Publications (47)
Kinematics of the Local Spiral Structure Revealed by Young Stars in \emph{Gaia}~DR3
Dejian Liu, Ye Xu, Chaojie Hao +4
Using young open clusters and O--B2-type stars in~\emph{Gaia}~DR3, we investigate the kinematics of the local spiral structure. In general, the young sources in the outer spiral ar…
A Nanometer-Thick Oxide Semiconductor Transistor with Ultra-High Drain Current
Zehao Lin, Mengwei Si, Vahid Askarpour +12
High drive current is a critical performance parameter in semiconductor devices for high-speed, low-power logic applications or high-efficiency, high-power, high-speed radio freque…
TAdaRAG: Task Adaptive Retrieval-Augmented Generation via On-the-Fly Knowledge Graph Construction
Jie Zhang, Bo Tang, Wanzi Shao +8
Retrieval-Augmented Generation (RAG) improves large language models by retrieving external knowledge, often truncated into smaller chunks due to the input context window, which lea…
Xinyu AI Search: Enhanced Relevance and Comprehensive Results with Rich Answer Presentations
Bo Tang, Junyi Zhu, Chenyang Xi +15
Traditional search engines struggle to synthesize fragmented information for complex queries, while generative AI search engines face challenges in relevance, comprehensiveness, an…
SparseX: Efficient Segment-Level KV Cache Sharing for Interleaved LLM Serving
Quqing Zhang, Kai Chen, Ning Liao +5
In long-context LLM serving, the prefill stage often dominates time-to-first-token and computational cost. Although Prefix Cache in vLLM/PagedAttention has been widely used to reus…
Teacher-Student Framework Enhanced Multi-domain Dialogue Generation
Shuke Peng, Xinjing Huang, Zehao Lin +3
Dialogue systems dealing with multi-domain tasks are highly required. How to record the state remains a key problem in a task-oriented dialogue system. Normally we use human-define…
Innovator: Scientific Continued Pretraining with Fine-grained MoE Upcycling
Ning Liao, Xiaoxing Wang, Zehao Lin +18
A large language model (LLM) with knowledge in both scientific and general tasks is the foundation of science general intelligence. However, directly continued pretraining an LLM u…
Breakdown of Ohm's Law by Disorders in Low-Dimensional Transistors
Chang Niu, Adam Charnas, Jian-Yu Lin +4
Ohm's law provides a fundamental framework for understanding charge transport in conductors and underpins the concept of electrical scaling that has enabled the continuous advancem…
Scalable Complexity Control Facilitates Reasoning Ability of LLMs
Liangkai Hang, Junjie Yao, Zhiwei Bai +17
The reasoning ability of large language models (LLMs) has been rapidly advancing in recent years, attracting interest in more fundamental approaches that can reliably enhance their…
FTII-Bench: A Comprehensive Multimodal Benchmark for Flow Text with Image Insertion
Jiacheng Ruan, Yebin Yang, Zehao Lin +4
Benefiting from the revolutionary advances in large language models (LLMs) and foundational vision models, large vision-language models (LVLMs) have also made significant progress.…
Experimental Investigation of Variations in Polycrystalline Hf0.5Zr0.5O2 (HZO)-based MFIM
Tae Ryong Kim, Revanth Koduru, Zehao Lin +2
Device-to-device variations in ferroelectric (FE) hafnium oxide (HfO2)-based devices pose a crucial challenge that limits the otherwise promising capabilities of this technology. A…
SurveyX: Academic Survey Automation via Large Language Models
Xun Liang, Jiawei Yang, Yezhaohui Wang +11
Large Language Models (LLMs) have demonstrated exceptional comprehension capabilities and a vast knowledge base, suggesting that LLMs can serve as efficient tools for automated sur…
Predict-then-Decide: A Predictive Approach for Wait or Answer Task in Dialogue Systems
Zehao Lin, Shaobo Cui, Guodun Li +6
Different people have different habits of describing their intents in conversations. Some people tend to deliberate their intents in several successive utterances, i.e., they use s…
Local Spiral Structure Traced by Red Clump Stars
Zehao Lin, Ye Xu, Ligang Hou +5
Using the cross-matched data of Gaia EDR3 and the 2MASS Point Source Catalog, a sample of RC stars with parallax accuracies better than 20% is identified and used to reveal the nea…
Molecular Bubble and Outflow in S Mon Revealed by Multiband Datasets
Dejian Liu, Ye Xu, YingJie Li +8
We identify a molecular bubble, and study the star formation and its feedback in the S Mon region, using multiple molecular lines, young stellar objects (YSOs), and infrared data.…
MemOS: A Memory OS for AI System
Zhiyu Li, Chenyang Xi, Chunyu Li +36
Large Language Models (LLMs) have become an essential infrastructure for Artificial General Intelligence (AGI), yet their lack of well-defined memory management systems hinders the…
How Does Environmental Information Disclosure Affect Corporate Environmental Performance? Evidence from Chinese A-Share Listed Companies
Zehao Lin
Global climate warming and air pollution pose severe threats to economic development and public safety, presenting significant challenges to sustainable development worldwide. Corp…
A Morphological Classification of 18190 Molecular Clouds Identified in CO Data from the MWISP Survey
Lixia Yuan, Ji Yang, Fujun Du +9
We attempt to visually classify the morphologies of 18190 molecular clouds, which are identified in the CO(1-0) spectral line data over 450 deg of the second Ga…
: Language Modeling with Explicit Memory
Hongkang Yang, Zehao Lin, Wenjin Wang +13
The training and inference of large language models (LLMs) are together a costly process that transports knowledge from raw data to meaningful computation. Inspired by the memory h…
A Survey on Long-Term Memory Security in LLM Agents: Attacks, Defenses, and Governance Across the Memory Lifecycle
Zehao Lin, Xixuan Hao, Renyu Fu +5
The emergence of writable, cross-session persistent memory in LLM agents introduces a qualitatively different threat landscape from conventional input-centric security concerns, ch…
Why In2O3 Can Make 0.7 nm Atomic Layer Thin Transistors?
