← Authors

Xiao Zhang

122 papers · 2016–2026 · 19 conferences · across top CS/AI conferences

Achievements

πŸ—ΊοΈ Taxonomy Completionist (29) 🧭 Keyword Pioneer 🐝 Cross-Pollinator (13) πŸƒ Academic Marathon (9) 🌍 Conference Polyglot (19) 🌈 Renaissance Researcher (7) πŸŒ‰ Interdisciplinary Bridge 🐣 Hot Topic Early Bird 🀝 Dynamic Duo (11) πŸ‘‘ Triple Crown πŸ† Grand Slam πŸ‘₯ Mega-Team (34) πŸ”¬ Deep Specialist (16) πŸ† Keyword Champion (4) πŸš€ Conference Pioneer ⚑ Prolific Year (12) πŸ”₯ Unstoppable (10) πŸ—ƒοΈ Keyword Collector (82) πŸ“ˆ Trend Setter πŸ’Ž Century Club (119) ❓ The Questioner (3)

Conferences

AAAI (18) ICML (13) NIPS (11) ICLR (11) IJCAI (10) ACL (10) CVPR (8) ICCV (8) COLING (8) EMNLP (5) AISTATS (4) ECCV (3) MICCAI (3) NAACL (3) OSDI (2) SEMEVAL (2) CONLL (1) NSDI (1) WACV (1)

Top co-authors

Jun Xu (11) Ji Wu (10) Quanquan Gu (7) Dan Goldwasser (7) David Evans (7) Michael Maire (5) Yu Qiao (5) Lingxiao Wang (5) Dongxiao Yu (4) hongsheng Li (4)

Research topics

Applications (1) Privacy (1)

Keywords

large language model (9) question answering (6) representation learning (6) regret bound (6) online learning (4) nonconvex optimization (4) reinforcement learning (4) low-rank matrix recovery (4) kernel methods (4) graph neural network (4) semi-supervised learning (4) attention mechanism (3) mutual information (3) self-supervised learning (3) text classification (3) machine reading comprehension (3) gradient descent (3) image generation (3) neural network training (3) text generation (3)

