PixSearch: Region-Grounded Retrieval for Knowledgeable Large Multimodal Models

arXiv:2601.19060 · cs.CV, cs.AI · Submitted 2026-01-27 · Read on arXiv

cs.CV, cs.AI

Submitted: 2026-01-27

Updated: 2026-10-13

Code: https://github.com/wjdghks950/PixSearch

Terminology

• Accuracy — 1× in this paper · explained in 1 episode
• Benchmark — 1× in this paper · explained in 2 episodes
• Consistency — 1× in this paper · explained in 3 episodes
• Fine-Tuning — 1× in this paper · explained in 5 episodes
• Generalization — 1× in this paper · explained in 13 episodes
• Grounding — 1× in this paper · explained in 3 episodes
• RAG — 1× in this paper · explained in 3 episodes
• Visual Question Answering — 1× in this paper

Sources

• The Llama 3 Herd of Models
• MM-PoisonRAG: Disrupting Multimodal RAG with Local and Global Poisoning Attacks
• Grounded SAM: Assembling Open-World Models for Diverse Visual Tasks
• DINOv3
• CRAG-MM: Multi-modal Multi-turn Comprehensive RAG Benchmark
• SegLLM: Multi-round Reasoning Segmentation

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models