Publications (130)
Algebraic Independence of Special Points on Shimura Varieties
Yu Fu, Roy Zhao
Given a correspondence between a connected Shimura variety , a commutative connected algebraic group , and , we prove that the -images of any spe…
Not All Heads Matter: A Head-Level KV Cache Compression Method with Integrated Retrieval and Reasoning
Yu Fu, Zefan Cai, Abedelkadir Asi +3
Key-Value (KV) caching is a common technique to enhance the computational efficiency of Large Language Models (LLMs), but its memory overhead grows rapidly with input length. Prior…
Understanding the Effects of Visualizing Missing Values on Visual Data Exploration
Hayeong Song, Yu Fu, Bahador Saket +1
When performing data analysis, people often confront data sets containing missing values. We conducted an empirical study to understand the effects of visualizing those missing val…
Non-simple abelian varieties in a family: arithmetic approaches
Yu Fu
Inspired by the work of Ellenberg, Elsholtz, Hall, and Kowalski, we investigate how the property of the generic fiber of a one-parameter family of abelian varieties being geometric…
AllocMV: Optimal Resource Allocation for Music Video Generation via Structured Persistent State
Huimin Wang, Leilei Ouyang, Chang Xia +3
Generating long-horizon music videos (MVs) is frequently constrained by prohibitive computational costs and difficulty maintaining cross-shot consistency. We propose AllocMV, a hie…
A Covert Data Transport Protocol
Yu Fu, Zhe Jia, Lu Yu +2
Both enterprise and national firewalls filter network connections. For data forensics and botnet removal applications, it is important to establish the information source. In this…
Generalized Eckardt points on del Pezzo surfaces of degree 1
Julie Desjardins, Yu Fu, Kelly Isham +1
We study intersections of exceptional curves on del Pezzo surfaces of degree 1, motivated by questions in arithmetic geometry. Outside characteristics 2 and 3, at most 10 exception…
CT Synthesis with Conditional Diffusion Models for Abdominal Lymph Node Segmentation
Yongrui Yu, Hanyu Chen, Zitian Zhang +8
Despite the significant success achieved by deep learning methods in medical image segmentation, researchers still struggle in the computer-aided diagnosis of abdominal lymph nodes…
Density of algebraic points on products of curves
Jennifer Berg, Yu Fu, Evangelia Gazaki +3
In this paper, we initiate the systematic study of density of algebraic points on surfaces. We give an effective asymptotic range in which the density degree set has regular behavi…
Free Lunch in Pathology Foundation Model: Task-specific Model Adaptation with Concept-Guided Feature Enhancement
Yanyan Huang, Weiqin Zhao, Yihang Chen +2
Whole slide image (WSI) analysis is gaining prominence within the medical imaging field. Recent advances in pathology foundation models have shown the potential to extract powerful…
A Dual-branch Network for Infrared and Visible Image Fusion
Yu Fu, Xiao-Jun Wu
Deep learning is a rapidly developing approach in the field of infrared and visible image fusion. In this context, the use of dense blocks in deep networks significantly improves t…
Biharmonic hypersurfaces with constant scalar curvature in space forms
Yu Fu, Min-Chun Hong
Let be a biharmonic hypersurface with constant scalar curvature in a space form . We show that has constant mean curvature if and is min…
In-vivo entropy production of A. subaru
Yu Fu, Emmy Dobson, Benjamin B. Machta +1
Entropy production is often used as a proxy for energy consumption of a non-equilibrium system. Lower bounds can be estimated from coarse-grained observations, and this has been do…
From Flow to One Step: Real-Time Multi-Modal Trajectory Policies via Implicit Maximum Likelihood Estimation-based Distribution Distillation
Ju Dong, Liding Zhang, Lei Zhang +7
Generative policies based on diffusion and flow matching achieve strong performance in robotic manipulation by modeling multi-modal human demonstrations. However, their reliance on…
Managing Project Teams in an Online Class of 1000+ Students
Nazanin Tabatabaei Anaraki, Taneisha Ng, Gaurav Verma +6
Team projects in Computer Science (CS) help students build collaboration skills, apply theory, and prepare for real-world software development. Online classes present unique opport…
Is Mathematical Problem-Solving Expertise in Large Language Models Associated with Assessment Performance?
