arXiv cs.AI / cs.LG / cs.CL·9d agoCross-Modal Attention Acts as a Frequency Filter: Why Verbose Prompts Improve Robustness in Vision-Language Models#cross-modal-attention#image-corruption#llava-onevisionAI research1
arXiv cs.AI / cs.LG / cs.CL·12d agoSlipSense: Multimodal Tactile Learning for Low-Latency and Generalized Slip Detection#cross-modal-attention#dexterous-manipulation#multimodalAI research