We propose Memory-Space Visual Retracing (MemVR), a novel hallucination mitigation paradigm without needing external knowledge retrieval or additional fine-tuning. MemVR has two significant advantages ...
Abstract: Multimodal large language models (MLLMs) have garnered widespread attention from researchers due to their remarkable understanding and generation capabilities in visual language tasks (e.g., ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results