Papers

OPTION: An Online Pricing Strategy for Asynchronous Federated Learning Against Free-Riding Attacks AAAI 2026
DGTF: Cross-Domain Decentralized Graph Learning with Topology-Aware Knowledge Fusion AAAI 2026
TrajAgg: Dual-Scale Feature Aggregation with Hybrid Training for Trajectory Similarity Computation in Free Space AAAI 2026
Reward Mixology: Crafting Hybrid Signals for Reinforcement Learning Driven In-Context Learning EMNLP 2025
Revisiting Chain-of-Thought Prompting: Zero-shot Can Be Stronger than Few-shot EMNLP 2025
Any-SSR: How Recursive Least Squares Works in Continual Learning of Large Language Model ICCV 2025
NullSwap: Proactive Identity Cloaking Against Deepfake Face Swapping ICCV 2025
UPRE: Zero-Shot Domain Adaptation for Object Detection via Unified Prompt and Representation Enhancement ICCV 2025
Similarity = Value? Consultation Value-Assessment and Alignment for Personalized Search EMNLP 2025
Length-Induced Embedding Collapse in PLM-based Models ACL 2025
Safe in Isolation, Dangerous Together: Agent-Driven Multi-Turn Decomposition Jailbreaks on LLMs ACL 2025
Fast Second-Order Online Kernel Learning Through Incremental Matrix Sketching and Decomposition IJCAI 2025
Evaluating LLMs Across Multi-Cognitive Levels: From Medical Knowledge Mastery to Scenario-Based Problem Solving ICML 2025
Generalization Analysis for Controllable Learning ICML 2025
Dimension-Free Adaptive Subgradient Methods with Frequent Directions ICML 2025
Provably Cost-Sensitive Adversarial Defense via Randomized Smoothing ICML 2025
How Distributed Collaboration Influences the Diffusion Model Training? A Theoretical Perspective ICML 2025
PDUDT: Provable Decentralized Unlearning under Dynamic Topologies ICML 2025
Perplexity Trap: PLM-Based Retrievers Overrate Low Perplexity Documents ICLR 2025
ReDeEP: Detecting Hallucination in Retrieval-Augmented Generation via Mechanistic Interpretability ICLR 2025
ACTIVE: Offline Reinforcement Learning via Adaptive Imitation and In-sample $V$-Ensemble ICLR 2025
Offline RL with Smooth OOD Generalization in Convex Hull and its Neighborhood ICLR 2025
Score-based free-form architectures for high-dimensional Fokker-Planck equations ICLR 2025
Reliable and Diverse Evaluation of LLM Medical Knowledge Mastery ICLR 2025
Nested Diffusion Models Using Hierarchical Latent Priors CVPR 2025
IAP: Invisible Adversarial Patch Attack through Perceptibility-Aware Localization and Perturbation Optimization ICCV 2025
PROGRESSOR: A Perceptually Guided Reward Estimator with Self-Supervised Online Refinement ICCV 2025
DiffPAD: Denoising Diffusion-Based Adversarial Patch Decontamination WACV 2025
UCFE: A User-Centric Financial Expertise Benchmark for Large Language Models NAACL 2025
DREAM: Disentangling Risks to Enhance Safety Alignment in Multimodal Large Language Models NAACL 2025
LS-TGNN: Long and Short-Term Temporal Graph Neural Network for Session-Based Recommendation AAAI 2025
Trigger3:Refining Query Correction via Adaptive Model Selector AAAI 2025
An Item Is Worth a Prompt: Versatile Image Editing with Disentangled Control AAAI 2025
TSVC: Tripartite Learning with Semantic Variation Consistency for Robust Image-Text Retrieval AAAI 2025
AdaO2B: Adaptive Online to Batch Conversion for Out-of-Distribution Generalization AAAI 2025
LightPROF: A Lightweight Reasoning Framework for Large Language Model on Knowledge Graph AAAI 2025
Enhancing Elusive Clues in Knowledge Learning by Contrasting Attention of Language Models AAAI 2025
Medical Contrastive Learning of Positive and Negative Mentions MICCAI 2025
Graph-based Neighbor-Aware Network for Gaze-Supervised Medical Image Segmentation MICCAI 2025
Survey on Strategic Mining in Blockchain: A Reinforcement Learning Approach IJCAI 2025
MAPS: Motivation-Aware Personalized Search via LLM-Driven Consultation Alignment ACL 2025
Bone Soups: A Seek-and-Soup Model Merging Approach for Controllable Multi-Objective Generation ACL 2025
FinBen: A Holistic Financial Benchmark for Large Language Models NIPS 2024
Latent Intrinsics Emerge from Training to Relight NIPS 2024
Co-occurrence is not Factual Association in Language Models NIPS 2024
QCAW 1.0: Building a Qatari Corpus of Student Argumentative Writing COLING 2024
Beaver: Practical Partial Snapshots for Distributed Cloud Services OSDI 2024
Gaze-directed Vision GNN for Mitigating Shortcut Learning in Medical Image MICCAI 2024
SciMRC: Multi-perspective Scientific Machine Reading Comprehension COLING 2024
NaMa: Neighbor-Aware Multi-Modal Adaptive Learning for Prostate Tumor Segmentation on Anisotropic MR Images AAAI 2024
Self-Paced Unified Representation Learning for Hierarchical Multi-Label Classification AAAI 2024
G–LIME: Statistical Learning for Local Interpretations of Deep Neural Networks Using Global Priors (Abstract Reprint) AAAI 2024
Resource-Aware Federated Self-Supervised Learning with Global Class Representations NIPS 2024
Effective In-Context Example Selection through Data Compression ACL 2024
Gaining More Insight into Neural Semantic Parsing with Challenging Benchmarks COLING 2024
Conditional Language Learning with Context ICML 2024
Deciphering 'What' and 'Where' Visual Pathways from Spectral Clustering of Layer-Distributed Neural Representations CVPR 2024
Dissecting learning and forgetting in language model finetuning ICLR 2024
Enhancing Parameter-efficient Fine-tuning with Simple Calibration Based on Stable Rank COLING 2024
