# When Images Look Right and Retrieve Wrong: Coverage-Guided Cross-Scale Re-Indexing for Knowledge-Faithful Generative Perception

arXiv: https://arxiv.org/abs/2608.20810 · HTML: https://mlsanity.com/paper/2608.20810/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 36 of its 57 references that are in the map.
- First posted on arXiv 21 Aug 2026.

## Builds on (most cited first, 30 of 36)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Sigmoid Loss for Language Image Pre-Training](https://mlsanity.com/paper/2303.15343/) (2023)
- [InstructPix2Pix: Learning to Follow Image Editing Instructions](https://mlsanity.com/paper/2211.09800/) (2022)
- [FiLM: Visual Reasoning with a General Conditioning Layer](https://mlsanity.com/paper/1709.07871/) (2017)
- [V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation](https://mlsanity.com/paper/1606.04797/) (2016)
- [Semantic Image Synthesis with Spatially-Adaptive Normalization](https://mlsanity.com/paper/1903.07291/) (2019)
- [SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features](https://mlsanity.com/paper/2502.14786/) (2025)
- [Extract Free Dense Labels from CLIP](https://mlsanity.com/paper/2112.01071/) (2021)
- [DenseCLIP: Language-Guided Dense Prediction with Context-Aware Prompting](https://mlsanity.com/paper/2112.01518/) (2021)
- [Stacked Cross Attention for Image-Text Matching](https://mlsanity.com/paper/1803.08024/) (2018)
- [Similarity Reasoning and Filtration for Image-Text Matching](https://mlsanity.com/paper/2101.01368/) (2021)
- [IMRAM: Iterative Matching with Recurrent Attention Memory for Cross-Modal Image-Text Retrieval](https://mlsanity.com/paper/2003.03772/) (2020)
- [Controlling Vision-Language Models for Multi-Task Image Restoration](https://mlsanity.com/paper/2310.01018/) (2023)
- [Learning Semantic Concepts and Order for Image and Sentence Matching](https://mlsanity.com/paper/1712.02036/) (2017)
- [Consensus-Aware Visual-Semantic Embedding for Image-Text Matching](https://mlsanity.com/paper/2007.08883/) (2020)
- [A Multi-Scale and Multi-Depth Convolutional Neural Network for Remote Sensing Imagery Pan-Sharpening](https://mlsanity.com/paper/1712.09809/) (2017)
- [Rethinking Entropy Interventions in RLVR: An Entropy Change Perspective](https://mlsanity.com/paper/2510.10150/) (2025)
- [HyperTransformer: A Textural and Spectral Feature Fusion Transformer for Pansharpening](https://mlsanity.com/paper/2203.02503/) (2022)
- [Fine-Grained Preference Optimization Improves Spatial Reasoning in VLMs](https://mlsanity.com/paper/2506.21656/) (2025)
- [Transfer CLIP for Generalizable Image Denoising](https://mlsanity.com/paper/2403.15132/) (2024)
- [ReCreate: Reasoning and Creating Domain Agents Driven by Experience](https://mlsanity.com/paper/2601.11100/) (2026)
- [Content-Adaptive Non-Local Convolution for Remote Sensing Pansharpening](https://mlsanity.com/paper/2404.07543/) (2024)
- [Learning Human-Perceived Fakeness in AI-Generated Videos via Multimodal LLMs](https://mlsanity.com/paper/2509.22646/) (2025)
- [Scheduling Your LLM Reinforcement Learning with Reasoning Trees](https://mlsanity.com/paper/2510.24832/) (2025)
- [CoRe3D: Collaborative Reasoning as a Foundation for 3D Intelligence](https://mlsanity.com/paper/2512.12768/) (2025)
- [The Dark Side of Explanations: Poisoning Recommender Systems with Counterfactual Examples](https://mlsanity.com/paper/2305.00574/) (2023)
- [Multi-class Support Vector Machine with Maximizing Minimum Margin](https://mlsanity.com/paper/2312.06578/) (2023)
- [CrossDiff: Exploring Self-Supervised Representation of Pansharpening via Cross-Predictive Diffusion Model](https://mlsanity.com/paper/2401.05153/) (2024)
- [DeepInterestGR: Mining Deep Multi-Interest Using Multi-Modal LLMs for Generative Recommendation](https://mlsanity.com/paper/2602.18907/) (2026)

## Built on by (most cited first, 3 of 3)

- [When LLM Meets Tree Search: A Systematic View of Inference as Search in Large Language Models](https://mlsanity.com/paper/2608.30395/) (2026)
- [HGSQ: Heatmap-Guided Sparse Query Detector for Real-Time Aerial Small Object Detection](https://mlsanity.com/paper/2609.13306/) (2026)
- [LIBERO-MAX: Do Robot Policies Adapt When the World Changes?](https://mlsanity.com/paper/2609.36518/) (2026)

## Abstract (arXiv)

Multimodal information systems increasingly route generated visual content back through the same vision-language index that informed its production, so the output must remain retrievable by the queries it was meant to serve. When the scene contains entities at vastly different scales, existing language-guided generators condition on a single, globally pooled text embedding and quietly drop scale-specific concepts, breaking concept-query retrieval even when pixel fidelity is high. We formalise this failure as semantic collapse and propose CERES, a closed-loop multimodal indexing framework that builds a three-level semantic pyramid, mines implicit concepts via a co-occurrence-aware router, performs scale-routed cross-attention into a lightweight U-Net generator, and verifies coverage by re-indexing the generated image with the same frozen VLM. A continuously differentiable soft-Jaccard coverage objective returns dense gradients to the 0.39 M-parameter generator under explicit non-degeneracy conditions, and coverage is verified by an independent DINOv2 linear probe trained only on external scene and object labels. On four pansharpening benchmarks across seven settings, CERES delivers the new state of the art with the largest gains where scale variation is most extreme (+4.64% relative Q2n and +9.7 mAP for DOTA detection). It also improves concept-query retrieval Recall@5 by +14.0 points and image-text mean reciprocal rank by 0.19 over the strongest baseline, showing that the closed loop preserves queryable content rather than self-referential feature consistency.