Liang Zhang, Yu Fu, Xinyi Jin
Large Language Models (LLMs) are increasingly used in math education not only as problem solvers but also as assessors of learners' reasoning. However, it remains unclear whether s…
From Skills to Talent: Organising Heterogeneous Agents as a Real-World Company
Zhengxu Yu, Yu Fu, Zhiyuan He +5
Individual agent capabilities have advanced rapidly through modular skills and tool integrations, yet multi-agent systems remain constrained by fixed team structures, tightly coupl…
Evaluating the Effect of Audience in a Virtual Reality Presentation Training Tool
Diego Monteiro, Hai-Ning Liang, Hongji Li +2
Public speaking is an essential skill in everyone's professional or academic career. Nevertheless, honing this skill is often tricky because training in front of a mirror does not…
RCoNet: Deformable Mutual Information Maximization and High-order Uncertainty-aware Learning for Robust COVID-19 Detection
Shunjie Dong, Qianqian Yang, Yu Fu +2
The novel 2019 Coronavirus (COVID-19) infection has spread world widely and is currently a major healthcare challenge around the world. Chest Computed Tomography (CT) and X-ray ima…
Cross-Task Defense: Instruction-Tuning LLMs for Content Safety
Yu Fu, Wen Xiao, Jia Chen +4
Recent studies reveal that Large Language Models (LLMs) face challenges in balancing safety with utility, particularly when processing long texts for NLP tasks like summarization a…
Independence of the inverse spin Hall effect with the magnetic phase in thin NiCu films
Sara Varotto, Maxen Cosset-Cheneau, Cécile Grezes +10
Large spin Hall angles have been observed in 3d ferromagnets, but their origin, and especially their link with the ferromagnetic order, remain unclear. Here, we investigate the inv…
Understanding Cellular Noise with Optical Perturbation and Deep Learning
Chuanbo Liu, Yu Fu, Lu Lin +2
Noise plays a crucial role in the regulation of cellular and organismal function and behavior. Exploring noise's impact is key to understanding fundamental biological processes, su…
DSL-LLaDA: Scaling Continuous Denoising to 8B Masked Diffusion LMs
Longxuan Yu, Yunshu Wu, Yu Fu +5
Discrete Masked diffusion language models generate text by iterative parallel decoding, but few-step decoding suffers from a tradeoff between length and quality: with a fixed step…
UniDiffGrasp: A Unified Framework Integrating VLM Reasoning and VLM-Guided Part Diffusion for Open-Vocabulary Constrained Grasping with Dual Arms
Xueyang Guo, Hongwei Hu, Chengye Song +5
Open-vocabulary, task-oriented grasping of specific functional parts, particularly with dual arms, remains a key challenge, as current Vision-Language Models (VLMs), while enhancin…
Revise, Don't Freeze: Sampler-Matched Training for Self-Correcting Masked Diffusion Language Models
Longxuan Yu, Shaorong Zhang, Yu Fu +3
Masked diffusion language models (MDLMs) re-predict every position at each denoising step, but standard samplers commit tokens once revealed, leaving this revision capability unuse…
MACE: A Hybrid LLM Serving System with Colocated SLO-aware Continuous Retraining Alignment
Yufei Li, Yu Fu, Yue Dong +1
Large language models (LLMs) deployed on edge servers are increasingly used in latency-sensitive applications such as personalized assistants, recommendation, and content moderatio…
Psyzkaller: Learning from Historical and On-the-Fly Execution Data for Smarter Seed Generation in OS kernel Fuzzing
Boyu Liu, Yang Zhang, Liang Cheng +6
OS Kernel fuzzers such as Syzkaller often struggle to generate syscall sequences that respect intrinsic Syscall Dependency Relations (SDRs), resulting in seeds that either violate…
LingLanMiDian: Systematic Evaluation of LLMs on TCM Knowledge and Clinical Reasoning
Rui Hua, Yu Wei, Zixin Shu +33
Large language models (LLMs) are advancing rapidly in medical NLP, yet Traditional Chinese Medicine (TCM) with its distinctive ontology, terminology, and reasoning patterns require…
Overton Pluralistic Reinforcement Learning for Large Language Models
Yu Fu, Seongho Son, Ilija Bogunovic
