wovepaper — the arXiv observatory

The paper studies how the choice of solver affects the success of randomness‑leakage attacks on the lattice‑based signature scheme ML‑DSA, providing a unified framework to evaluate…

#lattice-based signatures#randomness leakage#ILWE attacks#key recovery

astro-ph.CO2021

A new way to test the WIMP dark matter models

Wei Cheng, Yuan He, Jin-Wang Diao +3

cs.LG2025

xTime: Extreme Event Prediction with Hierarchical Knowledge Distillation and Expert Fusion

Quan Li, Wenchao Yu, Suhang Wang +4

cs.CV2023

MonoHuman: Animatable Human Neural Field from Monocular Video

Zhengming Yu, Wei Cheng, Xian Liu +2

astro-ph.CO2026

Effective Bayesian ranking of low order monomial potentials in low temperature warm inflation

Xin Peng, Xiang Cheng, Wei Cheng +3

cs.IR2026

OneMall: One Architecture, More Scenarios -- End-to-End Generative Recommender Family at Kuaishou E-Commerce

Kun Zhang, Jingming Zhang, Wei Cheng +29

cs.LG2017

FWDA: a Fast Wishart Discriminant Analysis with its Application to Electronic Health Records Data Classification

Haoyi Xiong, Wei Cheng, Wenqing Hu +2

math.FA2020

Monotone iterative schemes for positive solutions of a fractional differential system with integral boundary conditions on an infinite interval

Yaohong Li, Wei Cheng, Jiafa Xu

cs.IT2023

Integrated Sensing and Communication based Outdoor Multi-Target Detection, Tracking and Localization in Practical 5G Networks

Ruiqi Liu, Mengnan Jian, Dawei Chen +4

math.AP2014

Homoclinic orbits and critical points of barrier functions

Piermarco Cannarsa, Wei Cheng

cs.SE2026

Bootstrapping Code Translation with Weighted Multilanguage Exploration

Yuhan Wu, Huan Zhang, Wei Cheng +3

cs.CR2026

Insecure Coding Preferences in Long-Term Memory: Security Risks for LLM-based Code Generation

Yuchen Chen, Wei Cheng, Yuan Xiao +7

cs.CL2022

Zero-Shot Cross-Lingual Machine Reading Comprehension via Inter-sentence Dependency Graph

Liyan Xu, Xuchao Zhang, Bo Zong +6

cs.AI2026

Bridging Inference-Time Scaling and Episodic Memory with Action-Centric Graphs

Xu Zheng, Chaohao Lin, Zhuomin Chen +4

The paper introduces GAMER, a graph‑based action‑centric memory system that stores past reasoning as a dynamic graph and uses temporal‑difference learning to estimate action values…

#inference scaling#episodic memory#graph-based memory#temporal difference learning

math.AP2026

Recent progress in generalized Hamiltonian gradient flow: Singularities

Wei Cheng, Jiahui Hong

cs.LG2017

A Dual-Stage Attention-Based Recurrent Neural Network for Time Series Prediction

Yao Qin, Dongjin Song, Haifeng Chen +3

hep-ph2022

Reheating constraints on modified single-field Natural Inflation models

Hua Zhou, Qing Yu, Yu Pan +2

cs.CL2025

Baichuan-M1: Pushing the Medical Capability of Large Language Models

Bingning Wang, Haizhou Zhao, Huozhi Zhou +39

math.CO2022

Self-dual Hadamard bent sequences

Minjia Shi, Yaya Li, Wei Cheng +3

hep-ph2018

From inflation to cosmological electroweak phase transition with a complex scalar singlet

Wei Cheng, Ligong Bian

hep-ph2023

Non-minimal Coupling Inflation and Dark Matter under the $\mathbb{Z}_{3}$ Symmetry

Wei Cheng, Xuewen Liu, Ruiyu Zhou

math.AP2025

Singularities and their propagation in optimal transport

Piermarco Cannarsa, Wei Cheng, Tianqi Shi +1

hep-ph2018

The asymmetries of the $B \to K^* Î¼^+ Î¼^-$ decay and the search of new physics beyond the Standard Model

Hai-Bing Fu, Xing-Gang Wu, Wei Cheng +2

cs.CL2025

MixLLM: Dynamic Routing in Mixed Large Language Models

Xinyuan Wang, Yanchi Liu, Wei Cheng +5

hep-ph2019

Higgs inflation and cosmological electroweak phase transition with N scalars in the post-Higgs era

