TRACE: Task-Adaptive Reasoning and Representation Learning for Universal Multimodal Retrieval

Documenti analoghi

• WISER: Wider Search, Deeper Thinking, and Adaptive Fusion for Training-Free Zero-Shot Composed Image Retrieval
  di: Wang, Tianyue, et al.
  Pubblicazione: (2026)
• PLUME: Latent Reasoning Based Universal Multimodal Embedding
  di: He, Chenwei, et al.
  Pubblicazione: (2026)
• ReCALL: Recalibrating Capability Degradation for MLLM-based Composed Image Retrieval
  di: Yang, Tianyu, et al.
  Pubblicazione: (2026)
• UniFGVC: Universal Training-Free Few-Shot Fine-Grained Vision Classification via Attribute-Aware Multimodal Retrieval
  di: Guo, Hongyu, et al.
  Pubblicazione: (2025)
• Referring Expression Instance Retrieval and A Strong End-to-End Baseline
  di: Hao, Xiangzhao, et al.
  Pubblicazione: (2025)