Existing alignment paradigms remain limited in capturing the pluralistic nature of human values. Overton Pluralism addresses this gap by generating responses with diverse perspecti…
Jet Energy-Energy Correlator in Cold QCD Matter
Yu Fu, Berndt Müller, Chathuranga Sirimanna
We present a study of medium-induced modifications to the energy-energy correlator (EEC) for jets in cold nuclear matter. For electron-nucleus collisions, at leading order in the Q…
A Survey of Reinforcement Learning for Large Reasoning Models
Kaiyan Zhang, Yuxin Zuo, Bingxiang He +36
In this paper, we survey recent advances in Reinforcement Learning (RL) for reasoning with Large Language Models (LLMs). RL has achieved remarkable success in advancing the frontie…
Isogeny classes of non-simple abelian surfaces over finite fields
Yu Fu
Let be a principally polarized almost ordinary split abelian surface over a finite field . We give asymptotic upper and lower bounds on the numb…
Reducing the gap between streaming and non-streaming Transducer-based ASR by adaptive two-stage knowledge distillation
Haitao Tang, Yu Fu, Lei Sun +8
Transducer is one of the mainstream frameworks for streaming speech recognition. There is a performance gap between the streaming and non-streaming transducer models due to limited…
Thermalization of weakly coupled non-Abelian plasmas at next-to-leading order
Yu Fu, Jacopo Ghiglieri, Shahin Iqbal +1
We employ the QCD kinetic theory, including next-to-leading(NLO) order corrections in coupling constant, to study the evolution of weakly coupled non-Abelian plasmas towards therma…
Deep Model with Siamese Network for Viability and Necrosis Tumor Assessment in Osteosarcoma
Yu Fu
Osteosarcoma is the most common primary malignant bone tumor, which has high mortality due to easy lung metastasis. Osteosarcoma is a highly anaplastic, pleomorphic tumor with a va…
Bilinear magnetoresistance in HgTe topological insulator: opposite signs at opposite interfaces demonstrated by gate control
Yu Fu, Jing Li, Jules Papin +12
Spin-orbit effects appearing in topological insulators (TI) and at Rashba interfaces are currently revolutionizing how we can manipulate spins and have led to several newly discove…
On triharmonic hypersurfaces in space forms
Yu Fu, Dan Yang
In this paper we study triharmonic hypersurfaces immersed in a space form . We prove that any proper CMC triharmonic hypersurface in the sphere has co…
CalBrief: A Pilot Diagnostic Benchmark for Evidence-Calibrated Scientific Briefing with Large Language Models
Yu Fu, Yongqi Kang, Yong Zhao
Large language models (LLMs) are increasingly used as research assistants, yet it remains unclear whether they can calibrate research takeaways to the strength and scope of the sup…
PET-F2I: A Comprehensive Benchmark and Parameter-Efficient Fine-Tuning of LLMs for PET/CT Report Impression Generation
Yuchen Liu, Wenbo Zhang, Liling Peng +6
PET/CT imaging is pivotal in oncology and nuclear medicine, yet summarizing complex findings into precise diagnostic impressions is labor-intensive. While LLMs have shown promise i…
DATAWEAVER: Authoring Data-Driven Narratives through the Integrated Composition of Visualization and Text
Yu Fu, Dennis Bromley, Vidya Setlur
Data-driven storytelling has gained prominence in journalism and other data reporting fields. However, the process of creating these stories remains challenging, often requiring th…
Color Glass Condensate meets High Twist Expansion
Yu Fu, Zhong-Bo Kang, Farid Salazar +2
We establish the correspondence between two well-known frameworks for QCD multiple scattering in nuclear media: the Color Glass Condensate (CGC) and the High-Twist (HT) expansion f…
Modification of the Jet Energy-Energy Correlator in Cold Nuclear Matter
Yu Fu, Berndt Müller, Chathuranga Sirimanna
We compute medium corrections to the energy-energy correlator (EEC) for jets in electron-nucleus collisions at leading order in the QCD coupling and the interaction of the jet with…
Spectrum-Energy-Economy Efficiency Trade-off of Wireless Communication Systems with Separated Indoor/Outdoor Scenarios for 5G and B5G
