Aram Davtyan
7 papers · 2022–2025 · 5 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)
🐣
Hot Topic Early Bird
👥
Mega-Team · Squad
Top co-authors
Research topics
Deep Learning
(6)
Computer Vision
(5)
Generation
(5)
Machine Learning
(4)
Optimization & Theory · Machine Learning
(3)
Artificial Intelligence
(2)
Architectures
(2)
Core AI · Artificial Intelligence
(2)
Learning Types · Deep Learning
(2)
Models
(2)
Analysis
(1)
Core AI · Computer Vision
(1)
Domain-Specific
(1)
Learning Types · Machine Learning
(1)
Optimization & Theory · Deep Learning
(1)
Keywords
video prediction
(3)
video generation
(3)
motion control
(2)
unsupervised learning
(2)
autoregressive generation
(1)
multimodal learning
(1)
conditional generation
(1)
flow matching
(1)
neural network optimization
(1)
kalman filter
(1)
autoregressive model
(1)
adaptive optimization
(1)
adam optimizer
(1)
latent space
(1)
world model
(1)
controllable generation
(1)
momentum method
(1)
sampling trajectory
(1)
conditional flow matching
(1)
continuous normalizing flow
(1)
Papers
CAGE: Unsupervised Visual Composition and Animation for Controllable Video Generation
AAAI 2025
Faster Inference of Flow-Based Generative Models via Improved Data-Noise Coupling
ICLR 2025
GEM: A Generalizable Ego-Vision Multimodal World Model for Fine-Grained Ego-Motion, Object Dynamics, and Scene Composition Control
CVPR 2025
Learn the Force We Can: Enabling Sparse Motion Control in Multi-Object Video Generation
AAAI 2024
Efficient Video Prediction via Sparsely Conditioned Flow Matching
ICCV 2023
Controllable Video Generation through Global and Local Motion Dynamics
ECCV 2022
KOALA: A Kalman Optimization Algorithm with Loss Adaptivity
AAAI 2022