Searcharxiv⌕ Search

arXiv subjects

Chenghu Yang

Publications and source records attributed to Chenghu Yang.

4 recordsLinked to original sources

Synapse-Control: Making Agent Experience Actionable with Lightweight Runtime Control

Large language model agents reuse execution experience to improve reliability on complex tool-based tasks. Systems such as Sentry call large models to generate failure diagnoses before retrieving advice, adding inference cost to experience reuse. We present Synapse-Control, an agent runtime whose lightweight control plane selects advice and determines when to send it to the task-executing model. Rules shortlist relevant advice, and a lightweight 1.7B classifier fine-tuned on teacher-labeled state-suggestion pairs scores those candidates instead of generating a diagnosis. Micro-contracts encode reusable interface checks, such as required arguments or valid options, without prescribing complete task programs. A Prompt Value Table records earlier guidance and feedback to limit repeated suggestions through cooldown and token-budget checks. Across 1,308 attempts per method in AppWorld and WebShop, Synapse-Control achieves 270 successes (29.8% more than Base), replaces 4,987 generative diagnosis calls, and reduces auxiliary control time relative to Sentry by 50.2% and 51.0%, respectively.

cs.CL↗

ArcNeural: A Multi-Modal Database for the Gen-AI Era

ArcNeural introduces a novel multimodal database tailored for the demands of Generative AI and Large Language Models, enabling efficient management of diverse data types such as graphs, vectors, and documents. Its storage-compute separated architecture integrates graph technology, advanced vector indexing, and transaction processing to support real-time analytics and AI-driven applications. Key features include a unified storage layer, adaptive edge collection in MemEngine, and seamless integration of transaction and analytical processing. Experimental evaluations demonstrate ArcNeural's superior performance and scalability compared to state-of-the-art systems. This system bridges structured and unstructured data management, offering a versatile solution for enterprise-grade AI applications. ArcNeural's design addresses the challenges of multimodal data processing, providing a robust framework for intelligent, data-driven solutions in the Gen AI era.

cs.DB↗

Scale-Aware Neural Architecture Search for Multivariate Time Series Forecasting

Multivariate time series (MTS) forecasting has attracted much attention in many intelligent applications. It is not a trivial task, as we need to consider both intra-variable dependencies and inter-variable dependencies. However, existing works are designed for specific scenarios, and require much domain knowledge and expert efforts, which is difficult to transfer between different scenarios. In this paper, we propose a scale-aware neural architecture search framework for MTS forecasting (SNAS4MTF). A multi-scale decomposition module transforms raw time series into multi-scale sub-series, which can preserve multi-scale temporal patterns. An adaptive graph learning module infers the different inter-variable dependencies under different time scales without any prior knowledge. For MTS forecasting, a search space is designed to capture both intra-variable dependencies and inter-variable dependencies at each time scale. The multi-scale decomposition, adaptive graph learning, and neural architecture search modules are jointly learned in an end-to-end framework. Extensive experiments on two real-world datasets demonstrate that SNAS4MTF achieves a promising performance compared with the state-of-the-art methods.

cs.LG↗

Learning from Multiple Time Series: A Deep Disentangled Approach to Diversified Time Series Forecasting

Time series forecasting is a significant problem in many applications, e.g., financial predictions and business optimization. Modern datasets can have multiple correlated time series, which are often generated with global (shared) regularities and local (specific) dynamics. In this paper, we seek to tackle such forecasting problems with DeepDGL, a deep forecasting model that disentangles dynamics into global and local temporal patterns. DeepDGL employs an encoder-decoder architecture, consisting of two encoders to learn global and local temporal patterns, respectively, and a decoder to make multi-step forecasting. Specifically, to model complicated global patterns, the vector quantization (VQ) module is introduced, allowing the global feature encoder to learn a shared codebook among all time series. To model diversified and heterogenous local patterns, an adaptive parameter generation module enhanced by the contrastive multi-horizon coding (CMC) is proposed to generate the parameters of the local feature encoder for each individual time series, which maximizes the mutual information between the series-specific context variable and the long/short-term representations of the corresponding time series. Our experiments on several real-world datasets show that DeepDGL outperforms existing state-of-the-art models.

cs.LG↗