Yu Fu, Cheng-Xiang Wang, Zijun Zhao +1
In this paper, we consider a heterogeneous 5G cellular architecture that separates the outdoor and indoor scenarios and in particular study the trade-off between the spectrum effic…
StepAudio 2.5 Technical Report
Bin Lin, Bo Zhao, Boyong Wu +98
Unified audio-language modeling has emerged as a prominent trend in modern speech systems, promising to bring the reasoning capabilities of large language models to auditory tasks.…
Two-dimensional Cold Electron Transport for Steep-slope Transistors
Maomao Liu, Hemendra Nath Jaiswal, Simran Shahi +10
Room-temperature Fermi-Dirac electron thermal excitation in conventional three-dimensional (3D) or two-dimensional (2D) semiconductors generates hot electrons with a relatively lon…
End-to-End Energy Efficiency Evaluation for B5G Ultra Dense Networks
Yu Fu, Mohammad Dehghani Soltani, Hamada Alshaer +4
Energy efficiency (EE) is a major performance metric for fifth generation (5G) and beyond 5G (B5G) wireless communication systems, especially for ultra dense networks. This paper p…
GRLO: Towards Generalizable Reinforcement Learning in Open-Ended Environments from Zero
Shangjian Yin, Yu Fu, Yue Dong +1
Post-training has become a crucial step for unlocking the capabilities of large language models, with reinforcement learning (RL) emerging as a critical paradigm. Recent RL-based p…
SCP-NL2TL: Selective Conformal Prediction with Semantic Verification for Natural Language to Temporal Logic Specifications
Yixuan Wang, Licheng Luo, Yu Fu +3
Translating natural language instructions into machine-interpretable formal specifications enables robots and autonomous systems to plan, reason, and formally verify their behavior…
SemiSAM-O1: Pushing the Boundary of Annotation-Efficient Medical Image Segmentation with Generalist Knowledge Fusion
Yichi Zhang, Le Xue, Bichun Xu +6
Semi-supervised learning (SSL) has become a promising solution to alleviate the annotation burden of deep learning-based medical image segmentation models. While recent advances in…
Stealthy Malware Traffic - Not as Innocent as It Looks
Xingsi Zhong, Yu Fu, Lu Yu +1
Malware is constantly evolving. Although existing countermeasures have success in malware detection, corresponding counter-countermeasures are always emerging. In this study, a cou…
Network Traffic Anomaly Detection Method Based on Multi scale Residual Feature
Xueyuan Duan, Yu Fu, Kun Wang
To address the problem that traditional network traffic anomaly detection algorithms do not suffi-ciently mine potential features in long time domain, an anomaly detection method b…
OTFPF: Optimal Transport-Based Feature Pyramid Fusion Network for Brain Age Estimation with 3D Overlapped ConvNeXt
Yu Fu, Yanyan Huang, Yalin Wang +6
Chronological age of healthy brain is able to be predicted using deep neural networks from T1-weighted magnetic resonance images (T1 MRIs), and the predicted brain age could serve…
Reducing the Safety Tax in LLM Safety Alignment with On-Policy Self-Distillation
Yu Fu, Longxuan Yu, Haz Sameen Shahgir +4
Safety alignment often improves robustness to harmful queries at the cost of reasoning ability, a tradeoff known as the safety tax. A common cause is distributional mismatch: super…
SFCNeXt: a simple fully convolutional network for effective brain age estimation with small sample size
Yu Fu, Yanyan Huang, Shunjie Dong +4
Deep neural networks (DNN) have been designed to predict the chronological age of a healthy brain from T1-weighted magnetic resonance images (T1 MRIs), and the predicted brain age…
Magnetic phase transitions in Ta/CoFeB/MgO multilayers
I. Barsukov, Yu Fu, C. Safranski +8
We study thin films and magnetic tunnel junction nanopillars based on Ta/CoFeB/MgO multilayers by electrical transport and magnetometry measurements. These mea…
BER Performance of Spatial Modulation Systems Under a Non-Stationary Massive MIMO Channel Model
Yu Fu, Cheng-Xiang Wang, Xuming Fang +2
