9 citations · 21 across the 42 of their papers we have counts for
43 papers
LocalProp: Neuro-Localized Memory-Efficient Backpropagation
Diana-Nicoleta Grigore, Iuliana Georgescu, Radu Tudor Ionescu
The current deep learning training paradigm employs end-to-end backpropagation, regardless of the training stage, i.e. pre-training or fine-tuning. However, backpropagating through…
DF-MoE: Generalizable Deepfake Detection via Multimodal Sparse Mixture-of-Experts
Vlad Hondru, Florinel Alin Croitoru, Iuliana Georgescu +2
Audio-visual deepfake detection is an actively studied topic, where one of the main challenges is to develop detectors able to generalize across deepfake generation methods. We con…
Audio Sentiment Analysis via Distillation and Cross-Modal Integration of Generated Multilingual Transcripts
Andrei-George Durdun, Victor Constantinescu, Radu Tudor Ionescu
Automatically recognizing the sentiment, positive or negative, from speech is a challenging task, requiring both the analysis of vocal inflections and the interpretation of uttered…
Multilingual Coreference Resolution via Cycle-Consistent Machine Translation
Adriana-Valentina Costache, Eduard Poesina, Silviu-Florin Gheorghe +2
Coreference resolution is a core NLP task, having a broad range of downstream applications, e.g.~machine translation, question answering, document summarization, etc. While the tas…
MTL-MAD: Multi-Task Learners are Effective Medical Anomaly Detectors
Bogdan Alexandru Bercean, Florinel Alin Croitoru, Vlad Hondru +3
Anomaly detection in medical images is a challenging task, since anomalies are not typically available during training. Recent methods leverage a single pretext task coupled with a…
NTIRE 2026 Rip Current Detection and Segmentation (RipDetSeg) Challenge Report
Andrei Dumitriu, Aakash Ralhan, Florin Miron +32
This report presents the NTIRE 2026 Rip Current Detection and Segmentation (RipDetSeg) Challenge, which targets automatic rip current understanding in images. Rip currents are haza…
JumpLoRA: Sparse Adapters for Continual Learning in Large Language Models
Alexandra Dragomir, Ioana Pintilie, Antonio Barbalau +6
Adapter-based methods have become a cost-effective approach to continual learning (CL) for Large Language Models (LLMs), by sequentially learning a low-rank update matrix for each…
Out of Context: Reliability in Multimodal Anomaly Detection Requires Contextual Inference
Kevin Wilkinghoff, Neelu Madan, Juan Miguel Valverde +6
Anomaly detection aims to identify observations that deviate from expected behavior. Because anomalous events are inherently sparse, most frameworks are trained exclusively on norm…
SegMate: Asymmetric Attention-Based Lightweight Architecture for Efficient Multi-Organ Segmentation
Andrei-Alexandru Bunea, Dan-Matei Popovici, Radu Tudor Ionescu
State-of-the-art models for medical image segmentation achieve excellent accuracy but require substantial computational resources, limiting deployment in resource-constrained clini…
Curriculum-DPO++: Direct Preference Optimization via Data and Model Curricula for Text-to-Image Generation
Florinel-Alin Croitoru, Vlad Hondru, Radu Tudor Ionescu +2
Direct Preference Optimization (DPO) has been proposed as an effective and efficient alternative to reinforcement learning from human feedback (RLHF). However, neither RLHF nor DPO…
MOSLD-Bench: Multilingual Open-Set Learning and Discovery Benchmark for Text Categorization
Adriana-Valentina Costache, Daria-Nicoleta Dragomir, Silviu-Florin Gheorghe +3
Open-set learning and discovery (OSLD) is a challenging machine learning task in which samples from new (unknown) classes can appear at test time. It can be seen as a generalizatio…
CLewR: Curriculum Learning with Restarts for Machine Translation Preference Learning
Alexandra Dragomir, Florin Brad, Radu Tudor Ionescu
