Pith. sign in

REVIEW 5 cited by

Retrieval-Augmented Perception: High-Resolution Image Perception Meets Visual RAG

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2503.01222 v2 pith:WQM6LFRS submitted 2025-03-03 cs.CV cs.CL

Wenbin Wang , Yongcheng Jing , Liang Ding , Yingjie Wang , Li Shen , Yong Luo , Bo Du , Dacheng Tao This is my paper
classification cs.CVcs.CL
keywords perceptionimageretrieval-augmentedcropshigh-resolutionlong-contextmllmsproposed
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
abstract

High-resolution (HR) image perception remains a key challenge in multimodal large language models (MLLMs). To overcome the limitations of existing methods, this paper shifts away from prior dedicated heuristic approaches and revisits the most fundamental idea to HR perception by enhancing the long-context capability of MLLMs, driven by recent advances in long-context techniques like retrieval-augmented generation (RAG) for general LLMs. Towards this end, this paper presents the first study exploring the use of RAG to address HR perception challenges. Specifically, we propose Retrieval-Augmented Perception (RAP), a training-free framework that retrieves and fuses relevant image crops while preserving spatial context using the proposed Spatial-Awareness Layout. To accommodate different tasks, the proposed Retrieved-Exploration Search (RE-Search) dynamically selects the optimal number of crops based on model confidence and retrieval scores. Experimental results on HR benchmarks demonstrate the significant effectiveness of RAP, with LLaVA-v1.5-13B achieving a 43% improvement on $V^*$ Bench and 19% on HR-Bench.

Discussion (0). Sign in to comment.

Forward citations

Cited by 5 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. BVS: Bayesian Visual Search with Multimodal Large Language Model for Fine-grained Perception

    cs.CV 2026-07 conditional novelty 6.0 of 10

    BVS combines early-stop attention rollout priors with a scale-aware non-stationary kernel and GP-UCB to locate tiny objects in UHR images more accurately and with fewer MLLM queries than prior visual-search methods.

  2. BioMol-MQA: A Multi-Modal Question Answering Dataset For LLM Reasoning Over Bio-Molecular Interactions

    cs.CL 2025-06 conditional novelty 6.0 of 10

    BioMol-MQA is a new multimodal QA dataset for polypharmacy in which LLMs perform poorly zero-shot but much better when given gold context.

  3. AMIA: Automatic Masking and Joint Intention Analysis Makes LVLMs Robust Jailbreak Defenders

    cs.CV 2025-05 conditional novelty 6.0 of 10

    AMIA is an inference-only jailbreak defense that masks text-irrelevant image patches and prompts single-pass intention analysis, lifting average defense success on LVLMs from 52.4% to 81.7%.

  4. Toward Edge General Intelligence with Multiple-Large Language Model (Multi-LLM): Architecture, Trust, and Orchestration

    cs.NI 2025-07 conditional novelty 4.0 of 10

    A survey of multi-LLM systems in edge computing, covering architectures, enabling technologies, trust mechanisms, applications, and open datasets for edge general intelligence.

  5. Wireless Agentic AI with Retrieval-Augmented Multimodal Semantic Perception

    cs.NI 2025-05 conditional novelty 4.0 of 10

    A retrieval-augmented semantic communication framework with a DRL scheduler improves task completion efficiency and reduces bandwidth use in a simulated multi-agent autonomous driving setting.

Pith tools