In this paper, the bit error rate (BER) performance of spatial modulation (SM) systems is investigated both theoretically and by simulation in a non-stationary Kronecker-based mass…
ECHO: Explainable Co-editing with Human-in-the-loop Operations for Presentation Refinement
Yu Fu, Yongqi Kang, Yujia Zhou +1
Authoring and refining presentation slides is a highly time-consuming core task in academic and business domains. While generative AI tools have lowered the barrier for creating in…
-Scene: Physically Grounded Image-to-3D Scene Reconstruction
Haodong Li, Lulu Shao, Haolin Lu +4
Reconstructing compositional 3D scenes from a single image is a fundamental challenge in 3D world modeling. Recent methods can recover high-fidelity, complete 3D objects and predic…
The biharmonic hypersurface flow and the Willmore flow in higher dimensions
Yu Fu, Min-Chun Hong, Gang Tian
The biharmonic flow of hypersurfaces immersed in the Euclidean space for is given by a fourth order geometric evolution equation, which is simil…
D-Judge: Disrupting Multi-Turn Jailbreaks using Semantics-Preserving Output Rewriting
Huanli Gong, Zhipeng Wei, Yu Fu +4
Multi-turn jailbreak attacks pose a growing threat to large language model (LLM) safety because they exploit feedback from auxiliary judge models to iteratively refine prompts towa…
Euler characteristics of the generalized Kloosterman sheaves for symplectic and orthogonal groups
Yu Fu, Miao Pam Gu
We study the monodromy of certain -adic local systems attached to the generalized Kloosterman sheaves constructed by Yun and calculate their Euler characteristics under stand…
ConSlide: Asynchronous Hierarchical Interaction Transformer with Breakup-Reorganize Rehearsal for Continual Whole Slide Image Analysis
Yanyan Huang, Weiqin Zhao, Shujun Wang +3
Whole slide image (WSI) analysis has become increasingly important in the medical imaging community, enabling automated and objective diagnosis, prognosis, and therapeutic-response…
Artificial Intelligence Security Competition (AISC)
Yinpeng Dong, Peng Chen, Senyou Deng +49
The security of artificial intelligence (AI) is an important research area towards safe, reliable, and trustworthy AI systems. To accelerate the research on AI security, the Artifi…
Asymmetric transverse momentum broadening in an inhomogeneous medium
Yu Fu, Jorge Casalderrey-Solana, Xin-Nian Wang
Gradient jet tomography in high-energy heavy-ion collisions utilizes the asymmetric transverse momentum broadening of a propagating parton in an inhomogeneous medium. Such broadeni…
X-MADAM-RAG: Diagnosing and Handling Chinese-English Evidence Conflict in Retrieval-Augmented Generation
Yongqi Kang, Yu Fu, Yong Zhao
Retrieval-augmented generation (RAG) systems may receive evidence that is not merely noisy but mutually contradictory. This issue becomes particularly salient in multilingual setti…
When Correct Edges Cannot Be Verified: A Provenance Gap in Incomplete KGQA and a Provenance-Favoring Completion Policy
Yongqi Kang, Yu Fu, Yong Zhao
Incomplete Knowledge Graph Question Answering (IKGQA) requires completing missing edges to continue reasoning. A growing line of work verifies completed edges against retrieved tex…
Vector Copula Variational Inference and Dependent Block Posterior Approximations
Yu Fu, Michael Stanley Smith, Anastasios Panagiotelis
The key to VI is the selection of a tractable density to approximate the Bayesian posterior. For large and complex models a common choice is to assume independence between multivar…
SemiSAM+: Rethinking Semi-Supervised Medical Image Segmentation in the Era of Foundation Models
Yichi Zhang, Bohao Lv, Le Xue +5
Deep learning-based medical image segmentation typically requires large amount of labeled data for training, making it less applicable in clinical settings due to high annotation c…
Studying the divisibility of power LCM matrics by power GCD matrices on gcd-closed sets
Jianrong Zhao, Chenxu Wang, Yu Fu
Let be a gcd-closed set (i.e. for all ). In 2002, Hong proposed the divisibility problem of characterizing all gcd-closed s…
Do Reasoning LLMs Refuse What They Infer in Long Contexts?
