Xiaotian Han
24 papers · 2018–2026 · 9 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 ↓+8 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (56) π Conference Polyglot Β· Silver π Academic Marathon Β· Sprint π Interdisciplinary Bridge Β· Bronze π£ Hot Topic Early Bird
π
Triple Crown
π
Grand Slam
π§¬
Topic Evolution
π
Century Club Β· Bronze
π₯
Unstoppable Β· Bronze
β
The Questioner
(3)
ποΈ
Keyword Collector
(123)
β‘
Prolific Year Β· Productive
Top co-authors
Research topics
Machine Learning
(17)
Artificial Intelligence
(14)
Core AI
(14)
Deep Learning
(13)
Application Areas
(11)
Architectures
(8)
Models
(7)
Learning Types Β· Deep Learning
(6)
Learning Types Β· Machine Learning
(5)
Computer Vision
(3)
Natural Language Processing
(3)
Core Methods
(3)
Data Science & Analytics
(2)
Applications Β· Data Science & Analytics
(2)
Applications Β· Natural Language Processing
(2)
Keywords
large language model
(6)
multimodal large language model
(5)
graph neural network
(4)
language model
(3)
demographic parity
(3)
vision-language model
(3)
multimodal learning
(3)
node classification
(2)
context window
(2)
algorithmic fairness
(2)
fairness optimization
(2)
group fairness
(2)
model compression
(2)
message passing
(2)
graph classification
(1)
causal reasoning
(1)
vision transformer
(1)
image restoration
(1)
manifold learning
(1)
link prediction
(1)
Papers
InfiGUIAgent: A Multimodal Generalist GUI Agent with Native Reasoning and Reflection
EACL 2026
InfiGUI-G1: Advancing GUI Grounding with Adaptive Exploration Policy Optimization
AAAI 2026
100-LongBench: Are de facto Long-Context Benchmarks Literally Evaluating Long-Context Ability?
ACL 2025
CausalRAG: Integrating Causal Graphs into Retrieval-Augmented Generation
ACL 2025
InfiMM-WebMath-40B: Advancing Multimodal Pre-Training for Enhanced Mathematical Reasoning
EMNLP 2025
MEPT: Mixture of Expert Prompt Tuning as a Manifold Mapper
EMNLP 2025
Pruning Weights but Not Truth: Safeguarding Truthfulness While Pruning LLMs
EMNLP 2025
Quantized but Deceptive? A Multi-Dimensional Truthfulness Evaluation of Quantized LLMs
EMNLP 2025
When Truthful Representations Flip Under Deceptive Instructions?
EMNLP 2025
Chasing Fairness in Graphs: A GNN Architecture Perspective
AAAI 2024
DreamClear: High-Capacity Real-World Image Restoration with Privacy-Safe Dataset Curation
NeurIPS 2024
FFB: A Fair Fairness Benchmark for In-Processing Group Fairness Methods
ICLR 2024
Gradient Rewiring for Editable Graph Neural Network Training
NeurIPS 2024
InfiMM: Advancing Multimodal Understanding with an Open-Sourced Visual Language Model
ACL 2024
LLM Maybe LongLM: SelfExtend LLM Context Window Without Tuning
ICML 2024
PokeMQA: Programmable knowledge editing for Multi-hop Question Answering
ACL 2024
Visual Anchors Are Strong Information Aggregators For Multimodal Large Language Model
NeurIPS 2024
Chasing Fairness Under Distribution Shift: A Model Weight Perturbation Approach
NeurIPS 2023
MLPInit: Embarrassingly Simple GNN Training Acceleration with MLP Initialization
ICLR 2023
MMPTRACK: Large-Scale Densely Annotated Multi-Camera Multiple People Tracking Benchmark
WACV 2023
Generalized Demographic Parity for Group Fairness
ICLR 2022
G-Mixup: Graph Data Augmentation for Graph Classification
ICML 2022
FlowScope: Spotting Money Laundering Based on Graphs
AAAI 2020
Aspect-Level Deep Collaborative Filtering via Heterogeneous Information Networks
IJCAI 2018