papers

Publications (61)

eess.SY2024

Nonlinear Kalman Filtering based on Self-Attention Mechanism and Lattice Trajectory Piecewise Linear Approximation

Jiaming Wang, Xinyu Geng, Jun Xu

The traditional Kalman filter (KF) is widely applied in control systems, but it relies heavily on the accuracy of the system model and noise parameters, leading to potential perfor…

physics.space-ph2024

Anisotropy of Density Fluctuations in the Solar Wind at 1 au

Jiaming Wang, Rohit Chhiber, Sohom Roy +6

A well-known property of solar wind plasma turbulence is the observed anisotropy of the autocorrelations, or equivalently the spectra, of velocity and magnetic field fluctuations.…

cs.CV2026

The Second Challenge on Real-World Face Restoration at NTIRE 2026: Methods and Results

Jingkai Wang, Jue Gong, Zheng Chen +50

This paper provides a review of the NTIRE 2026 challenge on real-world face restoration, highlighting the proposed solutions and the resulting outcomes. The challenge focuses on ge…

cs.SD2023

FunASR: A Fundamental End-to-End Speech Recognition Toolkit

Zhifu Gao, Zerui Li, Jiaming Wang +8

This paper introduces FunASR, an open-source speech recognition toolkit designed to bridge the gap between academic research and industrial applications. FunASR offers models train…

astro-ph.HE2021

Chandra grating spectroscopy of embedded wind shock X-ray emission from O stars shows low plasma temperatures and significant wind absorption

David H. Cohen, Winter Parts, Graham M. Doskoch +4

We present a uniform analysis of six examples of embedded wind shock (EWS) O star X-ray sources observed at high resolution with the Chandra grating spectrometers. By modeling both…

cs.RO2023

Deep Reinforcement Learning Based Framework for Mobile Energy Disseminator Dispatching to Charge On-the-Road Electric Vehicles

Jiaming Wang, Jiqian Dong, Sikai Chen +2

The exponential growth of electric vehicles (EVs) presents novel challenges in preserving battery health and in addressing the persistent problem of vehicle range anxiety. To addre…

cs.CV2026

T2AV-Compass: Towards Unified Evaluation for Text-to-Audio-Video Generation

Zhe Cao, Tao Wang, Jiaming Wang +10

Text-to-Audio-Video (T2AV) generation aims to synthesize temporally coherent video and semantically synchronized audio from natural language, yet its evaluation remains fragmented,…

cs.CL2025

SDGO: Self-Discrimination-Guided Optimization for Consistent Safety in Large Language Models

Peng Ding, Wen Sun, Dailin Li +4

Large Language Models (LLMs) excel at various natural language processing tasks but remain vulnerable to jailbreaking attacks that induce harmful content generation. In this paper,…

cond-mat.str-el2022

Emergence of spin singlets with inhomogeneous gaps in the kagome Heisenberg antiferromagnets Zn-barlowite and herbertsmithite

Jiaming Wang, Weishi Yuan, Philip M. Singer +5

The kagome Heisenberg antiferromagnet formed by frustrated spins arranged in a lattice of corner-sharing triangles is a prime candidate for hosting a quantum spin liquid (QSL) grou…

cs.CV2021

Pan-sharpening via High-pass Modification Convolutional Neural Network

Jiaming Wang, Zhenfeng Shao, Xiao Huang +3

Most existing deep learning-based pan-sharpening methods have several widely recognized issues, such as spectral distortion and insufficient spatial texture enhancement, we propose…

astro-ph.SR2020

Chandra spectral measurements of the O supergiant Puppis indicate a surprising increase in the wind mass-loss rate over 18 years

David H. Cohen, Jiaming Wang, Véronique Petit +4

New long Chandra grating observations of the O supergiant Pup show not only a brightening of the x-ray emission line flux of 13 per cent in the 18 years since Chandra's first…

astro-ph.SR2026

Averaging Effects on the Solar Wind Alfven Mach Number: Implications for Switchbacks and Alfven Transition