Yu Fu, Haz Sameen Shahgir, Huanli Gong +3
Long-context LLMs can infer objectives that are not stated explicitly. This capability is useful for reasoning over documents, code, retrieved evidence, and tool traces, but it als…
SSRL: Self-Search Reinforcement Learning
Yuchen Fan, Kaiyan Zhang, Heng Zhou +15
We investigate the potential of large language models (LLMs) to serve as efficient simulators for agentic search tasks in reinforcement learning (RL), thereby reducing dependence o…
Precise Reduction of Solar Spectra Observed by the 1-meter New Vacuum Solar Telescope
Yunfang Cai, Zhi Xu, Zhenggang Li +4
We present a precise and complete procedure for processing spectral data observed by the 1-meter New Vacuum Solar Telescope (NVST). The procedure is suitable for both the sit-and-s…
HDNet: Hierarchical Dynamic Network for Gait Recognition using Millimeter-Wave Radar
Yanyan Huang, Yong Wang, Kun Shi +4
Gait recognition is widely used in diversified practical applications. Currently, the most prevalent approach is to recognize human gait from RGB images, owing to the progress of c…
Biharmonic hypersurfaces in a product space
Yu Fu, Shun Maeta, Ye-Lin Ou
In this paper, we study biharmonic hypersurfaces in a product of an Einstein space and a real line. We prove that a biharmonic hypersurface with constant mean curvature in such a p…
Composing Method for the Two-dimensional Scanning Spectra Observed by the New Vacuum Solar Telescope
Yun-Fang Cai, Zhi Xu, Yu-Chao Chen +4
In this paper we illustrate the technique used by the New Vacuum Solar Telescope to increase the spatial resolution of two-dimensional (2D) solar spectroscopy observation involving…
Dynamics of Irreversible Particle Adsorption to Fluid Interfaces
Marina Pasquet, Yu Fu, Joelle Frechette
Understanding the dynamic adsorption of colloidal particles at fluid interfaces is essential for applications ranging from emulsion stabilization to interfacial assembly of functio…
PhaseAware: Interpretable Human-in-the-Loop Rehabilitation Scoring with Boundary Monitoring
Yankai Zheng, Yuhe Liu, Yuxin Ma +8
Rehabilitation scoring systems are most useful when their outputs can be reviewed and interpreted within clinical workflows. This study presents PhaseAware, a compact framework for…
Safety Alignment in NLP Tasks: Weakly Aligned Summarization as an In-Context Attack
Yu Fu, Yufei Li, Wen Xiao +2
Recent developments in balancing the usefulness and safety of Large Language Models (LLMs) have raised a critical question: Are mainstream NLP tasks adequately aligned with safety…
A New Kind of High-Order Multi-step Schemes for Forward Backward Stochastic Differential Equations
Weidong Zhao, Yu Fu, Tao Zhou
In this work, we concern with the high order numerical methods for coupled forward-backward stochastic differential equations (FBSDEs). Based on the FBSDEs theory, we derive two re…
Abelian varieties with real multiplication: classification and isogeny classes over finite fields
Tejasi Bhatnagar, Yu Fu
In this paper, we provide a classification of certain points on Hilbert modular varieties over finite fields under a mild assumption on Newton polygon. Furthermore, we use this cha…
Diode-like Selective Enhancement of Carrier Transport through Metal-Semiconductor Interface Decorated by Monolayer Boron Nitride
Hemendra Nath Jaiswal, Maomao Liu, Simran Shahi +13
Two-dimensional (2D) semiconductors are promising material candidates for next-generation nanoelectronics. However, there are fundamental challenges related to their metal-semicond…
Deep Decomposition Network for Image Processing: A Case Study for Visible and Infrared Image Fusion
Yu Fu, Xiao-Jun Wu, Josef Kittler
Image decomposition is a crucial subject in the field of image processing. It can extract salient features from the source image. We propose a new image decomposition method based…
Families of isogenous elliptic curves ordered by height
Yu Fu
Given a family of products of elliptic curves over a rational curve defined over a number field , and assuming that there exists no isogeny between the pair of elliptic curves i…
Inducing superconductivity in quantum anomalous Hall regime
Yu Huang, Yu Fu, Peng Zhang +2
Interfacing the quantum anomalous Hall insulator with a conventional superconductor is known to be a promising manner for realizing a topological superconductor, which has been con…
Watermarking Conditional Text Generation for AI Detection: Unveiling Challenges and a Semantic-Aware Watermark Remedy
Yu Fu, Deyi Xiong, Yue Dong
To mitigate potential risks associated with language models, recent AI detection research proposes incorporating watermarks into machine-generated text through random vocabulary re…
