Diana Marculescu
21 papers · 2017–2025 · 10 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 ↓+9 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (46) π Conference Polyglot Β· Gold π Academic Marathon Β· Sprint π Interdisciplinary Bridge Β· Silver π£ Hot Topic Early Bird
π
Keyword Champion
(2)
π§
Keyword Pioneer
π
Grand Slam
π§¬
Topic Evolution
π
Trend Setter
β‘
Prolific Year Β· Productive
π
Conference Pioneer
π
Century Club Β· Bronze
ποΈ
Keyword Collector
(106)
Venues
Top co-authors
Research topics
Deep Learning
(17)
Machine Learning
(13)
Artificial Intelligence
(10)
Core AI
(10)
Computer Vision
(8)
Application Areas
(8)
Architectures
(8)
Optimization & Theory Β· Deep Learning
(6)
Learning Types Β· Deep Learning
(5)
Processing
(5)
Analysis
(4)
Learning Types Β· Machine Learning
(4)
Models
(4)
Generation
(3)
Optimization & Theory Β· Machine Learning
(3)
Keywords
model compression
(7)
temporal consistency
(4)
vision transformer
(3)
diffusion model
(3)
convolutional neural network
(3)
multimodal learning
(2)
audio separation
(2)
state space model
(2)
video editing
(2)
low-rank approximation
(2)
optical flow
(2)
sound source localization
(1)
zero-shot learning
(1)
object detection
(1)
source separation
(1)
transfer learning
(1)
image classification
(1)
quantization
(1)
few-shot learning
(1)
neural architecture search
(1)
Papers
Ada-VE: Training-Free Consistent Video Editing using Adaptive Motion Prior
WACV 2025
Looking Backward: Streaming Video-to-Video Translation with Feature Banks
ICLR 2025
Movie Weaver: Tuning-Free Multi-Concept Video Personalization with Anchored Prompts
CVPR 2025
Quamba2: A Robust and Scalable Post-training Quantization Framework for Selective State Space Models
ICML 2025
Quamba: A Post-Training Quantization Recipe for Selective State Space Models
ICLR 2025
FLORA: Fine-Grained Low-Rank Architecture Search for Vision Transformer
WACV 2024
FlowVid: Taming Imperfect Optical Flows for Consistent Video-to-Video Synthesis
CVPR 2024
OpenSep: Leveraging Large Language Models with Textual Inversion for Open World Audio Separation
EMNLP 2024
PaPr: Training-Free One-Step Patch Pruning with Lightweight ConvNets for Faster Inference
ECCV 2024
SSVOD: Semi-Supervised Video Object Detection With Sparse Annotations
WACV 2024
T-VSL: Text-Guided Visual Sound Source Localization in Mixtures
CVPR 2024
Weakly-supervised Audio Separation via Bi-modal Semantic Similarity
ICLR 2024
AVE-CLIP: AudioCLIP-Based Multi-Window Temporal Transformer for Audio Visual Event Localization
WACV 2023
Efficient Low-rank Backpropagation for Vision Transformer Adaptation
NeurIPS 2023
Jumping through Local Minima: Quantization in the Loss Landscape of Vision Transformers
ICCV 2023
MobileTL: On-Device Transfer Learning with Inverted Residual Blocks
AAAI 2023
Open-Vocabulary Semantic Segmentation With Mask-Adapted CLIP
CVPR 2023
Towards Efficient Model Compression via Learned Global Ranking
CVPR 2020
ViP: Virtual Pooling for Accelerating CNN-based Image Classification and Object Detection
WACV 2020
Regularizing Activation Distribution for Training Binarized Deep Networks
CVPR 2019
NeuralPower: Predict and Deploy Energy-Efficient Convolutional Neural Networks
ACML 2017