Joshua Goodwill, Subash Adhikari, Francesco Pecora +10

Averaging techniques in solar wind measurements have been a longstanding subject of debate. Using Parker Solar Probe (PSP) observations from encounters 1 to 19, we investigate how…

cs.CL2026

SOP-Maze: Evaluating Large Language Models on Complicated Business Standard Operating Procedures

Jiaming Wang, Zhe Tang, Zehao Jin +5

As large language models (LLMs) are widely deployed as domain-specific agents, many benchmarks have been proposed to evaluate their ability to follow instructions and make decision…

cs.CV2024

OrthCaps: An Orthogonal CapsNet with Sparse Attention Routing and Pruning

Xinyu Geng, Jiaming Wang, Jiawei Gong +4

Redundancy is a persistent challenge in Capsule Networks (CapsNet),leading to high computational costs and parameter counts. Although previous works have introduced pruning after t…

cs.SD2024

LauraGPT: Listen, Attend, Understand, and Regenerate Audio with GPT

Zhihao Du, Jiaming Wang, Qian Chen +12

Generative Pre-trained Transformer (GPT) models have achieved remarkable performance on various natural language processing tasks, and have shown great potential as backbones for a…

physics.space-ph2026

Noise in Synthetic and Solar Wind Data: Superposition Principles

Jiaming Wang, Francesco Pecora, Rohit Chhiber +3

The interplanetary magnetic field exhibits a distinctive spectral density from frequencies of around $\unit[10^{-6}]{Hz}$ to around $\unit[10^{-4}]{Hz}$, ranging from harmoni…

cs.SE2026

CodeTracer: Towards Traceable Agent States

Han Li, Yifan Yao, Letian Zhu +13

Code agents are advancing rapidly, but debugging them is becoming increasingly difficult. As frameworks orchestrate parallel tool calls and multi-stage workflows over complex tasks…

cs.RO2025

Training-free Task-oriented Grasp Generation

Jiaming Wang, Diwen Liu, Jizhuo Chen +1

This paper presents a training-free pipeline for task-oriented grasp generation that combines pre-trained grasp generation models with vision-language models (VLMs). Unlike traditi…

cond-mat.str-el2022

Spin excitations of a proximate Kitaev quantum spin liquid realized in CuIrO

Sean K. Takahashi, Jiaming Wang, Alexandre Arsenault +4

Magnetic moments arranged at the corners of a honeycomb lattice are predicted to form a novel state of matter, Kitaev quantum spin liquid, under the influence of frustration effect…

cond-mat.mes-hall2025

Angle-dependent resonant tunneling and thermoelectric energy management in a hybrid 1D-2D-1D semiconductor nanostructure

Xiaoguang Luo, Jiaming Wang, Jiawen Dai +2

Low-dimensional semiconductors have been widely exploited in thermoelectric energy conversion for high efficiencies due to their suppressed lattice thermal conduction, sharply defi…

quant-ph2021

Schrödinger-cat states in Landau-Zener-Stückelberg-Majorana interferometry: a multiple Davydov Ansatz approach

Lu Wang, Fulu Zheng, Jiaming Wang +2

Employing the time-dependent variational principle combined with the multiple Davydov Ansatz, we investigate Landau-Zener (LZ) transitions in a qubit coupled to a ph…

cs.MM2022

MMSpeech: Multi-modal Multi-task Encoder-Decoder Pre-training for Speech Recognition

Xiaohuan Zhou, Jiaming Wang, Zeyu Cui +4

In this paper, we propose a novel multi-modal multi-task encoder-decoder pre-training framework (MMSpeech) for Mandarin automatic speech recognition (ASR), which employs both unlab…

physics.plasm-ph2025

Healing of the edge magnetic island in the island divertor configuration on J-TEXT

Zhangrong Hou, Song Zhou, Nengchao Wang +18

The phenomena of island healing and configuration transition induced by high-power electron cyclotron resonance heating (ECRH) have been investigated in the island divertor configu…

cs.RO2025

GeNIE: A Generalizable Navigation System for In-the-Wild Environments

Jiaming Wang, Diwen Liu, Jizhuo Chen +4

Reliable navigation in unstructured, real-world environments remains a significant challenge for embodied agents, especially when operating across diverse terrains, weather conditi…

cs.CL2024

An Embarrassingly Simple Approach for LLM with Strong ASR Capacity

Ziyang Ma, Guanrou Yang, Yifan Yang +8

In this paper, we focus on solving one of the most important tasks in the field of speech processing, i.e., automatic speech recognition (ASR), with speech foundation encoders and…

cond-mat.str-el2023

Local probe investigation of the spin dynamics in the kagome and inter-layers of orthorhombic barlowite Cu(OD)FBr: Br and Cu NQR study

