6 citations · 7 across the 11 of their papers we have counts for
12 papers
The GEST-Engine: From Event Graphs to Synthetic Video. A Full Technical Report
Nicolae Cudlenco, Mihai Masala, Marius Leordeanu
We present the GEST-Engine, a complete system that goes from natural-language text to fully-annotated multi-actor video. At its core is an explicit world model: rather than encodin…
"Înţelegi Româneşte?'' A Recipe for Romanian Vision-Language Models
Mihai Masala, Marius Leordeanu, Mihai Dascalu +1
Vision-Language Models (VLMs) largely follow the text-only LLM trajectory, excelling on English benchmarks but sharply degrading on low-resource languages, where neither large-scal…
idSCD: Identifying Training Datasets through Semantic Correlation Descriptors
Andrada Gobeaja, Ionut Hodoroaga, Elena Burceanu +1
Can a dataset be recognized from the spurious correlations it induces during training? We argue that datasets leave dataset-specific traces in a model's learned semantic correlatio…
GTASA: Ground Truth Annotations for Spatiotemporal Analysis, Evaluation and Training of Video Models
Nicolae Cudlenco, Mihai Masala, Marius Leordeanu
Game engines hold what video models struggle to learn: a complete, explicit world state behind every frame. We turn one into a data instrument. GEST-Engine, our production-grade op…
Authoring for Living Worlds: Tool-Constrained LLM Agents for Executable Multi-Actor Scenarios
Nicolae Cudlenco, Mihai Masala, Marius Leordeanu
Authoring a multi-actor scenario for a living 3D world, where every action changes its state, and each action's validity depends on the state accumulated before it, demands the fre…
From Vision To Language through Graph of Events in Space and Time: An Explainable Self-supervised Approach
Mihai Masala, Marius Leordeanu
The task of describing video content in natural language is commonly referred to as video captioning. Unlike conventional video captions, which are typically brief and widely avail…
Learning from Random Subspace Exploration: Generalized Test-Time Augmentation with Self-supervised Distillation
Andrei Jelea, Ahmed Nabil Belbachir, Marius Leordeanu
We introduce Generalized Test-Time Augmentation (GTTA), a highly effective method for improving the performance of a trained model, which unlike other existing Test-Time Augmentati…
Towards Zero-Shot & Explainable Video Description by Reasoning over Graphs of Events in Space and Time
Mihai Masala, Marius Leordeanu
In the current era of Machine Learning, Transformers have become the de facto approach across a variety of domains, such as computer vision and natural language processing. Transfo…
"Vorbeşti Româneşte?" A Recipe to Train Powerful Romanian LLMs with English Instructions
Mihai Masala, Denis C. Ilie-Ablachim, Alexandru Dima +10
In recent years, Large Language Models (LLMs) have achieved almost human-like performance on various tasks. While some LLMs have been trained on multilingual data, most of the trai…
OpenLLM-Ro -- Technical Report on Open-source Romanian LLMs
Mihai Masala, Denis C. Ilie-Ablachim, Dragos Corlatescu +6
In recent years, Large Language Models (LLMs) have achieved almost human-like performance on various tasks. While some LLMs have been trained on multilingual data, most of the trai…
Explaining Vision and Language through Graphs of Events in Space and Time
Mihai Masala, Nicolae Cudlenco, Traian Rebedea +1
Artificial Intelligence makes great advances today and starts to bridge the gap between vision and language. However, we are still far from understanding, explaining and controllin…
A self-supervised neural-analytic method to predict the evolution of COVID-19 in Romania
Radu D. Stochiţoiu, Marian Petrica, Traian Rebedea +2
Analysing and understanding the transmission and evolution of the COVID-19 pandemic is mandatory to be able to design the best social and medical policies, foresee their outcomes a…