Meiqi Wu
9 papers · 2024–2026 · 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 ↓
🌍
Conference Polyglot · Silver
🌉
Interdisciplinary Bridge · Bronze
🗺️
Taxonomy Completionist
(19)
🗃️
Keyword Collector
(50)
Top co-authors
Research topics
Computer Vision
(8)
Artificial Intelligence
(4)
Deep Learning
(4)
Core AI · Artificial Intelligence
(4)
Generation
(4)
Machine Learning
(3)
Analysis
(3)
Models
(2)
Interdisciplinary
(1)
Reinforcement Learning
(1)
Architectures
(1)
Cognitive Science
(1)
Core AI · Computer Vision
(1)
Core Methods
(1)
Domain-Specific
(1)
Keywords
video generation
(3)
multimodal learning
(2)
object tracking
(2)
vision-language tracking
(2)
text-to-image generation
(1)
mathematical reasoning
(1)
human perception
(1)
video understanding
(1)
model calibration
(1)
conditional generation
(1)
mixture of expert
(1)
reward hacking
(1)
visual search
(1)
reinforcement learning from human feedback
(1)
diffusion model
(1)
visual object tracking
(1)
uncertainty quantification
(1)
vision-language model
(1)
prompt tuning
(1)
policy optimization
(1)
Papers
Calibration-Aware Policy Optimization for Reasoning LLMs
ACL 2026
ImagerySearch: Adaptive Test-Time Search for Video Generation Beyond Semantic Dependency Constraints
AAAI 2026
Omni-Effects: Unified and Spatially-Controllable Visual Effects Generation
AAAI 2026
Taming Preference Mode Collapse via Directional Decoupling Alignment in Diffusion Reinforcement Learning
CVPR 2026
ATCTrack: Aligning Target-Context Cues with Dynamic Target States for Robust Vision-Language Tracking
ICCV 2025
CSTrack: Enhancing RGB-X Tracking via Compact Spatiotemporal Features
ICML 2025
VMBench: A Benchmark for Perception-Aligned Video Motion Generation
ICCV 2025
Beyond Accuracy: Tracking more like Human via Visual Search
NeurIPS 2024
MemVLT: Vision-Language Tracking with Adaptive Memory-based Prompts
NeurIPS 2024