Vineeth N. Balasubramanian
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Vineeth N. Balasubramanian has a total of 4 co-authors. Here are the top co-authors by number of shared publications:
- Leonid Sigal
University of British Columbia
2 shared publications Shivam Chandhok
University of British Columbia
2 shared publications- Vered Shwartz
University of British Columbia, Vancouver, Canada
2 shared publications - Wan-Cyuan Fan
University of British Columbia
2 shared publications
Latest Publications
- Open Access
Response Wide Shut? Surprising Observations in Basic Vision Language Model Capabilities
Vision-language Models (VLMs) have emerged as general-purpose tools for addressing a variety of complex computer vision problems. Such models have been shown to be highly capable, but, at the same time, lacking some basic visual understanding skills. In this paper, we set out to understand the limitations of SoTA VLMs on fundamental visual tasks by constructing a series of tests that probe which components of design, specifically, may be lacking. Importantly, we go significantly beyond the current benchmarks, which simply measure the final performance of VLM response, by also comparing and contrasting it to the performance of probes trained directly on features obtained from the visual encoder, intermediate vision-language projection and LLM-decoder output. In doing so, we uncover shortcomings in VLMs and make a number of important observations about their capabilities, robustness and how they process visual information. We hope our insights will guide progress in further improving VLMs.
Open AccessResponse Wide Shut? Surprising Observations in Basic Vision Language Model Capabilities
Vision-language Models (VLMs) have emerged as general-purpose tools for addressing a variety of complex computer vision problems. Such models have been shown to be highly capable, but, at the same time, lacking some basic visual understanding skills. In this paper, we set out to understand the limitations of SoTA VLMs on fundamental visual tasks by constructing a series of tests that probe which components of design, specifically, may be lacking. Importantly, we go significantly beyond the current benchmarks, which simply measure the final performance of VLM response, by also comparing and contrasting it to the performance of probes trained directly on features obtained from the visual encoder, intermediate vision-language projection and LLM-decoder output. In doing so, we uncover shortcomings in VLMs and make a number of important observations about their capabilities, robustness and how they process visual information. We hope our insights will guide progress in further improving VLMs.
- Open Access
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 25530-25545
Response Wide Shut? Surprising Observations in Basic Vision Language Model Capabilities
Shivam Chandhok, Wan-Cyuan Fan, Vered Shwartz, Vineeth N. Balasubramanian, Leonid Sigal. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2025.
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 25530-25545
Open AccessResponse Wide Shut? Surprising Observations in Basic Vision Language Model Capabilities
Shivam Chandhok, Wan-Cyuan Fan, Vered Shwartz, Vineeth N. Balasubramanian, Leonid Sigal. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2025.