Reason To Contrast: A Cascaded Multimodal Retrieval Framework

Abstract

Traditional multimodal retrieval systems rely primarily on bi-encoder architectures, where performance is closely tied to embedding dimensionality. Recent work, Think-Then-Embed (TTE), shows that incorporating multimodal reasoning to elicit additional informative tokens before embedding can further improve retrieval. In this paper, we extend this paradigm with TTE-v2, a hybrid multimodal retrieval framework that introduces reasoning-driven performance scaling based on additional input token budget rather than model or embedding size. Our approach augments the initial multimodal retrieval with additional reasoning steps for reranking, enabling more expressive query-candidate interactions at test time. The reranking stage further provides fine-grained supervision for hard negative mining and false negative filtering, creating a feedback loop that effectively strengthens the upstream retriever. This cascaded design delivers substantial test-time improvements based on intermediate reasonin

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keycui2025reason

Related papers

• MARVEL: Multimodal Adaptive Reasoning-intensive Expand-rerank And Retrieval (2026)0.00
• Reasoning-augmented Representations For Multimodal Retrieval (2026)0.00
• Reasoning Guided Embeddings: Leveraging MLLM Reasoning For Improved Multimodal Retrieval (2025)0.00
• Mr\(^2\)-bench: Going Beyond Matching To Reasoning In Multimodal Retrieval (2025)1.81
• TRACE: Task-adaptive Reasoning And Representation Learning For Universal Multimodal Retrieval (2026)0.00
• V-retrver: Evidence-driven Agentic Reasoning For Universal Multimodal Retrieval (2026)0.00
• HIVE: Query, Hypothesize, Verify An LLM Framework For Multimodal Reasoning-intensive Retrieval (2026)0.00
• Metaembed: Scaling Multimodal Retrieval At Test-time With Flexible Late Interaction (2025)2.35