# SnapBench: Benchmarking Snap-and-Ask Multimodal Retrieval for Mobile Interactions

arXiv: https://arxiv.org/abs/2608.29607 · HTML: https://mlsanity.com/paper/2608.29607/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 51 references that are in the map.
- First posted on arXiv 30 Aug 2026.

## Builds on (most cited first, 30 of 30)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Sigmoid Loss for Language Image Pre-Training](https://mlsanity.com/paper/2303.15343/) (2023)
- [Benchmarking Neural Network Robustness to Common Corruptions and Perturbations](https://mlsanity.com/paper/1903.12261/) (2019)
- [Microsoft COCO Captions: Data Collection and Evaluation Server](https://mlsanity.com/paper/1504.00325/) (2015)
- [Flickr30k Entities: Collecting Region-to-Phrase Correspondences for Richer Image-to-Sentence Models](https://mlsanity.com/paper/1505.04870/) (2015)
- [SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features](https://mlsanity.com/paper/2502.14786/) (2025)
- [VizWiz Grand Challenge: Answering Visual Questions from Blind People](https://mlsanity.com/paper/1802.08218/) (2018)
- [Google Landmarks Dataset v2 -- A Large-Scale Benchmark for Instance-Level Recognition and Retrieval](https://mlsanity.com/paper/2004.01804/) (2020)
- [Image Retrieval on Real-life Images with Pre-trained Vision-and-Language Models](https://mlsanity.com/paper/2108.04024/) (2021)
- [Qwen3-VL-Embedding and Qwen3-VL-Reranker: A Unified Framework for State-of-the-Art Multimodal Retrieval and Ranking](https://mlsanity.com/paper/2601.04720/) (2026)
- [Can Pre-trained Vision and Language Models Answer Visual Information-Seeking Questions?](https://mlsanity.com/paper/2302.11713/) (2023)
- [Zero-Shot Composed Image Retrieval with Textual Inversion](https://mlsanity.com/paper/2303.15247/) (2023)
- [GME: Improving Universal Multimodal Retrieval by Multimodal LLMs](https://mlsanity.com/paper/2412.16855/) (2024)
- [UniIR: Training and Benchmarking Universal Multimodal Information Retrievers](https://mlsanity.com/paper/2311.17136/) (2023)
- [Open-domain Visual Entity Recognition: Towards Recognizing Millions of Wikipedia Entities](https://mlsanity.com/paper/2302.11154/) (2023)
- [jina-embeddings-v4: Universal Embeddings for Multimodal Multilingual Retrieval](https://mlsanity.com/paper/2506.18902/) (2025)
- [GeneCIS: A Benchmark for General Conditional Image Similarity](https://mlsanity.com/paper/2306.07969/) (2023)
- [UME-R1: Exploring Reasoning-Driven Generative Multimodal Embeddings](https://mlsanity.com/paper/2511.00405/) (2025)
- [Filter, Then Reweight: Rethinking Optimization Granularity in On-Policy Distillation](https://mlsanity.com/paper/2606.02684/) (2026)
- [GraphMaster: Automated Graph Synthesis via LLM Agents in Data-Limited Environments](https://mlsanity.com/paper/2504.00711/) (2025)
- [GameVerse: Can Vision-Language Models Learn from Video-based Reflection?](https://mlsanity.com/paper/2603.06656/) (2026)
- [IPIBench: Evaluating Interactive Proactive Intelligence of MLLMs under Continuous Streams](https://mlsanity.com/paper/2605.27074/) (2026)
- [Handling Label Noise via Instance-Level Difficulty Modeling and Dynamic Optimization](https://mlsanity.com/paper/2505.00812/) (2025)
- [Mixture of Length and Pruning Experts for Knowledge Graphs Reasoning](https://mlsanity.com/paper/2507.20498/) (2025)
- [CapGeo-Bench: Decoupling Visual Perception from Reasoning and Evaluating Geometric Understanding](https://mlsanity.com/paper/2510.09302/) (2025)
- [LEDGERMIND: Provenance-Constrained Multimodal Agentic Reasoning with a Structured Evidence Ledger](https://mlsanity.com/paper/2607.28374/) (2026)
- [Unveiling Fine-Grained Visual Traces: Evaluating Multimodal Interleaved Reasoning Chains in Multimodal STEM Tasks](https://mlsanity.com/paper/2604.19697/) (2026)
- [Towards Spatial Supersensing in the Wild](https://mlsanity.com/paper/2607.13681/) (2026)
- [Dynamic Residual Encoding with Slide-Level Contrastive Learning for End-to-End Whole Slide Image Representation](https://mlsanity.com/paper/2511.05034/) (2025)
- [EviRank: Structured Relevance Evidence for Multimodal Image Re-ranking](https://mlsanity.com/paper/2608.20886/) (2026)

## Built on by (most cited first, 2 of 2)

- [Learning Multimodal Embeddings with Evidence-Aligned Readout](https://mlsanity.com/paper/2609.33659/) (2026)
- [Video-Arena: A Scalable Agentic Video Benchmark for Spatiotemporal Capability](https://mlsanity.com/paper/2610.14158/) (2026)

## Abstract (arXiv)

Mobile AI acts as a visual oracle, empowering users to snap a picture of something and ask for information. Snap-and-ask retrieval is now one of the most common entry points for mobile AI, yet photos are often blurry, while text questions may be short or mistyped. Existing benchmarks only test on clean inputs or do not isolate paired robustness in snap-and-ask retrieval. Therefore, we introduce SnapBench, the first paired benchmark for robust snap-and-ask multimodal retrieval, spanning 1,145 queries, 9,085 gallery items under 53 controlled corruption conditions with human annotations. We evaluate 16 multimodal retrievers, covering dual-tower encoders and embedding-based VLMs. Results show that image corruptions substantially degrade retrieval, while text corruptions mainly affect text-only retrieval and have limited impact on joint retrieval. Clean image-only retrieval often outperforms joint retrieval, indicating the coarse-text drag and the lack of cross-modal fallback under noisy inputs. SnapBench provides a controlled testbed for evaluating robust retrieval in snap-and-ask scenarios. We further propose MOOR (Modality-anchored, Outlier-aware, Optimal Reweighting), a simple adaptive fusion approach, highlighting the need for reliability-aware modality calibration in snap-and-ask retrieval.