Shengjie Zhao

SiMO: Single-Modality-Operable Multimodal Collaborative Perception

GenCape: Structure-Inductive Generative Modeling for Category-Agnostic Pose Estimation

Point4Bit: Post Training 4-bit Quantization for Point Cloud 3D Detection

ShotBench: Expert-Level Cinematic Understanding in Vision-Language Models

From Imitation to Introspection: Probing Self-Consciousness in Language Models

Learning Semantic-Enhanced Dual Temporal Adjacent Maps for Video Moment Retrieval