Takashi Imai, Jiaming Wang, Rebecca W. Smaha +3

We report Br and Cu nuclear quadrupole resonance (NQR) in the paramagnetic state above K of the antiferromagnetic orthorhombic phase of barlowite Cu…

cond-mat.str-el2022

Emergence of the spin polarized domains in the kagome lattice Heisenberg antiferromagnet Zn-barlowite (ZnCu)Cu(OD)FBr

Weishi Yuan, Jiaming Wang, Philip M. Singer +4

Kagome lattice Heisenberg antiferromagnets are known to be highly sensitive to perturbations caused by structural disorder. NMR is a local probe ideally suited for investigating su…

cs.CR2026

Train in Vain: Functionality-Preserving Poisoning to Prevent Unauthorized Use of Code Datasets

Yuan Xiao, Jiaming Wang, Yuchen Chen +8

The widespread availability of large-scale code datasets has accelerated the development of code large language models (CodeLLMs), raising concerns about unauthorized dataset usage…

astro-ph.SR2024

Observed Fluctuation Enhancement and Departure from WKB Theory in Sub-Alfvénic Solar Wind

David Ruffolo, Panisara Thepthong, Peera Pongkitiwanichakul +12

Using Parker Solar Probe data from orbits 8 through 17, we examine fluctuation amplitudes throughout the critical region where the solar wind flow speed approaches and then exceeds…

cs.SD2023

TOLD: A Novel Two-Stage Overlap-Aware Framework for Speaker Diarization

Jiaming Wang, Zhihao Du, Shiliang Zhang

Recently, end-to-end neural diarization (EEND) is introduced and achieves promising results in speaker-overlapped scenarios. In EEND, speaker diarization is formulated as a multi-l…

cs.CV2020

Stroke Constrained Attention Network for Online Handwritten Mathematical Expression Recognition

Jiaming Wang, Jun Du, Jianshu Zhang

In this paper, we propose a novel stroke constrained attention network (SCAN) which treats stroke as the basic unit for encoder-decoder based online handwritten mathematical expres…

cs.CV2026

TextAlign: Preference Alignment for Text Rendering with Hierarchical Rewards

Mingxuan Cui, Jingpu Yang, Fengxian Ji +6

Faithful text rendering remains a persistent weakness of large text-to-image generative models, as it requires both semantic instruction following and fine-grained glyph-level stru…

physics.plasm-ph2023

Validation of the plasma-wall self-organization model for density limit in ECRH-assisted start-up of Ohmic discharges on J-TEXT

Jiaxing Liu, Ping Zhu, Dominique Franck Escande +14

A recently developed plasma-wall self-organization (PWSO) model predicts a significantly enhanced density limit, which may be attainable in tokamaks with ECRH-assisted ohmic startu…

cs.CV2022

GLSD: The Global Large-Scale Ship Database and Baseline Evaluations

Zhenfeng Shao, Jiaming Wang, Lianbing Deng +8

In this paper, we introduce a challenging global large-scale ship database (called GLSD), designed specifically for ship detection tasks. The designed GLSD database includes a tota…

quant-ph2026

Numerical simulation methods for quantum sensing at parametric criticality

Kirill Petrovnin, Jiaming Wang, Gheorghe Sorin Paraoanu

Microwave photon detection is a key technology for low-temperature superconducting electronics and quantum information processing. A promising possibility is to use switching proce…

eess.IV2021

SSCAN: A Spatial-spectral Cross Attention Network for Hyperspectral Image Denoising

Zhiqiang Wang, Zhenfeng Shao, Xiao Huang +3

Hyperspectral images (HSIs) have been widely used in a variety of applications thanks to the rich spectral information they are able to provide. Among all HSI processing tasks, HSI…

cs.CV2026

TOPO-Bench: An Open-Source Topological Mapping Evaluation Framework with Quantifiable Perceptual Aliasing

