Jinpeng Wang

While multimodal large language models have demonstrated impressive short-term reasoning, they struggle with long-horizon video understanding due to limited context windows and static memory mechanisms that fail to mirror human cognitive efficiency. Existing paradigms typically fall into two extr...

Sequential recommendation models often struggle to capture latent periodic patterns in user interests, primarily due to the noise inherent in time-domain behavioral data. While frequency-domain analysis offers a global perspective to address this, existing approaches typically treat user sequence...