Add ViGoRL work to visual methods papers - #17
Conversation
WalkthroughA new row was added to the Visual-based methods table in Changes
Estimated code review effort🎯 1 (Trivial) | ⏱️ ~2 minutes
Poem
Pre-merge checks and finishing touches✅ Passed checks (3 passed)
✨ Finishing touches🧪 Generate unit tests (beta)
Comment |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 2
🧹 Nitpick comments (1)
README.md (1)
39-39: Minor: Capitalize "GitHub" in link text.The static analysis tool and GitHub's official branding use "GitHub" with both capital G and H. Consider updating "[Github]" to "[GitHub]" for accuracy, though the codebase currently uses the "[Github]" convention consistently.
📜 Review details
Configuration used: CodeRabbit UI
Review profile: CHILL
Plan: Pro
⛔ Files ignored due to path filters (1)
imgs/vigorl_methods.pngis excluded by!**/*.png
📒 Files selected for processing (1)
README.md(1 hunks)
🧰 Additional context used
🪛 LanguageTool
README.md
[uncategorized] ~39-~39: The official name of this software platform is spelled with a capital “H”.
Context: ..."imgs/vigorl_methods.png"> | 2025-10 | [Github](https://github.com/Gabesarch/grounded-...
(GITHUB)
| ### Visual-based methods | ||
| | Title | Introduction | Date | Code | | ||
| | :----------------------------------------------------------- | :---------------------------------------------------------: | :--------: | :----------------------------------------------------------: | ||
| | <br/>[Grounded Reinforcement Learning for Visual Reasoning](https://arxiv.org/abs/2505.23678) | <img width="700" alt="image" src="imgs/vigorl_methods.png"> | 2025-10 | [Github](https://github.com/Gabesarch/grounded-rl) | |
There was a problem hiding this comment.
Chronological ordering issue: Entry should be placed after 2025-11 papers.
The new ViGoRL entry (2025-10) is positioned before entries dated 2025-11 (lines 40-42), violating the descending date order evident throughout the table. Move this entry to follow all 2025-11 papers.
🧰 Tools
🪛 LanguageTool
[uncategorized] ~39-~39: The official name of this software platform is spelled with a capital “H”.
Context: ..."imgs/vigorl_methods.png"> | 2025-10 | [Github](https://github.com/Gabesarch/grounded-...
(GITHUB)
🤖 Prompt for AI Agents
In README.md around line 39, the ViGoRL (2025-10) table row is placed before
several 2025-11 entries, breaking the descending chronological order; move the
entire ViGoRL row (the line shown) so it appears after all rows dated 2025-11 to
restore correct descending date ordering in the table.
Add NeurIPS 2025 conference badge.
Per the PR description, ViGoRL is to appear in NeurIPS 2025. Other NeurIPS 2025 papers in this table (e.g., lines 51, 56, 57, 66) include a conference badge. Add the badge before the title to maintain consistency:
-| <br/>[Grounded Reinforcement Learning for Visual Reasoning](https://arxiv.org/abs/2505.23678) | <img width="700" alt="image" src="imgs/vigorl_methods.png"> | 2025-10 | [Github](https://github.com/Gabesarch/grounded-rl) |
+| []()<br/>[Grounded Reinforcement Learning for Visual Reasoning](https://arxiv.org/abs/2505.23678) | <img width="700" alt="image" src="imgs/vigorl_methods.png"> | 2025-10 | [Github](https://github.com/Gabesarch/grounded-rl) |📝 Committable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
| | <br/>[Grounded Reinforcement Learning for Visual Reasoning](https://arxiv.org/abs/2505.23678) | <img width="700" alt="image" src="imgs/vigorl_methods.png"> | 2025-10 | [Github](https://github.com/Gabesarch/grounded-rl) | | |
| | []()<br/>[Grounded Reinforcement Learning for Visual Reasoning](https://arxiv.org/abs/2505.23678) | <img width="700" alt="image" src="imgs/vigorl_methods.png"> | 2025-10 | [Github](https://github.com/Gabesarch/grounded-rl) | |
🧰 Tools
🪛 LanguageTool
[uncategorized] ~39-~39: The official name of this software platform is spelled with a capital “H”.
Context: ..."imgs/vigorl_methods.png"> | 2025-10 | [Github](https://github.com/Gabesarch/grounded-...
(GITHUB)
🤖 Prompt for AI Agents
In README.md around line 39, the table row for "Grounded Reinforcement Learning
for Visual Reasoning" is missing the NeurIPS 2025 badge; update that table cell
by inserting the same NeurIPS 2025 badge markdown (the exact badge string used
in other rows — copy from lines 51/56/57/66) immediately before the paper title,
preserving the existing link and table formatting, and ensure alt text and
spacing match the other entries for consistency.
There was a problem hiding this comment.
Actionable comments posted: 0
🧹 Nitpick comments (1)
README.md (1)
54-54: Entry is correctly positioned chronologically and includes the required NeurIPS'25 badge.The ViGoRL entry (2025-07) is now placed in the correct descending date order after all 2025-11 and 2025-10 entries. The NeurIPS'25 conference badge is present, matching the pattern used for other NeurIPS 2025 papers in the table.
Minor: Address static analysis warnings for consistency across the file.
Two tools flagged minor issues on this line:
GitHub capitalization: The LanguageTool linter flagged
[Github]→ should be[GitHub](official name). This pattern appears throughout the file (lines 40–49, etc.), so consider applying this fix file-wide rather than in isolation.Empty badge link: The markdownlint flagged the empty URL in
()after the badge. This appears intentional for non-clickable visual badges and is consistent with other conference badges in the table (lines 50, 56–59, etc.), but you may want to audit if this is the desired pattern.
📜 Review details
Configuration used: CodeRabbit UI
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (1)
README.md(1 hunks)
🧰 Additional context used
🪛 LanguageTool
README.md
[uncategorized] ~54-~54: The official name of this software platform is spelled with a capital “H”.
Context: ..."imgs/vigorl_methods.png"> | 2025-07 | [Github](https://github.com/Gabesarch/grounded-...
(GITHUB)
🪛 markdownlint-cli2 (0.18.1)
README.md
54-54: No empty links
(MD042, no-empty-links)
1 participant
Hi! Thank you for the great review on spatial visual reasoning!
I'd like to suggest our recent work, ViGoRL (Visually Grounded Reinforcement Learning), for inclusion in your survey.
Our key contribution is demonstrating that RL of explicit visual spatial grounding in chain-of-thought reasoning significantly improves visual reasoning performance across multiple domains.
Paper: https://arxiv.org/abs/2505.23678
Project Page: https://visually-grounded-rl.github.io
Code: https://github.com/Gabesarch/grounded-rl
Models: https://huggingface.co/collections/gsarch/vigorl-6855655677fd6ff5864f65f2
Datasets: https://huggingface.co/datasets/gsarch/vigorl_datasets
To appear in NeurIPS 2025.
Thank you for considering our work and for being open to community contributions!
Summary by CodeRabbit
✏️ Tip: You can customize this high-level summary in your review settings.