Jiaming Wang, Jizhuo Chen, Diwen Liu +1

Topological mapping offers a compact and robust representation for navigation, but progress in the field is hindered by the lack of standardized evaluation metrics, datasets, and p…

cs.CV2024

ParseCaps: An Interpretable Parsing Capsule Network for Medical Image Diagnosis

Xinyu Geng, Jiaming Wang, Jun Xu

Deep learning has excelled in medical image classification, but its clinical application is limited by poor interpretability. Capsule networks, known for encoding hierarchical rela…

astro-ph.SR2025

Characterization of the Trans-Alfvénic Region Using Observations from Parker Solar Probe

Subash Adhikari, Riddhi Bandyopadhyay, Joshua Goodwill +14

Close to Earth the solar wind is usually super-Alfvénic, i.e. the speed of the solar wind is much larger than the Alfvén speed. However, in the lower coronal regions, the solar w…

cs.AI2026

Where Do Deep-Research Agents Go Wrong? Span-Level Error Localization in Agent Trajectories

Jiaming Wang, Ziteng Feng, Jiangtao Wu +8

Deep-research agents solve tasks through long trajectories of search, tool use, evidence inspection, and answer synthesis. Evaluation based on final answers shows whether an agent…

cond-mat.str-el2022

Freezing of the Lattice in the Kagome Lattice Heisenberg Antiferromagnet Zn-barlowite ZnCu(OD)FBr

Jiaming Wang, Weishi Yuan, Philip M. Singer +5

We use Br nuclear quadrupole resonance (NQR) to demonstrate that ultra slow lattice dynamics set in below the temperature scale set by the Cu-Cu super-exchange interaction $…

cs.RO2023

Probable Object Location (POLo) Score Estimation for Efficient Object Goal Navigation

Jiaming Wang, Harold Soh

To advance the field of autonomous robotics, particularly in object search tasks within unexplored environments, we introduce a novel framework centered around the Probable Object…

physics.space-ph2026

A robust empirical relationship between speed and turbulence energy in the near-Earth solar wind

Rohit Chhiber, Yanwen Wang, Manuel E. Cuesta +2

The connection between turbulence and solar-wind acceleration, long known in space physics, is further developed in this Letter by establishing a robust empirical law that relates…

cs.AI2026

LongCat-Flash-Thinking-2601 Technical Report

Meituan LongCat Team, Anchun Gui, Bei Li +162

We introduce LongCat-Flash-Thinking-2601, a 560-billion-parameter open-source Mixture-of-Experts (MoE) reasoning model with superior agentic reasoning capability. LongCat-Flash-Thi…

cs.CV2021

TANet: A new Paradigm for Global Face Super-resolution via Transformer-CNN Aggregation Network

Yuanzhi Wang, Tao Lu, Yanduo Zhang +4

Recently, face super-resolution (FSR) methods either feed whole face image into convolutional neural networks (CNNs) or utilize extra facial priors (e.g., facial parsing maps, faci…

astro-ph.SR2026

Interplanetary magnetic correlation and low-frequency spectrum over many solar rotations

Jiaming Wang, Francesco Pecora, Rohit Chhiber +2

Fluctuations and structure across a wide range of spatial and temporal scales are frequently studied in the solar wind. The properties of the low-frequency fluctuations are of rele…

cs.AI2026

Agentic-MME: What Agentic Capability Really Brings to Multimodal Intelligence?

Qianshan Wei, Yishan Yang, Siyi Wang +12

Multimodal Large Language Models (MLLMs) are evolving from passive observers into active agents, solving problems through Visual Expansion (invoking visual tools) and Knowledge Exp…

cs.CV2026

The 1st PortraitCraft Challenge: A CVPR 2026 Workshop Competition on Portrait Composition Understanding and Generation

