Huijia Zhu
26 papers · 2006–2026 · 12 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓+6 more ↓ Show less ↑
🗺️ Taxonomy Completionist (59) 🏃 Academic Marathon · Ultra 🌍 Conference Polyglot · Gold 🌉 Interdisciplinary Bridge · Silver 🤝 Dynamic Duo (14)
🤝
Dynamic Duo
(14)
🗃️
Keyword Collector
(117)
🔥
Unstoppable · Bronze
❓
The Questioner
⚡
Prolific Year · Productive
💎
Century Club · Bronze
Venues
Top co-authors
Research topics
Artificial Intelligence
(16)
Machine Learning
(12)
Core AI
(12)
Deep Learning
(11)
Natural Language Processing
(7)
Computer Vision
(6)
Core Methods
(6)
Learning Paradigms
(6)
Learning Types · Machine Learning
(6)
Learning Types · Deep Learning
(5)
Speech & Audio
(4)
Application Areas
(4)
Applications
(4)
Models
(4)
Analysis
(3)
Keywords
knowledge distillation
(3)
large language model
(2)
named entity recognition
(2)
open-domain question answering
(2)
transfer learning
(2)
document understanding
(2)
speaker recognition
(2)
speaker verification
(2)
convolutional neural network
(2)
ai-generated image detection
(2)
visual document
(2)
domain adaptation
(2)
diffusion model
(2)
text-to-image generation
(2)
multi-task learning
(2)
sentiment analysis
(1)
sequence labeling
(1)
vision transformer
(1)
adversarial learning
(1)
image classification
(1)
Papers
Locate-Then-Examine: Grounded Region Reasoning Improves Detection of AI-Generated Images
CVPR 2026
Aligning Retrieval with Reader Needs: Reader-Centered Passage Selection for Open-Domain Question Answering
COLING 2025
BR-ASR: Efficient and Scalable Bias Retrieval Framework for Contextual Biasing ASR in Speech LLM
Interspeech 2025
Can Knowledge be Transferred from Unimodal to Multimodal? Investigating the Transitivity of Multimodal Knowledge Editing
ICCV 2025
Generalizable Audio Deepfake Detection via Hierarchical Structure Learning and Feature Whitening in Poincaré sphere
Interspeech 2025
Sparse Latents Steer Retrieval-Augmented Generation
ACL 2025
SpeechFake: A Large-Scale Multilingual Speech Deepfake Dataset Incorporating Cutting-Edge Generation Methods
ACL 2025
Stochastic Layer-Wise Shuffle for Improving Vision Mamba Training
ICML 2025
WildFake: A Large-Scale and Hierarchical Dataset for AI-Generated Images Detection
AAAI 2025
Beyond Full Fine-tuning: Harnessing the Power of LoRA for Multi-Task Instruction Tuning
COLING 2024
Chain-of-Rewrite: Aligning Question and Documents for Open-Domain Question Answering
EMNLP 2024
COIN-Matting: Confounder Intervention for Image Matting
ECCV 2024
ComFusion: Enhancing Personalized Generation by Instance-Scene Compositing and Fusion
ECCV 2024
Debiasing In-Context Learning by Instructing LLMs How to Follow Demonstrations
ACL 2024
DomainGallery: Few-shot Domain-driven Image Generation by Attribute-centric Finetuning
NeurIPS 2024
Modeling Layout Reading Order as Ordering Relations for Visually-rich Document Understanding
EMNLP 2024
Probe Then Retrieve and Reason: Distilling Probing and Reasoning Capabilities into Smaller Language Models
COLING 2024
XMC-Agent : Dynamic Navigation over Scalable Hierarchical Index for Incremental Extreme Multi-label Classification
ACL 2024
DiffUTE: Universal Text Editing Diffusion Model
NeurIPS 2023
Reading Order Matters: Information Extraction from Visually-rich Documents by Token Path Prediction
EMNLP 2023
A Multi-Task Dual-Tree Network for Aspect Sentiment Triplet Extraction
COLING 2022
Ant Multilingual Recognition System for OLR 2021 Challenge
Interspeech 2022
TransAdv: A Translation-based Adversarial Learning Framework for Zero-Resource Cross-Lingual Named Entity Recognition
EMNLP 2022
AntVoice Neural Speaker Embedding System for FFSVC 2020
Interspeech 2021
Domain Adaptation with Latent Semantic Association for Named Entity Recognition
NAACL 2009
Dependency Parsing Based on Dynamic Local Optimization
CoNLL 2006