# WIDE: Wildcard Inference with Dynamic Expansion for Cross-Modal Generative Retrieval

arXiv: https://arxiv.org/abs/2609.03554 · HTML: https://mlsanity.com/paper/2609.03554/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 22 of its 40 references that are in the map.
- First posted on arXiv 3 Sep 2026.

## Builds on (most cited first, 22 of 22)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks](https://mlsanity.com/paper/1610.02136/) (2016)
- [SoundStream: An End-to-End Neural Audio Codec](https://mlsanity.com/paper/2107.03312/) (2021)
- [Autoregressive Image Generation using Residual Quantization](https://mlsanity.com/paper/2203.01941/) (2022)
- [Image Retrieval on Real-life Images with Pre-trained Vision-and-Language Models](https://mlsanity.com/paper/2108.04024/) (2021)
- [Transformer Memory as a Differentiable Search Index](https://mlsanity.com/paper/2202.06991/) (2022)
- [Lexically Constrained Decoding for Sequence Generation Using Grid Beam Search](https://mlsanity.com/paper/1704.07138/) (2017)
- [Can Pre-trained Vision and Language Models Answer Visual Information-Seeking Questions?](https://mlsanity.com/paper/2302.11713/) (2023)
- [Automatic Spatially-aware Fashion Concept Discovery](https://mlsanity.com/paper/1708.01311/) (2017)
- [Visual News: Benchmark and Challenges in News Image Captioning](https://mlsanity.com/paper/2010.03743/) (2020)
- [On NMT Search Errors and Model Errors: Cat Got Your Tongue?](https://mlsanity.com/paper/1908.10090/) (2019)
- [Open-domain Visual Entity Recognition: Towards Recognizing Millions of Wikipedia Entities](https://mlsanity.com/paper/2302.11154/) (2023)
- [A Neural Corpus Indexer for Document Retrieval](https://mlsanity.com/paper/2206.02743/) (2022)
- [Guided Open Vocabulary Image Captioning with Constrained Beam Search](https://mlsanity.com/paper/1612.00576/) (2016)
- [Sparse Meets Dense: Unified Generative Recommendations with Cascaded Sparse-Dense Representations](https://mlsanity.com/paper/2503.02453/) (2025)
- [Generative Cross-Modal Retrieval: Memorizing Images in Multimodal Language Models for Retrieval and Beyond](https://mlsanity.com/paper/2402.10805/) (2024)
- [EDIS: Entity-Driven Image Search over Multimodal Web Content](https://mlsanity.com/paper/2305.13631/) (2023)
- [Re3val: Reinforced and Reranked Generative Retrieval](https://mlsanity.com/paper/2401.16979/) (2024)
- [CART: A Generative Cross-Modal Retrieval Framework with Coarse-To-Fine Semantic Modeling](https://mlsanity.com/paper/2406.17507/) (2024)
- [SemCORE: A Semantic-Enhanced Generative Cross-Modal Retrieval Framework with MLLMs](https://mlsanity.com/paper/2504.13172/) (2025)

## Abstract (arXiv)

Generative retrieval has demonstrated significant success by unifying representation learning and search into a single sequence-to-sequence generation task. However, extending this paradigm to cross-modal retrieval reveals a critical challenge arising from the inherent information asymmetry across different modalities, such as the gap between concise text queries and dense visual candidates. This structural mismatch causes the autoregressive decoder to suffer from forced hallucination when generating identifiers via standard trie-constrained beam search, where the model is severely penalized for failing to guess fine-grained details absent from the query, allowing irrelevant candidates to hijack top rankings. To address this issue, we propose Wildcard Inference with Dynamic Expansion (WIDE). WIDE employs Adaptive Entropy Thresholding (AET) to calibrate layer-specific uncertainty boundaries offline. During the decoding generation phase, Asymmetry-aware Wildcard Decoding (AWD) detects semantic blind spots and emits wildcards instead of forced deterministic identifiers, dynamically expanding the search space without incurring log-probability penalties. Finally, Blind-Spot Re-ranking (BSR) evaluates the expanded candidate pool using a hybrid scoring mechanism that combines discrete generation confidence with continuous semantic similarity. Extensive experiments on the M-BEIR benchmark demonstrate that WIDE outperforms state-of-the-art generative retrieval methods, effectively suppressing forced hallucination while maintaining compact index structures.