ZH
Zijing Hu
cs.CVcs.LGcs.CL
On Valency
published · living versionsW_dbaw8ezb·v1 · currentpublished
MDSKILL: Learning to Internalize Skill Memory through Multi-View Distillation for Efficient Dynamic Agent Self-Evolution
with Dian Jin, Jinluan Yang, Kairong Han, Baohong Li +7
1 version
Preprints & journals
8 papers in the corpus · 2025–2026Towards Efficient Reasoning: Learning Causal Shortcuts for Diffusion Language Models2609.28272v1 · Dian Jin, Kairong Han, Baohong Li et al.2026 · 0 citationsarXiv
Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence2607.07675v1 · Shuailei Ma, Jiaqi Liao, Xinyang Wang et al.2026 · 0 citationsarXiv
DCD-PFN: A Decoupling-Aware Foundation Model for Causal Discovery2606.21212v1 · Zhengkang Guan, Yikang Chen, Yi He et al.2026 · 0 citationsarXiv
CDLM: Causal Concept-Guided Diffusion Large Language Models2511.22146v1 · Kairong Han, Nuanqiao Shan, Ziyu Zhao et al.2025 · 0 citationsarXiv
Noise Projection: Closing the Prompt-Agnostic Gap Behind Text-to-Image Misalignment in Diffusion Models2510.14526v1 · Yunze Tong, Didi Zhu, Zijing Hu et al.2025 · 0 citationsarXiv
Asynchronous Denoising Diffusion Models for Aligning Text-to-Image Generation2510.04504v2 · Zijing Hu, Yunze Tong, Fengda Zhang et al.2025 · 0 citationsarXiv
D-Fusion: Direct Preference Optimization for Aligning Diffusion Models with Visually Consistent Samples2505.22002v1 · Zijing Hu, Fengda Zhang, Kun Kuang2025 · 0 citationsarXiv
Towards Better Alignment: Training Diffusion Models with Reinforcement Learning Against Sparse Rewards2503.11240v2 · Zijing Hu, Fengda Zhang, Long Chen et al.2025 · 9 citationsarXiv
Career total: 14 works. 8 are in this corpus.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.