Time-series data generated by Web services and connected systems support applications such as user activity analysis, service monitoring, and resource management. However, learning transferable representations from heterogeneous time series remains challenging due to diverse temporal patterns, variable sequence lengths...
Pei-Wang Tang, He Cheng, Yu-Peng Ye et al.· 0 citations
Historical experience can guide scientific coding at multiple levels, but task-level retrieval may miss implementation lessons that become relevant during execution. We introduce MUSE, a memory management framework combining multi-level memory with selective runtime injection for scientific coding agents. MUSE builds g...
Hao-Ran Jin, De-Fu Lian, Xi-Ting Wang et al.· 0 citations
Generating and editing presentation slides requires models to combine accurate text rendering, instruction following, visual grounding, aesthetic design, and precise editing within one canvas. Existing work covers only subsets of these capabilities and lacks large-scale slide-native supervision and diagnostic evaluatio...
Jia-Hao Wang, Xi-Yan Jiang, Chen-Yuan Wu et al.· 0 citations
SYNTRA is introduced, a self-improving agentic framework that turns a few retrieval examples into reusable synthesis instructions that enables scalable embedding-model adaptation with minimal human intervention.
Zucan Lyu, Rui Tang, Jianlyu Chen et al.· 0 citations
Results show that long-horizon reflective data is an effective route toward self-improving agents, and synthesize long-horizon improvement trajectories from machine learning and algorithmic programming tasks, two domains that offer verifiable feedback and reward sustained iteration.
Hong-Jin Qian, Chao-Fan Li, Kun Luo et al.· 0 citations
Information-Gain-Gated Self-Distillation (IGSD) is proposed, which verifies on-policy token proposals with environment feedback before distillation, and supports environment-verified hindsight as an effective approach to reliable action-level supervision for search agents.
Ang-Qing Jiang, Gao-Ming Zhang, Chao-Qun Zhang et al.· 0 citations
This work introduces a clustering mechanism and proposes the Cluster Sketch Linear Bandit algorithm, which preserves the full covariance information in each cluster to guarantee robust sublinear regret without spectral-tail vulnerabilities, performs cluster switching by assigning a sentinel for each cluster, and reduce...
Dense retrieval has become a cornerstone of modern local-lifestyle e-commerce search by encoding queries and items into semantic embedding spaces. While recent advancements have transitioned from BERT-based embedding models to Large Language Models (LLMs), most approaches still treat LLMs as static text encoders, negle...
Ang-Qing Jiang, Gao-Ming Zhang, Jian-Chun Song et al.· ACM International Conference...· 0 citations
SpecTD-MR, a novel medication recommendation framework for Disease Spectrum-aware and Time-evolving Dependency Learning, is proposed that surpasses state-of-the-art baselines in accuracy, while providing visualizable structural associations to support insights into dynamic disease evolution.
Yi-Shuo Li, Cong Wang, Shou-Jin Wang et al.· ACM Transactions on Informat...· 1 citation
DisCo is presented, a skill-powered research agent that creates skills and uses them during research, and yields the AREX-Skill Library, with 5,000+ verified skills distilled from 1,000 widely used ML repositories and organized into 20 areas and 178 capability families.
Jianlyu Chen, Yuyang Hu, Hong-Jin Qian et al.· 1 citation
This work proposes Dynamic Index-based RECommendation with Transport-Optimized Retrieval with Transport-Optimized Retrieval (DIRECTOR), a transport-guided parallel reranking framework that consistently outperforms strong reranking baselines, achieving significant improvement in large-scale industrial recommendation sce...
A Hierarchical Semantic Alignment module to align query's latent space with item's quantization path and synchronize multi-granular semantics, and a personalized GR framework that models user behavior by synergizing discrete SIDs for structural guidance and continuous representations for fine-grained semantic refinemen...
Gao-Ming Zhang, Ang-Qing Jiang, Jian-Chun Song et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.