Searcharxiv⌕ Search

arXiv subjects

Chunyang Jiang

Publications and source records attributed to Chunyang Jiang.

23 records · Page 2Linked to original sources

Exploring Italian sentence embeddings properties through multi-tasking

We investigate to what degree existing LLMs encode abstract linguistic information in Italian in a multi-task setting. We exploit curated synthetic data on a large scale -- several Blackbird Language Matrices (BLMs) problems in Italian -- and use them to study how sentence representations built using pre-trained language models encode specific syntactic and semantic information. We use a two-level architecture to model separately a compression of the sentence embeddings into a representation that contains relevant information for a task, and a BLM task. We then investigate whether we can obtain compressed sentence representations that encode syntactic and semantic information relevant to several BLM tasks. While we expected that the sentence structure -- in terms of sequence of phrases/chunks -- and chunk properties could be shared across tasks, performance and error analysis show that the clues for the different tasks are encoded in different manners in the sentence embeddings, suggesting that abstract linguistic notions such as constituents or thematic roles does not seem to be present in the pretrained sentence embeddings.

cs.CL↗

AgentMonitor: A Plug-and-Play Framework for Predictive and Secure Multi-Agent Systems

The rapid advancement of large language models (LLMs) has led to the rise of LLM-based agents. Recent research shows that multi-agent systems (MAS), where each agent plays a specific role, can outperform individual LLMs. However, configuring an MAS for a task remains challenging, with performance only observable post-execution. Inspired by scaling laws in LLM development, we investigate whether MAS performance can be predicted beforehand. We introduce AgentMonitor, a framework that integrates at the agent level to capture inputs and outputs, transforming them into statistics for training a regression model to predict task performance. Additionally, it can further apply real-time corrections to address security risks posed by malicious agents, mitigating negative impacts and enhancing MAS security. Experiments demonstrate that an XGBoost model achieves a Spearman correlation of 0.89 in-domain and 0.58 in more challenging scenarios. Furthermore, using AgentMonitor reduces harmful content by 6.2% and increases helpful content by 1.8% on average, enhancing safety and reliability. Code is available at \url{https://github.com/chanchimin/AgentMonitor}.

cs.CL↗

Diffuse X-ray Explorer: a high-resolution X-ray spectroscopic sky surveyor on the China Space Station

DIffuse X-ray Explorer (DIXE) is a proposed high-resolution X-ray spectroscopic sky surveyor on the China Space Station (CSS). DIXE will focus on studying hot baryons in the Milky Way. Galactic hot baryons like the X-ray emitting Milky Way halo and eROSITA bubbles are best observed in the sky survey mode with a large field of view. DIXE will take advantage of the orbital motion of the CSS to scan a large fraction of the sky. High-resolution X-ray spectroscopy, enabled by superconducting microcalorimeters based on the transition-edge sensor (TES) technology, will probe the physical properties (e.g., temperature, density, elemental abundances, kinematics) of the Galactic hot baryons. This will complement the high-resolution imaging data obtained with the eROSITA mission. Here we present the preliminary design of DIXE. The payload consists mainly of a detector assembly and a cryogenic cooling system. The key components of the detector assembly are a microcalorimeter array and frequency-domain multiplexing readout electronics. To provide a working temperature for the detector assembly, the cooling system consists of an adiabatic demagnetization refrigerator and a mechanical cryocooler system.

astro-ph.IM↗

Evaluating the System Compliance in Testing Carbon Nanotube Fibers

System compliances of two testing machines (Keysight T150 and Instron 3365) were studied for the tensile testing of carbon nanotube (CNT) fibers. Due to the different gripping methods, the T150's system compliance was nearly zero, while that of the Instron was nonnegligible. By analyzing the data dispersion with the Weibull theory, a safe gauge length of >10 mm was suggested for CNT fibers. Therefore, a standard test procedure should involve the compliance evaluation, choice of gauge length, and Weibull statistical analysis.

cond-mat.mtrl-sci↗

Assembly-Dependent Interfacial Property of Carbon Nanotube Fibers with Epoxy and Its Enhancement via Generalized Surface Sizing

In building up composite structures using carbon nanotube (CNT) fibers, the fiber-to-matrix interfacial shear strength (IFSS) is one of the most important issues. Originating from the assembly characteristics of CNT fiber, the IFSS strongly depends on the fiber's twisting level and densification level. Furthermore, there are rich ways to modify the fiber surface and thus enhance the IFSS, including the physical and chemical modification on fiber surface, the infiltration of matrix resin into CNT fiber, and the introduction of silane coupling agent. A new feature differing from carbon fibers is that all these treatments either change the fiber's surface structure or form a several-hundreds-nm-thick interphase inside rather than around the fiber. These "generalized" treatments obviously extend the common concept of surface sizing and can be used for various forms of CNT assembly structures.

cond-mat.mtrl-sci↗