Publications 论文发表

arXiv2026 Carnator: Fast Text-to-Video Generation with Generation-Native Compatibility-Guided Cross-Request Reuse

A cross-request acceleration framework that uses generation-native compatibility evidence from early diffusion states, reaching up to 2.17× end-to-end speedup.一个跨请求加速框架：从扩散模型的早期状态中读出「生成原生」的兼容性证据，端到端最高加速 2.17 倍。
View Paper查看论文

arXiv2026 CoDeR: Local Constraint-Compatible Retrieval Beyond Semantic Similarity

A local constraint-compatible dense retrieval method that separates topical relevance from constraint compatibility for constraint-sensitive queries.一种面向约束敏感查询的局部约束相容稠密检索方法，把「主题相关」与「约束相容」分开建模。
View Paper查看论文

NeurIPS2026 GLOVE: Global Verifier for LLM Memory-Environment Realignment

A framework that introduces a new design dimension for LLM memory systems by establishing a relative notion of truth.一个通过建立「相对真理」这一概念，为大模型记忆系统引入新设计维度的框架。
View Paper查看论文

arXiv2025 Experience Scaling: Post-Deployment Evolution For Large Language Models

A framework for continuous post-deployment evolution for LLMs through autonomous interaction with the environment and collaborative sharing of accumulated experience.一个让大模型通过与环境的自主交互、以及协同共享所积累的经验，在部署之后持续演化的框架。
View Paper查看论文

npj Wireless Technology2025 Ubiquitous Intelligence Via Wireless Network-Driven LLMs Evolution

A paradigm where LLMs evolve within wireless network-driven ecosystems through continuous coordination between networks and models.一种让大模型在无线网络驱动的生态中、通过网络与模型的持续协同而演化的范式。
View Paper查看论文

IJCNN2021 Forecasting Stock Prices Using Stock Correlation Graph: A Graph Convolutional Network Approach

Glad to see this work being used by quant firms :)很高兴看到这项研究被量化机构采用 :)

A graph convolutional network approach that leverages stock correlation graphs to forecast stock prices.一种利用股票之间的相关性图来预测股价的图卷积网络方法。
View Paper查看论文