Large language models (LLMs) have demonstrated competitive performance in zero-shot multilingual machine translation (MT). Some follow-up works further improved MT performance via…
Machine Unlearning in the Era of Quantum Machine Learning: An Empirical Study
Carla Crivoi, Radu Tudor Ionescu
We present the first empirical study of machine unlearning (MU) in hybrid quantum-classical neural networks. While MU has been extensively explored in classical deep learning, its…
AutoMalDesc: Large-Scale Script Analysis for Cyber Threat Research
Alexandru-Mihai Apostu, Andrei Preda, Alexandra Daniela Damir +4
Generating thorough natural language explanations for threat detections remains an open problem in cybersecurity research, despite significant advances in automated malware detecti…
Every Character Counts: From Vulnerability to Defense in Phishing Detection
Maria Chiper, Radu Tudor Ionescu
Phishing attacks targeting both organizations and individuals are becoming an increasingly significant threat as technology advances. Current automatic detection methods often lack…
PRNU-Bench: A Novel Benchmark and Model for PRNU-Based Camera Identification
Florinel Alin Croitoru, Vlad Hondru, Radu Tudor Ionescu
We propose a novel benchmark for camera identification via Photo Response Non-Uniformity (PRNU) estimation. The benchmark comprises 13K photos taken with 120+ cameras, where the tr…
Curriculum Multi-Task Self-Supervision Improves Lightweight Architectures for Onboard Satellite Hyperspectral Image Segmentation
Hugo Carlesso, Josiane Mothe, Radu Tudor Ionescu
Hyperspectral imaging (HSI) captures detailed spectral signatures across hundreds of contiguous bands per pixel, being indispensable for remote sensing applications such as land-co…
A Large-Scale Benchmark for Evaluating Large Language Models on Medical Question Answering in Romanian
Ana-Cristina Rogoz, Radu Tudor Ionescu, Alexandra-Valentina Anghel +3
We introduce MedQARo, the first large-scale medical QA benchmark in Romanian, alongside a comprehensive evaluation of state-of-the-art large language models (LLMs). We construct a…
AIM 2025 Rip Current Segmentation (RipSeg) Challenge Report
Andrei Dumitriu, Florin Miron, Florin Tatui +24
This report presents an overview of the AIM 2025 RipSeg Challenge, a competition designed to advance techniques for automatic rip current segmentation in still images. Rip currents…
SlotMatch: Distilling Object-Centric Representations for Unsupervised Video Segmentation
Diana-Nicoleta Grigore, Neelu Madan, Andreas Mogelmose +2
Unsupervised video segmentation is a challenging computer vision task, especially due to the lack of supervisory signals coupled with the complexity of visual scenes. To overcome t…
GeMix: Conditional GAN-Based Mixup for Improved Medical Image Augmentation
Hugo Carlesso, Maria Eliza Patulea, Moncef Garouani +2
Mixup has become a popular augmentation strategy for image classification, yet its naive pixel-wise interpolation often produces unrealistic images that can hinder learning, partic…
XMAD-Bench: Cross-Domain Multilingual Audio Deepfake Benchmark
Ioan-Paul Ciobanu, Andrei-Iulian Hiji, Nicolae-Catalin Ristea +3
Recent advances in audio generation led to an increasing number of deepfakes, making the general public more vulnerable to financial scams, identity theft, and misinformation. Audi…
MAVOS-DD: Multilingual Audio-Video Open-Set Deepfake Detection Benchmark
Florinel-Alin Croitoru, Vlad Hondru, Marius Popescu +3
We present the first large-scale open-set benchmark for multilingual audio-video deepfake detection. Our dataset comprises nearly 350 hours of real and fake videos across eight lan…
RipVIS: Rip Currents Video Instance Segmentation Benchmark for Beach Monitoring and Safety
Andrei Dumitriu, Florin Tatui, Florin Miron +3
Rip currents are strong, localized and narrow currents of water that flow outwards into the sea, causing numerous beach-related injuries and fatalities worldwide. Accurate identifi…