Canran Xiao

Reversible Primitive–Composition Alignment for Continual Vision–Language Learning

Pi-CCA: Prompt-Invariant CCA Certificates for Replay-Free Continual Multimodal Learning

Path Matters: Unveiling Geometric Implicit Bias via Curvature-Aware Sparse View Optimization

Meta-UCF: Unified Task-Conditioned LoRA Generation for Continual Learning in Large Language Models

CoMem: Compositional Concept-Graph Memory for Vision–Language Adaptation

C3-OWD: A Curriculum Cross-modal Contrastive Learning Framework for Open-World Detection

Flames: Multi-Scale Mamba with Adaptive Fourier Filters and Laplace Transform for Time Series Forecasting

AdaKAN: Kolmogorov-Arnold Networks with Adaptive Spectral Decomposition for Time Series Forecasting

Dynamic Cross-Layer Prefix Alignment for Resolving Label Preference Discrepancies in LLMs Fine-Tuning

Enhancing Cooperative Problem-Solving in Sparse-Reward Systems via Co-evolutionary Curriculum Learning