3 papers
cs.CV2026
FocusMem: Factorizing Content, Readout, and Trust in Latent GUI Memory
Zhuoran Zhang, Bowen Li, Jingcheng Ju +5
GUI agents must remember both useful experience from earlier tasks and unfinished progress in the current interaction. Latent memory offers a compact solution by compressing multim…
cs.LG2025
Hybrid Attribution Priors for Explainable and Robust Model Training
Zhuoran Zhang, Feng Zhang, Shangyuan Li +5
Small language models (SLMs) are widely used in tasks that require low latency and lightweight deployment, particularly classification. As interpretability and robustness gain incr…
cs.CL2025
Instance Relation Learning Network with Label Knowledge Propagation for Few-shot Multi-label Intent Detection
Shiman Zhao, Shangyuan Li, Wei Chen +4
Few-shot Multi-label Intent Detection (MID) is crucial for dialogue systems, aiming to detect multiple intents of utterances in low-resource dialogue domains. Previous studies focu…