visual recognition
- HetSyn: Versatile Timescale Integration in Spiking Neural Networks via Heterogeneous Synapses
- InfoChartQA: A Benchmark for Multimodal Question Answering on Infographic Charts
- RePIC: Reinforced Post-Training for Personalizing Multi-Modal Language Models
- TaiwanVQA: Benchmarking and Enhancing Cultural Understanding in Vision-Language Models