Mengwei Si, Yaoqiao Hu, Zehao Lin +7
In this work, we demonstrate enhancement-mode field-effect transistors by atomic-layer-deposited (ALD) amorphous In2O3 channel with thickness down to 0.7 nm. Thickness is found to…
"Wait, I'm Still Talking!" Predicting the Dialogue Interaction Behavior Using Imagine-Then-Arbitrate Model
Zehao Lin, Shaobo Cui, Guodun Li +6
Producing natural and accurate responses like human beings is the ultimate goal of intelligent dialogue agents. So far, most of the past works concentrate on selecting or generatin…
Metis: Memory Foundation Model
Zeyu Zhang, Ziliang Guo, Yihang Sun +14
The paper presents Metis, a memory foundation model that embeds a persistent, dynamically updated memory state within the model backbone, allowing it to store and retrieve informat…
Scaled indium oxide transistors fabricated using atomic layer deposition
Mengwei Si, Zehao Lin, Zhizhong Chen +3
In order to continue to improve integrated circuit performance and functionality, scaled transistors with short channel lengths and low thickness are needed. But the further scalin…
MemOS: An Operating System for Memory-Augmented Generation (MAG) in Large Language Models
Zhiyu Li, Shichao Song, Hanyu Wang +19
Large Language Models (LLMs) have emerged as foundational infrastructure in the pursuit of Artificial General Intelligence (AGI). Despite their remarkable capabilities in language…
Calibrating the Cepheid Period--Wesenheit Relation in the Gaia Bands using Galactic Open Cluster Cepheids
Zehao Lin, Ye Xu, Chaojie Hao +3
Establishing the period--Wesenheit relation requires independent and accurate distance measurements of classical Cepheids (DCEPs). The precise distance provided by an associated op…
MTSS: Learn from Multiple Domain Teachers and Become a Multi-domain Dialogue Expert
Shuke Peng, Feng Ji, Zehao Lin +3
How to build a high-quality multi-domain dialogue system is a challenging work due to its complicated and entangled dialogue state space among each domain, which seriously limits t…
MemOps: Benchmarking Lifecycle Memory Operations in Long-Horizon Conversations
Xixuan Hao, Zeyu Zhang, Zehao Lin +6
The paper introduces MemOps, a benchmark that evaluates long‑term conversational memory by tracking explicit lifecycle operations (remember, forget, update, etc.) rather than only…
East Asian VLBI Network astrometry toward the star-forming region G040.96+02.48 in the Extreme Outer Galaxy
Xianjin Shen, Zehao Lin, Nobuyuki Sakai +18
Accurate astrometric measurements for star-forming regions located on the far side of the Milky Way remain scarce. In this work, we present the astrometric results for a 22\,GHz wa…
Examinations of CO completeness based on three independent CO surveys
Yan Sun, Ji Yang, Qing-Zeng Yan +7
We report the global properties recovered by an ongoing CO survey of the Milky Way Imaging Scroll Painting (MWISP) toward the Galactic outskirts. %To better understand the observat…
Calibrating the Color-Magnitude Relation of M Giants by Using Open Clusters
Xiaoyu Tang, Chaojie Hao, Jing Li +8
M giants, with their distinctive properties such as high luminosity, serve as excellent indicators for mapping the structure of the Milky Way. The distance to distant M giants can…
Chiral Landau levels in Weyl semimetal NbAs with multiple topological carriers
Xiang Yuan, Zhongbo Yan, Chaoyu Song +21
Recently, Weyl semimetals have been experimentally discovered in both inversion-symmetry-breaking and time-reversal-symmetry-breaking crystals. The non-trivial topology in Weyl sem…
Task-Oriented Conversation Generation Using Heterogeneous Memory Networks
Zehao Lin, Xinjing Huang, Feng Ji +2
How to incorporate external knowledge into a neural dialogue model is critically important for dialogue systems to behave like real humans. To handle this problem, memory networks…
VLBI with SKA: Possible Arrays and Astrometric Science
Yingjie Li, Ye Xu, Jingjing Li +4
The next generation of very long baseline interferometry (VLBI) is stepping into the era of microarcsecond (as) astronomy, and pushing astronomy, especially astrometry, to new…
