Research map / Large language models / Retrieval and knowledge
AVIS: Autonomous Visual Information Seeking with Large Language Model Agent
Ziniu Hu, Ahmet Iscen, Chen Sun, Kai-Wei Chang, Yizhou Sun, David A Ross, Cordelia Schmid, Alireza Fathi
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add PALI* (VQA/captioning) tool group (ablation) | AVIS · Infoseek (Wikidata) unseen entity | VQA accuracy: 47.9 -> 50.7 | Improved |
| add Object detection tool group (ablation) | AVIS · Infoseek (Wikidata) unseen entity | VQA accuracy: 41.2 -> 50.7 | Improved |
| add Search tool group (ablation) | AVIS · Infoseek (Wikidata) unseen entity | VQA accuracy: 42.5 -> 50.7 | Improved |
| add PALI* tool group (ablation) | AVIS · Infoseek (Wikidata) unseen question | VQA accuracy: 54.2 -> 56.4 | Improved |
| add Object detection tool group (ablation) | AVIS · Infoseek (Wikidata) unseen question | VQA accuracy: 48.4 -> 56.4 | Improved |
| add Search tool group (ablation) | AVIS · Infoseek (Wikidata) unseen question | VQA accuracy: 49.6 -> 56.4 | Improved |
| add PALI* tool group (ablation) | AVIS · OK-VQA | VQA accuracy: 47.1 -> 60.2 | Improved |
| add Object detection tool group (ablation) | AVIS · OK-VQA | VQA accuracy: 58.3 -> 60.2 | Improved |
| add Search tool group (ablation) | AVIS · OK-VQA | VQA accuracy: 55.0 -> 60.2 | Improved |
| add transition graph and user-study prompts to planner (ablation) | AVIS · Infoseek (Wikidata) unseen entity | VQA accuracy: 38.2 -> 50.7 | Improved |
| add transition graph and user-study prompts to planner (ablation) | AVIS · OK-VQA | VQA accuracy: 47.3 -> 60.2 | Improved |
| dynamic decision making instead of sequentially executing all tools | PALM + tools · Infoseek (Wikidata) unseen entity | VQA accuracy: 36.1 -> 50.7 | Improved |
Closest papers by meaning
- VQ-VA World: Towards High-Quality Visual Question-Visual Answering (CVPR 2026 · similarity 0.90)
- Separation of Powers: On Segregating Knowledge from Observation in LLM-enabled Knowledge-based Visual Question Answering (CVPR 2025 · similarity 0.89)
- Knowledge-based Visual Question Answer with Multimodal Processing, Retrieval and Filtering (NeurIPS 2025 · similarity 0.89)
- Retrieval-Augmented Visual Question Answering via Built-in Autoregressive Search Engines (AAAI 2025 · similarity 0.89)
- Automated Generation of Challenging Multiple-Choice Questions for Vision Language Model Evaluation (CVPR 2025 · similarity 0.88)
- ConVQG: Contrastive Visual Question Generation with Multimodal Guidance (AAAI 2024 · similarity 0.88)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
