Afshin Dehghan
15 papers · 2013–2026 · 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 ↓+7 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (36) π Academic Marathon Β· Half π Conference Polyglot Β· Silver π Interdisciplinary Bridge Β· Silver π£ Hot Topic Early Bird
π₯
Mega-Team Β· Squad
π
Conference Pioneer
π₯
Unstoppable Β· Bronze
β
The Questioner
π
Century Club Β· Bronze
π
Trend Setter
ποΈ
Keyword Collector
(85)
Venues
Top co-authors
Research topics
Computer Vision
(12)
Deep Learning
(8)
Artificial Intelligence
(7)
Core AI Β· Artificial Intelligence
(7)
Analysis
(5)
Machine Learning
(4)
Generation
(4)
Models
(4)
Architectures
(3)
Learning Types Β· Machine Learning
(3)
Learning Types Β· Deep Learning
(3)
Processing
(3)
Core AI Β· Computer Vision
(2)
Core Methods
(2)
Mathematics & Optimization
(1)
Keywords
multimodal large language model
(5)
image generation
(3)
image segmentation
(2)
multiple object tracking
(2)
data association
(2)
multimodal learning
(2)
object detection
(2)
depth perception
(1)
feature extraction
(1)
reinforcement learning
(1)
autoregressive generation
(1)
point cloud
(1)
face recognition
(1)
monocular depth estimation
(1)
video analysis
(1)
information extraction
(1)
neural architecture
(1)
deep learning
(1)
visual grounding
(1)
image editing
(1)
Papers
AToken: A Unified Tokenizer for Vision
CVPR 2026
SO-Bench: A Structural Output Evaluation of Multimodal LLM
CVPR 2026
UniGen-1.5: Enhancing Image Generation and Editing through Reward Unification in RL
CVPR 2026
Cubify Anything: Scaling Indoor 3D Object Detection
CVPR 2025
FlexTok: Resampling Images into 1D Token Sequences of Flexible Length
ICML 2025
MM1.5: Methods, Analysis & Insights from Multimodal LLM Fine-tuning
ICLR 2025
MM-Spatial: Exploring 3D Spatial Understanding in Multimodal LLMs
ICCV 2025
4M-21: An Any-to-Any Vision Model for Tens of Tasks and Modalities
NeurIPS 2024
4M: Massively Multimodal Masked Modeling
NeurIPS 2023
GAUDI: A Neural Architect for Immersive 3D Scene Generation
NeurIPS 2022
GMMCP Tracker: Globally Optimal Generalized Maximum Multi Clique Problem for Multiple Object Tracking
CVPR 2015
Target Identity-Aware Network Flow for Online Multiple Target Tracking
CVPR 2015
Improving Semantic Concept Detection through the Dictionary of Visually-distinct Elements
CVPR 2014
Who Do I Look Like? Determining Parent-Offspring Resemblance via Gated Autoencoders
CVPR 2014
Improving an Object Detector and Extracting Regions Using Superpixels
CVPR 2013