Wei Cheng, Ligong Bian

hep-ph2018

The longitudinal leading-twist distribution amplitude of $J/Ï$ meson within background field theory

Hai-Bing Fu, Long Zeng, Wei Cheng +2

cs.CV2025

RegionE: Adaptive Region-Aware Generation for Efficient Image Editing

Pengtao Chen, Xianfang Zeng, Maosen Zhao +7

cs.CL2023

Exploring the Limits of ChatGPT for Query or Aspect-based Text Summarization

Xianjun Yang, Yan Li, Xinlu Zhang +2

cs.LG2026

FinAbstain: Uncertainty-Calibrated Multimodal RAG for Selective Financial Forecasting

Dorothy Torres, Wei Cheng, Henan Huang

cs.CV2026

ShutterMuse: Capture-Time Photography Guidance with MLLMs

Jiayu Li, Yixiao Fang, Tianyu Hu +5

hep-ph2018

The $B \to Ï$ helicity form factors within the QCD light-cone sum rules

Wei Cheng, Xing-Gang Wu, Rui-Yu Zhou +1

eess.SY2026

Agentic AI for Scalable and Robust Optical Systems Control

Zehao Wang, Mingzhe Han, Wei Cheng +12

cs.CV2023

RenderMe-360: A Large Digital Asset Library and Benchmarks Towards High-fidelity Head Avatars

Dongwei Pan, Long Zhuo, Jingtan Piao +13

Publications (242)

DNA-GPT: Divergent N-Gram Analysis for Training-Free Detection of GPT-Generated Text

Constraints on real scalar inflation from preheating of LATTICEEASY

Learning to Drop: Robust Graph Neural Network via Topological Denoising

Weak KAM approach to first-order Mean Field Games with state constraints

Rise From The Ashes: LLM-based Static Analysis for Deep Learning Framework Bugs

PAC Learnability under Explanation-Preserving Graph Perturbations

DALD: Improving Logits-based Detector without Logits from Black-box LLMs

Gravitational Waves from Higgs Preheating after Inflaton $Z_2$-Symmetry Breaking

The $D\to Ï$ semileptonic and radiative decays within the light-cone sum rules

Spatio-temporal Granger causality: a new framework

Optimal transport in the frame of abstract Lax-Oleinik operator revisited

Pruning as a Domain-specific LLM Extractor

Open-ended Commonsense Reasoning with Unrestricted Answer Scope

Experimental test of the Jarzynski equality in a single spin-1 system using high-fidelity single-shot readouts

FreeStyle: Free Control of Style-Content Dual-Reference Generation from Community LoRA Mining

Parameterized Explainer for Graph Neural Network

FACESEC: A Fine-grained Robustness Evaluation Framework for Face Recognition Systems

Qualitative Estimates of Topological Entropy for Non-Monotone Contact Lax-Oleinik Semiflow

KV Shifting Attention Enhances Language Modeling

Experimental violation of the Leggett-Garg inequality with a single-spin system

FAVOR-Bench: A Comprehensive Benchmark for Fine-Grained Video Motion Understanding

PrivacyMind: Large Language Models Can Be Contextual Privacy Protection Learners

Variational construction of singular characteristics and propagation of singularities

Dark matter production accompanied by gravitational wave signals during cosmological phase transitions

Scattered Forest Search: Smarter Code Space Exploration with LLMs

DeepSieve: Information Sieving via LLM-as-a-Knowledge-Router

TrustAgent: Towards Safe and Trustworthy LLM-based Agents

Increased Coupling in the Saliency Network is the main cause/effect of Attention Deficit Hyperactivity Disorder

Observation of hierarchy of Hilbert space ergodicities in the quantum dynamics of a single spin

OmniSVG: A Unified Scalable Vector Graphics Generation Model

Harnessing Vision Models for Time Series Analysis: A Survey

Topology of singular set of semiconcave function via Arnaud's theorem

The ratio $\mathcal{R}(D_s)$ for $B_s \to D_s \ellÎ½_\ell$ by using the QCD light-cone sum rules within the framework of heavy quark effective field theory

Insight from NLP Analysis: COVID-19 Vaccines Sentiments on Social Media

Vanishing contact structure problem and convergence of the viscosity solutions

Structure-Aware RAG: Structured Retrieval Augmented Generation from Noisy Data for Conversational Agents

Electroweak phase transition and Higgs phenomenology in the Georgi-Machacek model

