adding visualoverload

[paulgavrikov]

This PR adds our VisualOverload dataset and benchmark for spatial understanding and reasoning in visually dense and high-resolution scenes.

Looking forward to feedback and happy to iterate!

Summary by CodeRabbit

• Documentation
  • Added VisualOverload: Probing Visual Understanding of VLMs in Really Dense Scenes to the Visual-based Methods and Datasets & Benchmarks tables, including links, images, publication date (2025-09), and repository information.

_{✏️ Tip: You can customize this high-level summary in your review settings.}

[coderabbitai]

Walkthrough

Added a new entry for "VisualOverload: Probing Visual Understanding of VLMs in Really Dense Scenes" to both the Visual-based Methods and Datasets & Benchmarks tables in the README with metadata including link, image, publication date (2025-09), and Github URL.

Changes

Cohort / File(s)	Change Summary
Documentation Updates README.md	Added VisualOverload entry to Visual-based Methods table with publication details and GitHub link; Added matching VisualOverload entry to Datasets & Benchmarks > Visual-based data table with identical metadata

Estimated code review effort

🎯 1 (Trivial) | ⏱️ ~2 minutes

• Straightforward documentation additions with consistent formatting

Possibly related PRs

• PR #13: Both PRs modify the README's Visual-based Methods and Visual-based Datasets & Benchmarks tables by adding new dataset/method entries to the same sections.
• PR #14: Both PRs add new entries to the Visual-based methods and Datasets & Benchmarks tables in README.md with similar metadata structure and formatting.

Poem

🐰 A repository grows with each entry we add,
New datasets and methods make scholars quite glad,
VisualOverload now shines bright in our table,
Dense scenes decoded—a benchmark most stable! ✨

Pre-merge checks and finishing touches

✅ Passed checks (3 passed)

Check name	Status	Explanation
Description Check	✅ Passed	Check skipped - CodeRabbit’s high-level summary is enabled.
Title check	✅ Passed	The title 'adding visualoverload' directly corresponds to the main change: adding the VisualOverload dataset entry to multiple tables in the README.
Docstring Coverage	✅ Passed	No functions found in the changed files to evaluate docstring coverage. Skipping docstring coverage check.

✨ Finishing touches

🧪 Generate unit tests (beta)

• Create PR with unit tests
• Post copyable unit tests in a comment

Tip

📝 Customizable high-level summaries are now available in beta!

You can now customize how CodeRabbit generates the high-level summary in your pull requests — including its content, structure, tone, and formatting.

• Provide your own instructions using the high_level_summary_instructions setting.
• Format the summary however you like (bullet lists, tables, multi-section layouts, contributor stats, etc.).
• Use high_level_summary_in_walkthrough to move the summary from the description to the walkthrough section.

Example instruction:

"Divide the high-level summary into five sections:

1. 📝 Description — Summarize the main change in 50–60 words, explaining what was done.
2. 📓 References — List relevant issues, discussions, documentation, or related PRs.
3. 📦 Dependencies & Requirements — Mention any new/updated dependencies, environment variable changes, or configuration updates.
4. 📊 Contributor Summary — Include a Markdown table showing contributions:
   | Contributor | Lines Added | Lines Removed | Files Changed |
5. ✔️ Additional Notes — Add any extra reviewer context.
   Keep each section concise (under 200 words) and use bullet or numbered lists for clarity."

Note: This feature is currently in beta for Pro-tier users, and pricing will be announced later.

---

_{Comment @coderabbitai help to get the list of available commands and usage tips.}

[coderabbitai]

Actionable comments posted: 0

🧹 Nitpick comments (1)

README.md (1)

111-111: Minor: Capitalize "Github" to "GitHub" for consistency with official branding.

Per the static analysis hint, the official name of the platform is "GitHub" (capital H). While the project currently uses lowercase "Github" throughout, updating this entry to the official spelling would align with best practices.

Apply this diff to correct the capitalization:

-| <br/>[VisualOverload: Probing Visual Understanding of VLMs in Really Dense Scenes](https://arxiv.org/abs/2509.25339) | <img width="700" alt="image" src="imgs/VisualOverload.png"> | 2025-09 | [Github](https://paulgavrikov.github.io/visualoverload/) |
+| <br/>[VisualOverload: Probing Visual Understanding of VLMs in Really Dense Scenes](https://arxiv.org/abs/2509.25339) | <img width="700" alt="image" src="imgs/VisualOverload.png"> | 2025-09 | [GitHub](https://paulgavrikov.github.io/visualoverload/) |

Alternatively, if the project intends to keep "Github" consistent across all entries, this comment can be disregarded.

📜 Review details

Configuration used: CodeRabbit UI

Review profile: CHILL

Plan: Pro

📥 Commits

Reviewing files that changed from the base of the PR and between 6bc1dee and 66c0488.

⛔ Files ignored due to path filters (1)

• imgs/VisualOverload.png is excluded by !**/*.png

📒 Files selected for processing (1)

• README.md (1 hunks)

🧰 Additional context used

🪛 LanguageTool

README.md

[uncategorized] ~111-~111: The official name of this software platform is spelled with a capital “H”.
Context: ..."imgs/VisualOverload.png"> | 2025-09 | [Github](https://paulgavrikov.github.io/visualo...

(GITHUB)

🔇 Additional comments (1)

README.md (1)

111-111: Verify the entry appears in both tables as described in the summary.

The AI summary indicates the VisualOverload entry was added to both the "Visual-based Methods" and "Datasets & Benchmarks" tables. However, only the change at line 111 (Datasets & Benchmarks section) is marked in the provided code. The Visual-based Methods section (lines 36–89) does not show a corresponding addition.

Please confirm whether VisualOverload should appear in both tables or only in Datasets & Benchmarks. If it should be in the Methods table as well, ensure that entry is also added and consistently formatted.