3 papers
cs.LG2026
OpenAVS: Training-Free Open-Vocabulary Audio Visual Segmentation with Foundational Models
Shengkai Chen, Yifang Yin, Jinming Cao +3
Audio-visual segmentation aims to separate sounding objects from videos by predicting pixel-level masks based on audio signals. Existing methods primarily concentrate on closed-set…
cs.AI2026
DRAGON: LLM-Driven Decomposition and Reconstruction Agents for Large-Scale Combinatorial Optimization
Shengkai Chen, Zhiguang Cao, Jianan Zhou +5
Large Language Models (LLMs) have recently shown promise in addressing combinatorial optimization problems (COPs) through prompt-based strategies. However, their scalability and ge…
cs.CV2025
SimCast: Enhancing Precipitation Nowcasting with Short-to-Long Term Knowledge Distillation
Yifang Yin, Shengkai Chen, Yiyao Li +4
Precipitation nowcasting predicts future radar sequences based on current observations, which is a highly challenging task driven by the inherent complexity of the Earth system. Ac…