Verve: Versatile Retrieval For Videos Via Unified Embeddings

Abstract

Modern video retrieval systems are expected to handle diverse tasks ranging from corpus-level retrieval, fine-grained moment localization to flexible multimodal querying. Specialized architectures achieve strong retrieval performance by training modality-specific encoders on massive datasets, but they lack the ability to process composed multimodal queries. In contrast, multimodal LLM (MLLM)-based methods support rich multimodal search but their retrieval performance remains well below that of specialized systems. We present VeRVE, an MLLM-based versatile video retrieval framework that integrates corpus and moment-level retrieval capabilities while accommodating composed multimodal queries within a single architecture. We use contrastive alignment of visual and textual embeddings generated using a shared MLLM backbone to facilitate efficient embedding-based candidate search. Our embedding model, trained efficiently using low-rank adaptation (LoRA) on 700K paired visual-text data sample

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyhalbe2026verve

Related papers

• Vidvec: Unlocking Video MLLM Embeddings For Video-text Retrieval (2026)0.00
• Vlm2vec-v2: Advancing Multimodal Embedding For Videos, Images, And Visual Documents (2025)0.00
• Vill-e: Video LLM Embeddings For Retrieval (2026)0.00
• MERLIN: Multimodal Embedding Refinement Via Llm-based Iterative Navigation For Text-video Retrieval-rerank Pipeline (2024)5.84
• Embedding-based Retrieval In Multimodal Content Moderation (2025)2.26
• Evo-retriever: Llm-guided Curriculum Evolution With Viewpoint-pathway Collaboration For Multimodal Document Retrieval (2026)0.00
• Multiple Visual-semantic Embedding For Video Retrieval From Query Sentence (2020)2.26
• Modality-balanced Embedding For Video Retrieval (2022)7.16