wovepaper — the arXiv observatory

The paper introduces a federated learning approach for constructing non‑parametric cumulative incidence curves for competing risks without sharing patient‑level data, and applies i…

#federated learning#competing risks#cumulative incidence curves#post-market safety surveillance

cs.CV2020

Deformation Flow Based Two-Stream Network for Lip Reading

Jingyun Xiao, Shuang Yang, Yuanhang Zhang +2

Publications (90)

Synchronous Bidirectional Learning for Multilingual Lip Reading

STARK: Strategic Team of Agents for Refining Kernels

CoFiRec: Coarse-to-Fine Tokenization for Generative Recommendation

Mutual Information Maximization for Effective Lip Reading

Multimodal Recommendation via Self-Corrective Preference Alignmen

Nonlinear Projection Based Gradient Estimation for Query Efficient Blackbox Attacks

Foresight Prediction Enhanced Live-Streaming Recommendation

SAIL-Embedding Technical Report: Omni-modal Embedding Foundation Model

LLM-Alignment Live-Streaming Recommendation

Pseudo-Convolutional Policy Gradient for Sequence-to-Sequence Lip-Reading

FARM: Frequency-Aware Model for Cross-Domain Live-Streaming Recommendation

Planar Embedding of Okamura-Seymour Quasimetrics in Polynomial Time with an Application to Distributed SSSP

Learning Separable Hidden Unit Contributions for Speaker-Adaptive Lip-Reading

ARMs: Adaptive Red-Teaming Agent against Multimodal Models with Plug-and-Play Attacks

Unpaired Multi-domain Attribute Translation of 3D Facial Shapes with a Square and Symmetric Geometric Map

Moment&Cross: Next-Generation Real-Time Cross-Domain CTR Prediction for Live-Streaming Recommendation at Kuaishou

Zinc-blende and wurtzite GaAs quantum dots in nanowires studied using hydrostatic pressure

AutoRedTeamer: Autonomous Red Teaming with Lifelong Attack Integration

From Agnostic to Specific: Latent Preference Diffusion for Multi-Behavior Sequential Recommendation

Optimizing Electric Carsharing System Operations and Battery Management: Integrating V2G, B2G and Battery Swapping Strategies

Industrial Scale Privacy Preserving Deep Neural Network

Unifying Generative Recall and Multi-Objective Ranking in a Single Decoder-Only Sequence

Solving Billion-Scale Knapsack Problems

High-Precision Calibration Workflow Achieves Above 99.9% CZ Gate Fidelity on a Scalable Superconducting Processor

QARM V2: Quantitative Alignment Multi-Modal Recommendation for Reasoning User Sequence Modeling

ArchPilot: A Proxy-Guided Multi-Agent Approach for Machine Learning Engineering

OneLive: Dynamically Unified Generative Framework for Live-Streaming Recommendation

Optimal Bounds for Spanners and Tree Covers in Doubling Metrics

On the Equivalence Between Auto-Regressive Next Token Prediction and Full-Item-Vocabulary Maximum Likelihood Estimation in Generative Recommendation--A Short Note

Tile Networks: Learning Optimal Geometric Layout for Whole-page Recommendation

Privacy Preserving PCA for Multiparty Modeling

Reward Guided Decoding for Generative Recommendation

UniRec: Unified Multimodal Encoding for LLM-Based Recommendations

Cooperative Dual Attention for Audio-Visual Speech Enhancement with Facial Cues

Global-guided Focal Neural Radiance Field for Large-scale Scene Rendering

Accurate Nuclear Segmentation with Center Vector Encoding

Progressive-Scale Boundary Blackbox Attack via Projective Gradient Estimation

Learning to Schedule DAG Tasks

QEBA: Query-Efficient Boundary-Based Blackbox Attack

UniCon+: ICTCAS-UCAS Submission to the AVA-ActiveSpeaker Task at ActivityNet Challenge 2022

MyPortrait: Morphable Prior-Guided Personalized Portrait Generation

SafeVision: Efficient Image Guardrail with Robust Policy Adherence and Explainability

OneRec Technical Report

Contour-Variable Model of Constitutive Equations for Polymer Melts

Generating Natural Language Adversarial Examples on a Large Scale with Generative Models

Pantheon: Personalized Multi-objective Ensemble Sort via Iterative Pareto Policy Optimization

LRW-1000: A Naturally-Distributed Large-Scale Benchmark for Lip Reading in the Wild

Realization of high-fidelity perfect entangler between remote superconducting quantum processors

Model-based Constrained MDP for Budget Allocation in Sequential Incentive Marketing

ExpGraph: Model-Agnostic Experience Learning with Graph-Structured Memory for LLM Agents

UDora: A Unified Red Teaming Framework against LLM Agents by Dynamically Hijacking Their Own Reasoning

ExpWeaver: LLM Agents Learn from Experience via Latent RAG

Ads Supply Personalization via Doubly Robust Learning

AgentX: Towards Agent-Driven Self-Iteration of Industrial Recommender Systems

A Unified Framework for Cross-Domain Recommendation

RecoReward: Recommender-Guided Multimodal Description Generation for Recommendation

Bandit Samplers for Training Graph Neural Networks

Uncovering Insurance Fraud Conspiracy with Network Learning

Learning Speaker-Invariant Visual Features for Lipreading

R1-Ranker: Teaching LLM Rankers to Reason

Secret Sharing based Secure Regressions with Applications

A Practical Distributed ADMM Solver for Billion-Scale Generalized Assignment Problems

A Semi-supervised Graph Attentive Network for Financial Fraud Detection

MemReward: Graph-Based Experience Memory for LLM Reward Prediction with Limited Labels

Breaking the Curse of Quality Saturation with User-Centric Ranking

SenseNova-U1: Unifying Multimodal Understanding and Generation with NEO-unify Architecture

GLip: A Global-Local Integrated Progressive Framework for Robust Visual Speech Recognition

Enhancing Embedding Representation Stability in Recommendation Systems with Semantic ID

UniCon: Unified Context Network for Robust Active Speaker Detection

LRanker: LLM Ranker for Massive Candidates

SARM: LLM-Augmented Semantic Anchor for End-to-End Live-Streaming Ranking

Signet Ring Cell Detection With a Semi-supervised Learning Framework

Probabilistic Residual Learning for Online Recommendations

Characterizing Attacks on Deep Reinforcement Learning

Session-Level Dynamic Ad Load Optimization using Offline Robust Reinforcement Learning

You Only Search Once: A Fast Automation Framework for Single-Stage DNN/Accelerator Co-design

Learning (Re-)Starting Solutions for Vehicle Routing Problems

Unified Semantic and ID Representation Learning for Deep Recommenders

Cosmic-ray-induced correlated errors in superconducting qubit array

High-Precision Calibration Workflow Achieves Above $99.9%$ CZ Gate Fidelity on a Scalable Superconducting Processor