On Chen's biharmonic conjecture for hypersurfaces in
Yu Fu, Min-Chun Hong, Xin Zhan
A longstanding conjecture on biharmonic submanifolds, proposed by Chen in 1991, is that {\it any biharmonic submanifold in a Euclidean space is minimal}. In the case of a hypersurf…
Biharmonic hypersurfaces with three distinct principal curvatures in spheres
Yu Fu
We obtain a complete classification of proper biharmonic hypersurfaces with at most three distinct principal curvatures in sphere spaces with arbitrary dimension. Precisely, togeth…
Efficient spectral sparse grid approximations for solving multi-dimensional forward backward SDEs
Yu Fu, Weidong Zhao, Tao Zhou
This is the second part in a series of papers on multi-step schemes for solving coupled forward backward stochastic differential equations (FBSDEs). We extend the basic idea in our…
The exceptional set for Diophantine inequality with mixed powers of primes
Yu Fu, Linzhu Fu, Liqun Hu
Assume that are non-zero real numbers , is an irrational number. Let be a well-spaced sequence, and . For an…
Evaluating and Enhancing Large Language Models Performance in Domain-specific Medicine: Osteoarthritis Management with DocOA
Xi Chen, MingKe You, Li Wang +7
The efficacy of large language models (LLMs) in domain-specific medicine, particularly for managing complex diseases such as osteoarthritis (OA), remains largely unexplored. This s…
Meta-RTL: Reinforcement-Based Meta-Transfer Learning for Low-Resource Commonsense Reasoning
Yu Fu, Jie He, Yifan Yang +2
Meta learning has been widely used to exploit rich-resource source tasks to improve the performance of low-resource target tasks. Unfortunately, most existing meta learning approac…
On the biharmonic hypersurfaces with three distinct principal curvatures in space forms
Åtefan Andronic, Yu Fu, Cezar Oniciuc
In [16] there was proved that any biharmonic hypersurface with at most three distinct principal curvatures in space forms has constant mean curvature. At the very last step of the…
MOSAIC: A Unified Platform for Cross-Paradigm Comparison and Evaluation of Homogeneous and Heterogeneous Multi-Agent RL, LLM, VLM, and Human Decision-Makers
Abdulhamid M. Mousa, Yu Fu, Rakhmonberdi Khajiev +5
Reinforcement learning (RL), large language models (LLMs), and vision-language models (VLMs) have been widely studied in isolation. However, existing infrastructure lacks the abili…
TRAWL: Tensor Reduced and Approximated Weights for Large Language Models
Yiran Luo, Het Patel, Yu Fu +4
Recent research has shown that pruning large-scale language models for inference is an effective approach to improving model efficiency, significantly reducing model weights with m…
Using Markov Models and Statistics to Learn, Extract, Fuse, and Detect Patterns in Raw Data
Richard R. Brooks, Lu Yu, Yu Fu +3
Many systems are partially stochastic in nature. We have derived data driven approaches for extracting stochastic state machines (Markov models) directly from observed data. This c…
Frontis-MA1: Training an AI4AI Model towards Recursive Self-Improvement in Machine Learning Engineering
Junlin Yang, Che Jiang, Yu Fu +21
The paper presents Frontis-MA1, a 35‑billion‑parameter model trained as a meta‑evolution agent for machine learning engineering, using a new OpenMLE stack that combines operator le…
Complete classification of biconservative hypersurfaces with diagonalizable shape operator in Minkowski 4-space
Yu Fu, Nurettin Cenk Turgay
In this paper, we study biconservative hypersurfaces in the four dimensional Minkowski space . We give the complete explicit classification of biconservative hypersu…
Open heavy-flavor transport and hadronization in heavy-ion collisions
Yu Fu, Tharun Krishna, Weiyao Ke +2
We develop a comprehensive model for heavy-quark evolution in a realistic QGP, from their production in the initial collision to hadronic freeze-out. Heavy-quark transport is descr…
A resource-efficient deep learning framework for low-dose brain PET image reconstruction and analysis
Yu Fu, Shunjie Dong, Yi Liao +7
18F-fluorodeoxyglucose (18F-FDG) Positron Emission Tomography (PET) imaging usually needs a full-dose radioactive tracer to obtain satisfactory diagnostic results, which raises con…
VLMs Need Words: Vision Language Models Ignore Visual Detail In Favor of Semantic Anchors
Haz Sameen Shahgir, Xiaofu Chen, Yu Fu +4
Vision-language models (VLMs) have achieved impressive performance across a wide range of multimodal tasks. However, they often fail on tasks that require fine-grained visual perce…