Jia Li

Regulation of La₂O₃ dispersed distribution on grain boundary pinning and sintering densification of MoLa alloy

Ke Yang, Boliang Hu, Jia Li, Xinrui Zhao et autres

cn (code pays fourni par la source)

Sintering densification kinetics and microstructural-property evolution of ultrafine molybdenum powders

Qianjun Zhang, Boliang Hu, Jia Li, Xinrui Zhao et autres

cn, by (code pays fourni par la source)

Enhanced coking and sintering resistant in dry reforming of methane over CoRh alloy confined in mesoporous silica

Liang Ye, Wenming Liu, Bo Yao, Guobo Li et autres

cn (code pays fourni par la source)

Taohong siwu decoction alleviates hand-foot skin reaction by regulating RAGE-mediated keratinocyte apoptosis and autophagy

Huijing Dong, Zhening Liu, Fuhuan Yu, Jia Li et autres

cn (code pays fourni par la source)

Train Short, Inference Long: Training-free Horizon Extension for Autoregressive Video Generation

Jia Li, Xiaoqin Fu, Xurui Peng, Weifeng Chen et autres

Autoregressive video diffusion models have emerged as a scalable paradigm for long video generation. However, they often suffer from severe extrapolation failure, where rapid error accumulation leads to significant temporal degradation when extending beyond training horizons. We identify that this failure primarily …

Scaling the Scaling Logic: Agentic Meta-Synthesis of Logic Reasoning

Bowen Liu, Zhe Wu, Runquan Xie, Zhanhui Kang et autres

Reinforcement Learning from Verifiable Rewards (RLVR) is bottlenecked by data: existing synthesis pipelines rely on expert-written code or fixed templates, confining growth to instance-level perturbations. We shift the evolvable unit from problem instances to task-family specifications. SSLogic is an agentic meta-synthesis framework …

Scaling the Scaling Logic: Agentic Meta-Synthesis of Logic Reasoning

Bowen Liu, Zhe Wu, Runquan Xie, Zhanhui Kang et autres

Reinforcement Learning from Verifiable Rewards (RLVR) is bottlenecked by data: existing synthesis pipelines rely on expert-written code or fixed templates, confining growth to instance-level perturbations. We shift the evolvable unit from problem instances to task-family specifications. SSLogic is an agentic meta-synthesis framework …

hk, cn (code pays fourni par la source)