FUSE: Flow-based Unified Zero-shot Segmentation by ExpressionHouru Jiang*, Zixi Wang, Mingliang Hou, Zitao Liu, Teng Guo, Renqiang Luo Submitted to CVPR 2026 on December 9, 2025
All-as-Vision: Transferable Visual Exercise Representation for Knowledge TracingZixi Wang, Qing Qing, Houru Jiang, Mingliang Hou, Ziqi Xu, Renqiang Luo Submitted to ACMMM 2026 on March 26, 2026
An Information-Theoretic Evaluation Framework for Benchmark and Model Diagnosis in Knowledge TracingHouru Jiang*, Zixi Wang*, Tengteng Cheng, Xueyi Li, Mingliang Hou, Jiaqi Zheng, Renqiang Luo, Teng Guo, Zitao Liu Accepted as poster at NeurIPS 2026 · arXiv
VLM-CD: Making Concept Annotations Optional with Frozen Vision-Language EmbeddingsZixi Wang, Houru Jiang*, Mingliang Hou, Youheng Bai, Renqiang Luo, Teng Guo, Jiaqi Zheng, Qianru Liang Submitted to AAAI 2027 on July 20, 2026
All-as-Vision: A Content-Native Exercise Interface for Transferable Knowledge TracingZixi Wang, Qing Qing, Houru Jiang, Mingliang Hou, Renqiang Luo, Xikun Zhang, Ziqi Xu Submitted to AAAI 2027 on July 20, 2026
ResidKT: Disentangling Sequential Dynamics via Neuro-Symbolic Prior-Residual Learning for Knowledge TracingZixi Wang*, Houru Jiang*, Tengteng Cheng, Xueyi Li, Mingliang Hou, Zitao Liu Submitted to AAAI 2027 on July 21, 2026
When Target Accuracy Hides Semantic Interface Drift in Vision–Language AdaptationHouru Jiang*, Zixi Wang*, Mingliang Hou, Xueyi Li, Teng Guo, Qianru Liang, Zitao Liu Submitted to ICLR 2027 on September 17, 2026
Residualizing DKT with Symbolic Sequence Priors for Knowledge TracingZixi Wang*, Houru Jiang*, Tengteng Cheng, Xueyi Li, Mingliang Hou, Zitao Liu Submitted to AISTATS 2027 on September 29, 2026
CDIS: Training-Free Data Selection for Instruction Tuning with Compression Ratio and Token EntropyHouru Jiang*, Zixi Wang, Mingliang Hou, Xueyi Li, Teng Guo, Jiaqi Zheng, Renqiang Luo Submitted to ACL ARR 2026 October on October 5, 2026
