REVIEW 10 cited by
MegaPairs: Massive Data Synthesis For Universal Multimodal Retrieval
Not yet reviewed by Pith; the record is open.
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
MegaPairs: Massive Data Synthesis For Universal Multimodal Retrieval
read the original abstract
Despite the rapidly growing demand for multimodal retrieval, progress in this field remains severely constrained by a lack of training data. In this paper, we introduce MegaPairs, a novel data synthesis method that leverages vision language models (VLMs) and open-domain images, together with a massive synthetic dataset generated from this method. Our empirical analysis shows that MegaPairs generates high-quality data, enabling the multimodal retriever to significantly outperform the baseline model trained on 70$\times$ more data from existing datasets. Moreover, since MegaPairs solely relies on general image corpora and open-source VLMs, it can be easily scaled up, enabling continuous improvements in retrieval performance. In this stage, we produced more than 26 million training instances and trained several models of varying sizes using this data. These new models achieve state-of-the-art zero-shot performance across 4 popular composed image retrieval (CIR) benchmarks and the highest overall performance on the 36 datasets provided by MMEB. They also demonstrate notable performance improvements with additional downstream fine-tuning. Our produced dataset, well-trained models, and data synthesis pipeline will be made publicly available to facilitate the future development of this field.
Forward citations
Cited by 10 Pith papers
-
PLUME: Latent Reasoning Based Universal Multimodal Embedding
PLUME uses latent-state autoregressive rollouts and a progressive training curriculum to deliver efficient reasoning for universal multimodal embeddings without generating explicit rationales.
-
Douyin Multimodal Embedding Model Technical Report
Latent typed reasoning plus cross-conditional reconstruction during training improves multimodal retrieval accuracy while keeping inference a standard dense bi-encoder, yielding 74.8 (2B) and 78.4 (9B) on MMEB-v2.
-
VIG-RL: Learning to Search and Insert for Verified Image Grounding
An RL-trained ReAct agent learns joint search–selection–insertion of retrieved authentic images, setting SOTA on MRAMG-Bench Verified Image Grounding.
-
TIGER-FG: Text-Guided Implicit Fine-Grained Grounding for E-commerce Retrieval
TIGER-FG proposes text-guided implicit fine-grained grounding with dual distillation to address modality and granularity asymmetries in image-to-multimodal e-commerce retrieval, reporting Recall@1 gains of 6.1 and 34....
-
HIVE: Query, Hypothesize, Verify An LLM Framework for Multimodal Reasoning-Intensive Retrieval
HIVE raises multimodal retrieval nDCG@10 to 41.7 on the MM-BRIGHT benchmark by inserting LLM-driven hypothesis generation and verification between retrieval passes, delivering +9.5 over the best text-only baseline and...
-
FreeRet: MLLMs as Training-Free Retrievers
A prompt-and-layer tweak lets pretrained multimodal LLMs serve as competitive retrieval systems without any additional training, with reranking framed as multiple-choice questions to reduce label bias.
-
FreeRet: MLLMs as Training-Free Retrievers
FreeRet enables pretrained MLLMs to act as training-free retrievers via semantically grounded embeddings and reasoning-based reranking, outperforming models trained on millions of pairs on MMEB benchmarks.
-
MetaEmbed: Scaling Multimodal Retrieval at Test-Time with Flexible Late Interaction
MetaEmbed trains fixed learnable Meta Tokens to produce granularity-organized multi-vector embeddings that support test-time scaling in multimodal retrieval.
-
Combating Visual Neglect and Semantic Drift in Large Multimodal Models for Enhanced Cross-Modal Retrieval
SSA-ME uses saliency-aware modeling to reduce visual neglect and semantic drift, achieving SOTA results on the MMEB benchmark for multimodal retrieval.
-
MOON2.0: Dynamic Modality-balanced Multimodal Representation Learning for E-commerce Product Understanding
MOON2.0 combines modality-routed experts, intra-product image-text alignment, MLLM-generated data augmentation, and dynamic sample filtering to reach state-of-the-art zero-shot e-commerce product understanding.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.