Xin Gu
11 papers · 2023–2026 · 6 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 ↓+2 more ↓ Show less ↑
🌉 Interdisciplinary Bridge · Gold 🗺️ Taxonomy Completionist (24) 🌍 Conference Polyglot · Silver 🗃️ Keyword Collector (53) 🌈 Renaissance Researcher (6)
⚡
Prolific Year · Productive
💎
Century Club · Bronze
Top co-authors
Research topics
Computer Vision
(8)
Deep Learning
(7)
Processing
(6)
Generation
(4)
Artificial Intelligence
(3)
Machine Learning
(3)
Architectures
(3)
Core AI
(3)
Learning Types · Deep Learning
(3)
Natural Language Processing
(2)
Analysis
(2)
Core Methods
(2)
Learning Types · Machine Learning
(2)
Models
(2)
Knowledge & Reasoning
(1)
Keywords
video understanding
(3)
spatio-temporal video grounding
(2)
video captioning
(2)
image editing
(2)
vision-language model
(2)
temporal modeling
(1)
action recognition
(1)
reinforcement learning
(1)
image synthesis
(1)
multimodal learning
(1)
reward modeling
(1)
correlated noise
(1)
object localization
(1)
temporal grounding
(1)
natural language
(1)
instruction following
(1)
image generation
(1)
spatio-temporal localization
(1)
knowledge graph
(1)
benchmark evaluation
(1)
Papers
Beyond Counting: Evaluating Abstract and Emotional Reasoning in Vision-Language Models
AAAI 2026
Cocoon: A System Architecture for Differentially Private Training with Correlated Noises
OSDI 2026
LookFlow: Training-Free and Efficient High-Resolution Image Synthesis via Dynamic Lookahead Guidance Flow
AAAI 2026
Structured Context Learning for Generic Event Boundary Detection
WACV 2026
Thinking With Videos: Multimodal Tool-Augmented Reinforcement Learning for Long Video Reasoning
CVPR 2026
Knowing Your Target: Target-Aware Transformer Makes Better Spatio-Temporal Video Grounding
ICLR 2025
Multi-Reward as Condition for Instruction-based Image Editing
ICLR 2025
SuperEdit: Rectifying and Facilitating Supervision for Instruction-Based Image Editing
ICCV 2025
Context-Guided Spatio-Temporal Video Grounding
CVPR 2024
Accurate and Fast Compressed Video Captioning
ICCV 2023
Text With Knowledge Graph Augmented Transformer for Video Captioning
CVPR 2023