$B_{(s)} \to S(a_0(1450), K_0^*(1430), f_0(1500))$ helicity form factors within QCD light-cone sum rules

MIITA: Memory-Induced Inference-Time Adaptation for Continual Learning with Small Language Models

Skilled AI Agents for Embedded and IoT Systems Development

Revisiting the production of $J/Ï+Î·_c$ via the $e^+e^-$ annihilation within the QCD light-cone sum rules

EPIC: Abstraction and Polymorphism of In-Network Collectives on Ethernet

Branching fractions and polarizations of $D\to V(Ï,Ï, K^*) \ell Î½_\ell$ within QCD LCSR

POND: Multi-Source Time Series Domain Adaptation with Information-Aware Prompt Tuning

Comparison of Effective Dissipation Channels in Warm Higgs Inflation from Warm Background Evolution

ReasonEdit: Towards Reasoning-Enhanced Image Editing Models

Generalizing Variational Autoencoders with Hierarchical Empirical Bayes

Explainable AML Triage with LLMs: Evidence Retrieval and Counterfactual Checks

Leveraging Large Self-Supervised Time-Series Models for Transferable Diagnosis in Cross-Aircraft Type Bleed Air System

Topological and control theoretic properties of Hamilton-Jacobi equations via Lax-Oleinik commutators

Dynamic and asymptotic behavior of singularities of certain weak KAM solutions on the torus

Coupled Hierarchical Search over Topology and Execution for Agentic Workflow Synthesis

The $B\to Ï\ellÎ½_\ell$ semileptonic decay within the LCSR approach under heavy quark effective field theory

Dynamic Prompting: A Unified Framework for Prompt Tuning

Skill Disentanglement for Imitation Learning from Suboptimal Demonstrations

Global generalized characteristics for the Dirichlet problem for Hamilton-Jacobi equations at a supercritical energy level

ChorusCVR: Chorus Supervision for Entire Space Post-Click Conversion Rate Modeling

Attacking Masked Cryptographic Implementations: Information-Theoretic Bounds

InfuserKI: Enhancing Large Language Models with Knowledge Graphs via Infuser-Guided Knowledge Integration

Maximal Leakage of Masked Implementations Using Mrs. Gerber's Lemma for Min-Entropy

RealRestorer: Towards Generalizable Real-World Image Restoration with Large-Scale Image Editing Models

Mastering Long-Tail Complexity on Graphs: Characterization, Learning, and Generalization

Less is More: Towards Green Code Large Language Models via Unified Structural Pruning

Recommend for a Reason: Unlocking the Power of Unsupervised Aspect-Sentiment Co-Extraction

Native 3D Editing with Full Attention

Conflict-aware Inference of Python Compatible Runtime Environments with Domain Knowledge Graph

Local singular characteristics on $\mathbb{R}^2$

From Regression to Prior-Aware Inference: Solving the ILWE Family in Randomness Leakage Attacks against ML-DSA

A new way to test the WIMP dark matter models

xTime: Extreme Event Prediction with Hierarchical Knowledge Distillation and Expert Fusion

MonoHuman: Animatable Human Neural Field from Monocular Video

Effective Bayesian ranking of low order monomial potentials in low temperature warm inflation

OneMall: One Architecture, More Scenarios -- End-to-End Generative Recommender Family at Kuaishou E-Commerce

FWDA: a Fast Wishart Discriminant Analysis with its Application to Electronic Health Records Data Classification

Monotone iterative schemes for positive solutions of a fractional differential system with integral boundary conditions on an infinite interval

Integrated Sensing and Communication based Outdoor Multi-Target Detection, Tracking and Localization in Practical 5G Networks

Homoclinic orbits and critical points of barrier functions

Bootstrapping Code Translation with Weighted Multilanguage Exploration

Insecure Coding Preferences in Long-Term Memory: Security Risks for LLM-based Code Generation

The $D\to Ï$ semileptonic and radiative decays within the light-cone sum rules

Revisiting the production of $J/Ï+Î·_c$ via the $e^+e^-$ annihilation within the QCD light-cone sum rules

Branching fractions and polarizations of $D\to V(Ï,Ï, K^*) \ell Î½_\ell$ within QCD LCSR

The $B\to Ï\ellÎ½_\ell$ semileptonic decay within the LCSR approach under heavy quark effective field theory

The longitudinal leading-twist distribution amplitude of $J/Ï$ meson within background field theory

The $B \to Ï$ helicity form factors within the QCD light-cone sum rules