Licheng Jiao

Task-free Adaptive Meta Black-box Optimization

STVG-R1: Incentivizing Instance-Level Reasoning and Grounding in Videos via Reinforcement Learning

SM-ShapNAS: Shapley-Enhanced Multimodal Neural Architecture Search via Sparse Modeling

Rethinking Multiple-Instance Learning From Feature Space to Probability Space

Vision Foundation Models Bridge the Geometric Knowledge Across Domains for Long-Tailed Recognition

Hybrid Contrastive Transformer for Visual Tracking

Spatio-temporal Diffusion Transformer for Action Recognition

Diffusion SigFormer for Interference Time-series Signal Recognition