safety in industrial environment},
  author = {Abdullah, Raiyaan and Rawat, Yogesh Singh and Vyas, Shruti},
  booktitle = {IEEE/CVF International Conference on Computer Vision Workshops (ICCVW)},
  pages = {1433--1442},
  year = {2025},
}

Re: Verse-Can Your VLM Read a Manga?

Aaditya Baranwal, Madhav Kataria, Naitik Agrawal, Yogesh S Rawat, and Shruti Vyas

In IEEE/CVF International Conference on Computer Vision Workshops (ICCVW), 2025

ICCVW Awarded arXiv Bib Code Website

Best Paper Award, AI Story Workshop @ ICCV 2025

@inproceedings{baranwal2025re,
  title = {Re: Verse-Can Your VLM Read a Manga?},
  author = {Baranwal, Aaditya and Kataria, Madhav and Agrawal, Naitik and Rawat, Yogesh S and Vyas, Shruti},
  booktitle = {IEEE/CVF International Conference on Computer Vision Workshops (ICCVW)},
  pages = {3761--3771},
  year = {2025},
}

2024

Probing conceptual understanding of large visual-language models

Madeline Schiappa, Raiyaan Abdullah, Shehreen Azad, Jared Claypoole, Michael Cogswell, Ajay Divakaran, and Yogesh Rawat

In IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2024

CVPRW arXiv Bib

@inproceedings{schiappa2024probing,
  title = {Probing conceptual understanding of large visual-language models},
  author = {Schiappa, Madeline and Abdullah, Raiyaan and Azad, Shehreen and Claypoole, Jared and Cogswell, Michael and Divakaran, Ajay and Rawat, Yogesh},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)},
  pages = {1797--1807},
  year = {2024},
}

Navigating Hallucinations for Reasoning of Unintentional Activities

Shresth Grover, Vibhav Vineet, and Yogesh S. Rawat

In Findings of the Association for Computational Linguistics: EMNLP, 2024

EMNLP Findings arXiv Bib

@inproceedings{grover2024navigating,
  title = {Navigating Hallucinations for Reasoning of Unintentional Activities},
  author = {Grover, Shresth and Vineet, Vibhav and Rawat, Yogesh S.},
  booktitle = {Findings of the Association for Computational Linguistics: EMNLP},
  year = {2024},
}