Model Releases
HMGCLIP: Heterogeneous Multi-Granularity Contrastive Learning for E-commerce Representation Learning
arXiv:2608.24467v1 Announce Type: new Abstract: Although recent Multimodal Large Language Models (MLLMs) have advanced general product understanding, they implicitly encode product information into gl
arXiv:2608.24467v1 Announce Type: new Abstract: Although recent Multimodal Large Language Models (MLLMs) have advanced general product understanding, they implicitly encode product information into global embeddings, thereby limiting their ability to capture fine-grained attributes. This limitation hinders performance in tasks requiring precise attribute discrimination, such as distinguishing subtle material differences among visually similar products. To address this challenge, we propose HMGCLIP, a unified multimodal embedding framework. By constructing a heterogeneous hypergraph, we leverage hypergraph topology to mine structure-aware hard negatives and align multi-granular semantics at both relation and hyperedge levels. This design enables a dual-granularity inference mechanism that dynamically fuses attribute evidence for both fine-grained and coarse-grained downstream tasks. Furthermore, we release a comprehensive fine-grained e-commerce dataset to facilitate future benchmarking. Extensive experiments on this new dataset and the public MAVE benchmark show that HMGCLIP outperforms strong multimodal encoders, MLLMs, and e-commerce baselines, validating the superiority of HMGCLIP.
Related
- MOON2.0: Dynamic Modality-balanced Multimodal Representation Learning for E-commerce Product Understanding
- MOON3.0: Reasoning-aware Multimodal Representation Learning for E-commerce Product Understanding
- From Generator to Embedder: Harnessing Innate Abilities of Multimodal LLMs via Building Zero-Shot Discriminative Embedding Model
Source: arXiv cs.AI | 2026-08-26