Zijie Lou, Youyun Tang, Xiaochao Qu +40

This paper presents an overview of the inaugural PortraitCraft Challenge, held as one of the official competitions at CVPR 2026. The challenge focuses on portrait composition under…

quant-ph2025

Microwave photon detection at parametric criticality

Kirill Petrovnin, Jiaming Wang, Michael Perelshtein +2

The detection of microwave fields at single-photon power levels is a much sought-after technology, with practical applications in nanoelectronics and quantum information science. H…

cs.RO2026

Change-Robust Online Spatial-Semantic Topological Mapping

Jiaming Wang, Jizhuo Chen, Diwen Liu +4

Autonomous robots require change-robust spatial-semantic reasoning: using spatial and semantic knowledge to decide where to go, how to get there, and where the robot is despite env…

cs.RO2026

VRA: Grounding Discrete-Time Joint Acceleration in Voltage-Constrained Actuation

Lingwei Zhang, Jiaming Wang, Tianlin Zhang +5

Discrete-time joint acceleration constraints are widely used to enforce position and velocity limits. However, under voltage-constrained electric actuators, kinematically admissibl…

cs.CV2026

CoVEBench: Can Video Editing Models Handle Complex Instructions?

Jiangtao Wu, Jiaming Wang, Yiwen He +7

While recent text-guided video editing models excel at elementary tasks (e.g., style transfer, object insertion), real-world user requests are highly compositional. A single prompt…

cs.LG2026

ContextBench: A Benchmark for Context Retrieval in Coding Agents

Han Li, Letian Zhu, Bohan Zhang +7

LLM-based coding agents have shown strong performance on automated issue resolution benchmarks, yet existing evaluations largely focus on final task success, providing limited insi…

cs.CL2026

Winning the Pruning Gamble: A Unified Approach to Joint Sample and Token Pruning for Efficient Supervised Fine-Tuning

Shaobo Wang, Jiaming Wang, Jiajun Zhang +9

As supervised fine-tuning (SFT) evolves from a lightweight post-training step into a compute-intensive phase rivaling mid-training in scale, data efficiency has become critical for…

cs.CL2025

LongCat-Flash Technical Report

Meituan LongCat Team, Bayan, Bei Li +179

We introduce LongCat-Flash, a 560-billion-parameter Mixture-of-Experts (MoE) language model designed for both computational efficiency and advanced agentic capabilities. Stemming f…

astro-ph.SR2024

Noise in the Heliosphere: A Target for PUNCH Science

Jiaming Wang, William H. Matthaeus, Rohit Chhiber +4

We present a broad review of 1/f noise observations in the heliosphere, and discuss and complement the theoretical background of generic 1/f models as relevant to NASA's PUNCH miss…

cs.CV2021

Unsupervised Remote Sensing Super-Resolution via Migration Image Prior

Jiaming Wang, Zhenfeng Shao, Tao Lu +3

Recently, satellites with high temporal resolution have fostered wide attention in various practical applications. Due to limitations of bandwidth and hardware cost, however, the s…

cs.SE2023

kTrans: Knowledge-Aware Transformer for Binary Code Embedding

Wenyu Zhu, Hao Wang, Yuchen Zhou +4

Binary Code Embedding (BCE) has important applications in various reverse engineering tasks such as binary code similarity detection, type recovery, control-flow recovery and data-…

cond-mat.str-el2021

NMR Investigation on Honeycomb Iridate AgLiIrO

Jiaming Wang, Weishi Yuan, Takashi Imai +3

We investigate the structural and magnetic properties of a Kitaev spin liquid candidate material AgLiIrO based on Li nuclear magnetic resonance line shape, Knight s…

cs.RO2025

GBPP: Grasp-Aware Base Placement Prediction for Robots via Two-Stage Learning

Jizhuo Chen, Diwen Liu, Jiaming Wang +1

GBPP is a fast learning based scorer that selects a robot base pose for grasping from a single RGB-D snapshot. The method uses a two stage curriculum: (1) a simple distance-visibil…

astro-ph.SR2024

The Alfvén Transition Zone observed by the Parker Solar Probe in Young Solar Wind -- Global Properties and Model Comparisons

Rohit Chhiber, Francesco Pecora, Arcadi V Usmanov +6

The transition from subAlfvénic to superAlfvénic flow in the solar atmosphere is examined by means of Parker Solar Probe (PSP) measurements during solar encounters 8 to 14. Aroun…