CLEAR: Unlocking Generative Potential for Degraded Image Understanding in Unified Multimodal Models Paper • 2604.04780 • Published 5 days ago • 8
TRACE: Task-Adaptive Reasoning and Representation Learning for Universal Multimodal Retrieval Paper • 2603.02929 • Published Mar 4
WISER: Wider Search, Deeper Thinking, and Adaptive Fusion for Training-Free Zero-Shot Composed Image Retrieval Paper • 2602.23029 • Published 18 days ago • 1
ReCALL: Recalibrating Capability Degradation for MLLM-based Composed Image Retrieval Paper • 2602.01639 • Published 11 days ago
WISER: Wider Search, Deeper Thinking, and Adaptive Fusion for Training-Free Zero-Shot Composed Image Retrieval Paper • 2602.23029 • Published 18 days ago • 1
PLUME: Latent Reasoning Based Universal Multimodal Embedding Paper • 2604.02073 • Published 9 days ago • 13
CLEAR: Unlocking Generative Potential for Degraded Image Understanding in Unified Multimodal Models Paper • 2604.04780 • Published 5 days ago • 8
CLEAR: Unlocking Generative Potential for Degraded Image Understanding in Unified Multimodal Models Paper • 2604.04780 • Published 5 days ago • 8
PLUME: Latent Reasoning Based Universal Multimodal Embedding Paper • 2604.02073 • Published 9 days ago • 13
PLUME: Latent Reasoning Based Universal Multimodal Embedding Paper • 2604.02073 • Published 9 days ago • 13
Unifying Group-Relative and Self-Distillation Policy Optimization via Sample Routing Paper • 2604.02288 • Published 9 days ago • 27