left|,circlearrowright,text{BUS},right|: A Large and Diverse Multimodal Benchmark for evaluating the ability of Vision-Language Models to understand Rebus Puzzles Paper • 2511.01340 • Published Nov 3 • 12
Leveraging Self-Attention for Input-Dependent Soft Prompting in LLMs Paper • 2506.05629 • Published Jun 5 • 37