Peter Vajda
29 papers · 2018–2025 · 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 ↓+10 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (49) π Academic Marathon Β· Sprint π Conference Polyglot Β· Silver π Interdisciplinary Bridge Β· Bronze π£ Hot Topic Early Bird
π€
Dynamic Duo
(18)
π§¬
Topic Evolution
π
Keyword Champion
(2)
π
Conference Pioneer
π₯
Unstoppable Β· Bronze
β
The Questioner
β‘
Prolific Year Β· Productive
π
Century Club Β· Bronze
π
Trend Setter
ποΈ
Keyword Collector
(119)
Top co-authors
Research topics
Deep Learning
(17)
Computer Vision
(15)
Machine Learning
(12)
Artificial Intelligence
(9)
Application Areas
(9)
Core AI
(9)
Generation
(8)
Models
(8)
Analysis
(7)
Learning Types Β· Deep Learning
(7)
Architectures
(5)
Optimization & Theory
(5)
Processing
(5)
Learning Types Β· Machine Learning
(4)
Techniques
(4)
Keywords
diffusion model
(5)
efficient computing
(5)
knowledge distillation
(3)
video generation
(3)
neural network
(3)
model compression
(3)
neural architecture search
(3)
video editing
(2)
semantic segmentation
(2)
differentiable neural architecture search
(2)
diffusion transformer
(2)
video-to-video synthesis
(2)
temporal consistency
(2)
hardware-aware design
(2)
vision-language model
(2)
object detection
(1)
hyperparameter optimization
(1)
adversarial learning
(1)
image restoration
(1)
domain adaptation
(1)
Papers
Learnings from Scaling Visual Tokenizers for Reconstruction and Generation
ICML 2025
LinGen: Towards High-Resolution Minute-Length Text-to-Video Generation with Linear Computational Complexity
CVPR 2025
Movie Weaver: Tuning-Free Multi-Concept Video Personalization with Anchored Prompts
CVPR 2025
AVID: Any-Length Video Inpainting with Diffusion Model
CVPR 2024
Cache Me if You Can: Accelerating Diffusion Models through Block Caching
CVPR 2024
ControlRoom3D: Room Generation using Semantic Proxy Rooms
CVPR 2024
Fairy: Fast Parallelized Instruction-Guided Video-to-Video Synthesis
CVPR 2024
FlowVid: Taming Imperfect Optical Flows for Consistent Video-to-Video Synthesis
CVPR 2024
A Practical Stereo Depth System for Smart Glasses
CVPR 2023
Castling-ViT: Compressing Self-Attention via Switching Towards Linear-Angular Attention at Vision Transformer Inference
CVPR 2023
NeRF-Det: Learning Geometry-Aware Volumetric Representation for Multi-View 3D Object Detection
ICCV 2023
Open-Vocabulary Semantic Segmentation With Mask-Adapted CLIP
CVPR 2023
Cross-Domain Adaptive Teacher for Object Detection
CVPR 2022
Data Efficient Language-Supervised Zero-Shot Recognition with Optimal Transport Distillation
ICLR 2022
Image2Point: 3D Point-Cloud Understanding with 2D Image Pretrained Models
ECCV 2022
Open-Set Semi-Supervised Object Detection
ECCV 2022
FBNetV3: Joint Architecture-Recipe Search Using Predictor Pretraining
CVPR 2021
Tackling the Ill-Posedness of Super-Resolution Through Adaptive Target Generation
CVPR 2021
Unbiased Teacher for Semi-Supervised Object Detection
ICLR 2021
Visual Transformers: Where Do Transformers Really Belong in Vision Models?
ICCV 2021
Deep Space-Time Video Upsampling Networks
ECCV 2020
FBNetV2: Differentiable Neural Architecture Search for Spatial and Channel Dimensions
CVPR 2020
Geometric Correspondence Fields: Learned Differentiable Rendering for 3D Pose Refinement in the Wild
ECCV 2020
Learning to Generate Grounded Visual Captions without Localization Supervision
ECCV 2020
SqueezeSegV3: Spatially-Adaptive Convolution for Efficient Point-Cloud Segmentation
ECCV 2020
ChamNet: Towards Efficient Network Design Through Platform-Aware Model Adaptation
CVPR 2019
Efficient Segmentation: Learning Downsampling Near Semantic Boundaries
ICCV 2019
FBNet: Hardware-Aware Efficient ConvNet Design via Differentiable Neural Architecture Search
CVPR 2019
Value-aware Quantization for Training and Inference of Neural Networks
ECCV 2018