Papers › Learning to Localize Objects Improves Spatial Reasoning in Visual-LLMs
Learning to Localize Objects Improves Spatial Reasoning in Visual-LLMs
Kanchana Ranasinghe, Satya Narayan Shukla, Omid Poursaeed, Michael S. Ryoo, Tsung-Yu Lin
Integration of Large Language Models (LLMs) into visual domain tasks, resulting in visual-LLMs (V-LLMs), has enabled exceptional performance in vision-language tasks, particularly for visual question answering (VQA). However, existing V-LLMs (e.g. BLIP-2, LLaVA) demonstrate weak spatial reasoning and localization awareness. Despite generating highly descriptive and elaborate textual answers, these models fail at simple tasks like distinguishing a left vs right location. In this work, we explore how image-space coordinate based instruction fine-tuning objectives could inject spatial awareness into V-LLMs. We discover optimal coordinate representations, data-efficient instruction fine-tuning objectives, and pseudo-data generation strategies that lead to improved spatial awareness in V-LLMs. Additionally, our resulting model improves VQA across image and video domains, reduces undesired hallucination, and generates better contextual object descriptions. Experiments across 5 vision-language tasks involving 14 different datasets establish the clear performance improvements achieved by our proposed framework.
In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
Code
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Video Question Answering | ActivityNet-QA | LocVLM-Vid-B+ | Accuracy | 38.2 | #27 of 36 | Archive leaderboard | report |
| Video Question Answering | ActivityNet-QA | LocVLM-Vid-B | Accuracy | 37.4 | #28 of 36 | Archive leaderboard | report |
| Video Question Answering | MSR-VTT | LocVLM-Vid-B | Accuracy | 51.2 | #1 of 1 | Archive leaderboard | report |
| Video Question Answering | MSVD-QA | LocVLM-Vid-B | Accuracy | 66.1 | #1 of 1 | Archive leaderboard | report |
| Video Question Answering | TGIF-QA | LocVLM-Vid-B | Accuracy | 51.8 | #1 of 1 | Archive leaderboard | report |
| Visual Question Answering | GQA | LocVLM-L | Accuracy | 50.2 | #1 of 1 | Archive leaderboard | report |
| Visual Question Answering | VQA v2 test-dev | LocVLM-L | Accuracy | 56.2 | #11 of 11 | Archive leaderboard | report |
| Visual Question Answering | VQA v2 val | LocVLM-L | Accuracy | 55.9 | #4 of 4 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections