Hongxia Xie
9 papers · 2023–2026 · 4 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 ↓
🌍
Conference Polyglot · Bronze
🌉
Interdisciplinary Bridge · Silver
🗺️
Taxonomy Completionist
(19)
⚡
Prolific Year · Productive
🌈
Renaissance Researcher
(5)
Top co-authors
Research topics
Artificial Intelligence
(5)
Core AI
(4)
Computer Vision
(3)
Machine Learning
(2)
Generation
(2)
Learning Types · Machine Learning
(2)
Computer Science
(1)
Deep Learning
(1)
Reinforcement Learning
(1)
Robotics
(1)
Analysis
(1)
Applications
(1)
Capabilities
(1)
Learning Paradigms
(1)
Learning Types · Deep Learning
(1)
Keywords
transformer architecture
(1)
contrastive learning
(1)
zero-shot learning
(1)
offline reinforcement learning
(1)
decision making
(1)
attention mechanism
(1)
emotion recognition
(1)
face recognition
(1)
deepfake detection
(1)
robot manipulation
(1)
sequential recommendation
(1)
3d generation
(1)
vision-language model
(1)
multimodal large language model
(1)
embodied agent
(1)
reward shaping
(1)
visual instruction tuning
(1)
hallucination detection
(1)
multimodal input
(1)
theory of mind
(1)
Papers
Beyond Success: Refining Elegant Robot Manipulation from Mixed-Quality Data via Just-in-Time Intervention
CVPR 2026
CAD-Refiner: A Unified Framework for CAD Generation and Iterative Editing
CVPR 2026
KPLM-STA: Physically-Accurate Shadow Synthesis for Human Relighting via Keypoint-Based Light Modeling
AAAI 2026
MindPower: Enabling Theory-of-Mind Reasoning in VLM-based Embodied Agents
CVPR 2026
TriDF: Evaluating Perception, Detection, and Hallucination for Interpretable DeepFake Detection
CVPR 2026
Future Sight and Tough Fights: Revolutionizing Sequential Recommendation with FENRec
AAAI 2025
EmoVIT: Revolutionizing Emotion Insights with Visual Instruction Tuning
CVPR 2024
The Fabrication of Reality and Fantasy: Scene Generation with LLM-Assisted Prompt Interpretation
ECCV 2024
Most Important Person-Guided Dual-Branch Cross-Patch Attention for Group Affect Recognition
ICCV 2023