Kinematics of Young Stellar Objects Under Various Stellar Feedback
Longhui Yang, Dejian Liu, Chaojie Hao +6
Based on the Gaia Data Release 3 and APOGEE datasets, we investigate the kinematic differences between young stellar objects (YSOs) and their parent clouds in five nearby star-form…
TA-VLA: Elucidating the Design Space of Torque-aware Vision-Language-Action Models
Zongzheng Zhang, Haobo Xu, Zhuo Yang +5
Many robotic manipulation tasks require sensing and responding to force signals such as torque to assess whether the task has been successfully completed and to enable closed-loop…
Distributions and Physical Properties of Molecular Clouds in the Third Galactic Quadrant: = [219.75, 229.75] and = [-5.25, 5.25]
Yiwei Dong, Yan Sun, Ye Xu +11
We present the results of an unbiased CO/CO/CO ( = 1-0) survey in a portion of the third Galactic quadrant (TGQ): = [219.75, 229.75] and = […
Mapping the Milky Way with Masers
Ye Xu, Kazi Rygl, Huib Jan van Langevelde +10
SKA-VLBI is poised to revolutionize our understanding of the Galactic structure through its unprecedented astrometric precision and sensitivity. As a next-generation facility, it w…
Ultralow Voltage Operation of p- and n-FETs Enabled by Self-Formed Gate Dielectric and Metal Contacts on 2D Tellurium
Chang Niu, Linjia Long, Yizhi Zhang +6
The ongoing demand for more energy-efficient, high-performance electronics is driving the exploration of innovative materials and device architectures, where interfaces play a cruc…
Search for Classical Cepheids in Galactic Open Clusters and Calibration of the Period Wesenheit Metallicity Relation in the Gaia Bands
Huajian Wang, Ye Xu, Zehao Lin +3
It is beneficial to calibrate the period Wesenheit metallicity relation (PWZR) of Delta Cephei stars (DCEPs), i.e., classical Cepheids, using accurate parallaxes of associated open…
200 mm Wafer-Scale Monolithic 3D Integration of Atomic Layer-Deposited Oxide Semiconductors
Chang Niu, Linjia Long, Luqi Zheng +9
Monolithic 3D (M3D) integration offers a pathway to overcome the scaling limits of conventional silicon complementary metal-oxide-semiconductor (CMOS) technology by extending dense…
A Gate-All-Around Single-Channel In2O3 Nanoribbon FET with Near 20 mA/μm Drain Current
Zhuocheng Zhang, Zehao Lin, Pai-Ying Liao +12
In this work, we demonstrate atomic-layer-deposited (ALD) single-channel indium oxide (In2O3) gate-all-around (GAA) nanoribbon FETs in a back-end-of-line (BEOL) compatible process.…
Similar Scenes arouse Similar Emotions: Parallel Data Augmentation for Stylized Image Captioning
Guodun Li, Yuchen Zhai, Zehao Lin +1
Stylized image captioning systems aim to generate a caption not only semantically related to a given image but also consistent with a given style description. One of the biggest ch…
Scaled Atomic-Layer-Deposited Indium Oxide Nanometer Transistors with Maximum Drain Current Exceeding 2 A/mm at Drain Voltage of 0.7 V
Mengwei Si, Zehao Lin, Adam Charnas +1
In this work, we demonstrate scaled back-end-of-line (BEOL) compatible indium oxide (In2O3) transistors by atomic layer deposition (ALD) with channel thickness (Tch) of 1.0-1.5 nm,…
MM-CamObj: A Comprehensive Multimodal Dataset for Camouflaged Object Scenarios
Jiacheng Ruan, Wenzhen Yuan, Zehao Lin +5
Large visual-language models (LVLMs) have achieved great success in multiple applications. However, they still encounter challenges in complex scenes, especially those involving ca…
A New Statistical Analysis of the Morphology of Spiral Galaxies
Junye Wei, Ye Xu, Zehao Lin +4
Morphology is the starting point for understanding galaxies. Elmegreen et al. classified spiral galaxies into flocculent, multiple-arm, and grand-design galaxies based on the regul…
Dialogue State Tracking with Multi-Level Fusion of Predicted Dialogue States and Conversations
Jingyao Zhou, Haipang Wu, Zehao Lin +2
Most recently proposed approaches in dialogue state tracking (DST) leverage the context and the last dialogue states to track current dialogue states, which are often slot-value pa…