Integrating View Conditions for Image Synthesis IJCAI 2024
Joint Semantic and Strategy Matching for Persuasive Dialogue EMNLP 2023
PIXIU: A Comprehensive Benchmark, Instruction Dataset and Large Language Model for Finance NIPS 2023
What Distributions are Robust to Indiscriminate Poisoning Attacks for Linear Learners? NIPS 2023
How to Fine-tune the Model: Unified Model Shift and Model Bias Policy Optimization NIPS 2023
Reward Imputation with Sketching for Contextual Batched Bandits NIPS 2023
Bridging The Gap: Entailment Fused-T5 for Open-retrieval Conversational Machine Reading Comprehension ACL 2023
Robust Image Ordinal Regression with Controllable Image Generation IJCAI 2023
Flattened Clos: Designing High-performance Deadlock-free Expander Data Center Networks Using Graph Contraction NSDI 2023
Understanding Intrinsic Robustness Using Label Uncertainty ICLR 2022
Cross-Lingual Phrase Retrieval ACL 2022
ASM2TV: An Adaptive Semi-supervised Multi-Task Multi-View Learning Framework for Human Activity Recognition AAAI 2022
PseudoAugment: Learning to Use Unlabeled Data for Data Augmentation in Point Clouds ECCV 2022
MICO: Selective Search with Mutual Information Co-training COLING 2022
ET5: A Novel End-to-end Framework for Conversational Machine Reading Comprehension COLING 2022
To the Point: Efficient 3D Object Detection in the Range Image With Graph Convolution Kernels CVPR 2021
Refining Pseudo Labels With Clustering Consensus Over Generations for Unsupervised Object Re-Identification CVPR 2021
Rethink the Connections among Generalization, Memorization, and the Spectral Bias of DNNs IJCAI 2021
Regret Bounds for Online Kernel Selection in Continuous Kernel Space AAAI 2021
Modeling Heterogeneous Relations across Multiple Modes for Potential Crowd Flow Prediction AAAI 2021
Multi-Grained Knowledge Distillation for Named Entity Recognition NAACL 2021
Improved Estimation of Concentration Under $\ell_p$-Norm Distance Metrics Using Half Spaces ICLR 2021
RSN: Range Sparse Net for Efficient, Accurate LiDAR 3D Object Detection CVPR 2021
Empirical Studies on the Properties of Linear Regions in Deep Neural Networks ICLR 2020
RBF-Softmax: Learning Deep Representative Prototypes with Radial Basis Function Softmax ECCV 2020
Learning Adversarially Robust Representations via Worst-Case Mutual Information Maximization ICML 2020
Semi-supervised Autoencoding Projective Dependency Parsing COLING 2020
Cross-Lingual Document Retrieval with Smooth Learning COLING 2020
Understanding the Intrinsic Robustness of Image Distributions using Conditional Generative Models AISTATS 2020
Hypothesis Sketching for Online Kernel Selection in Continuous Kernel Space IJCAI 2020
Self-Supervised Visual Representation Learning from Hierarchical Grouping NIPS 2020
Semi-supervised Parsing with a Variational Autoencoding Parser ACL 2020
Thunderbolt: Throughput-Optimized, Quality-of-Service-Aware Power Capping at Scale OSDI 2020
Learning Conceptual-Contextual Embeddings for Medical Text AAAI 2020
Tensor Graph Convolutional Networks for Text Classification AAAI 2020
Empirically Measuring Concentration: Fundamental Limits on Intrinsic Robustness NIPS 2019
An Adaptive Empirical Bayesian Method for Sparse Deep Learning NIPS 2019
Learning One-hidden-layer ReLU Networks via Gradient Descent AISTATS 2019
AttnSense: Multi-level Attention Mechanism For Multimodal Human Activity Recognition IJCAI 2019
AdaCos: Adaptively Scaling Cosine Logits for Effectively Learning Deep Face Representations CVPR 2019
Delta Embedding Learning ACL 2019
Sentiment Tagging with Partial Labels using Modular Architectures ACL 2019
Cost-Sensitive Robustness against Adversarial Examples ICLR 2019
Incremental Randomized Sketching for Online Kernel Learning ICML 2019
P2SGrad: Refined Gradients for Optimizing Deep Face Models CVPR 2019
Normalized Diversification CVPR 2019
SegSort: Segmentation by Discriminative Sorting of Segments ICCV 2019
NetAdapt: Platform-Aware Neural Network Adaptation for Mobile Applications ECCV 2018
A Primal-Dual Analysis of Global Optimality in Nonconvex Low-Rank Matrix Recovery ICML 2018
Online Kernel Selection via Incremental Sketched Kernel Alignment IJCAI 2018
Label-Sensitive Task Grouping by Bayesian Nonparametric Approach for Multi-Task Multi-Label Learning IJCAI 2018
Fast and Sample Efficient Inductive Matrix Completion via Multi-Phase Procrustes Flow ICML 2018
A Unified Framework for Nonconvex Low-Rank plus Sparse Matrix Recovery AISTATS 2018
Semi-supervised Structured Prediction with Neural CRF Autoencoder EMNLP 2017
Opinion-aware Knowledge Graph for Political Ideology Detection IJCAI 2017
A Unified Computational and Statistical Framework for Nonconvex Low-rank Matrix Estimation AISTATS 2017
PurdueNLP at SemEval-2017 Task 1: Predicting Semantic Textual Similarity with Paraphrase and Event Embeddings SEMEVAL 2017
A Unified Variance Reduction-Based Framework for Nonconvex Low-Rank Matrix Recovery ICML 2017
Range Loss for Deep Face Recognition With Long-Tailed Training Data ICCV 2017
Automatic Spatially-Aware Fashion Concept Discovery ICCV 2017
Asynchronous Distributed Variational Gaussian Process for Regression ICML 2017
pkudblab at SemEval-2016 Task 6 : A Specific Convolutional Neural Network System for Effective Stance Detection SEMEVAL 2016
Adapting Event Embedding for Implicit Discourse Relation Recognition CONLL 2016