Publications (40)
Reading Between the Frames: Multi-Modal Depression Detection in Videos from Non-Verbal Cues
David Gimeno-Gómez, Ana-Maria Bucur, Adrian Cosma +2
Depression, a prominent contributor to global disability, affects a substantial portion of the population. Efforts to detect depression from social media texts have been prevalent,…
Aligning Actions and Walking to LLM-Generated Textual Descriptions
Radu Chivereanu, Adrian Cosma, Andy Catruna +2
Large Language Models (LLMs) have demonstrated remarkable capabilities in various domains, including data augmentation and synthetic data generation. This work explores the use of…
Self-Supervised Representation Learning on Document Images
Adrian Cosma, Mihai Ghidoveanu, Michael Panaitescu-Liess +1
This work analyses the impact of self-supervised pre-training on document images in the context of document image classification. While previous approaches explore the effect of se…
Gait Recognition from Highly Compressed Videos
Andrei Niculae, Andy Catruna, Adrian Cosma +2
Surveillance footage represents a valuable resource and opportunities for conducting gait analysis. However, the typical low quality and high noise levels in such footage can sever…
A Generic and Model-Agnostic Exemplar Synthetization Framework for Explainable AI
Antonio Barbalau, Adrian Cosma, Radu Tudor Ionescu +1
With the growing complexity of deep learning methods adopted in practical applications, there is an increasing and stringent need to explain and interpret the decisions of such met…
Spatial Colour Mixing Illusions as a Perception Stress Test for Vision-Language Models
Nicoleta-Nina Basoc, Adrian Cosma, Emilian Radoi
Vision-language models (VLMs) achieve strong benchmark results, yet can exhibit systematic perceptual weaknesses: structured, large changes to pixel values can cause confident yet…
It's Just a Matter of Time: Detecting Depression with Time-Enriched Multimodal Transformers
Ana-Maria Bucur, Adrian Cosma, Paolo Rosso +1
Depression detection from user-generated content on the internet has been a long-lasting topic of interest in the research community, providing valuable screening tools for psychol…
MoME: Estimating Psychological Traits from Gait with Multi-Stage Mixture of Movement Experts
Andy CÇtrunÇ, Adrian Cosma, Emilian RÇdoi
Gait encodes rich biometric and behavioural information, yet leveraging the manner of walking to infer psychological traits remains a challenging and underexplored problem. We intr…
CrossGaze: A Strong Method for 3D Gaze Estimation in the Wild
Andy CÄtrunÄ, Adrian Cosma, Emilian RÄdoi
Gaze estimation, the task of predicting where an individual is looking, is a critical task with direct applications in areas such as human-computer interaction and virtual reality.…
Humanity's Last Exam
Long Phan, Alice Gatti, Ziwen Han +1144
Benchmarks are important tools for tracking the rapid advancements in large language model (LLM) capabilities. However, benchmarks are not keeping pace in difficulty: LLMs now achi…
Counterfactual Methods for Detecting Unfairness in Anti-Money Laundering Algorithms
Lea Multerer, Michele Inchingolo, David Kletz +3
The application of machine learning-based predictive algorithms to Anti-Money Laundering (AML) has grown rapidly, driven by the vast volume of financial transaction data available…
Automatic Prompt Optimization for Dataset-Level Feature Discovery
Adrian Cosma, Oleg Szehr, David Kletz +2
Feature extraction from unstructured text is a critical step in many downstream classification pipelines, yet current approaches largely rely on hand-crafted prompts or fixed featu…
The Strawberry Problem: Emergence of Character-level Understanding in Tokenized Language Models
Adrian Cosma, Stefan Ruseti, Emilian Radoi +1
Despite their remarkable progress across diverse domains, Large Language Models (LLMs) consistently fail at simple character-level tasks, such as counting letters in words, due to…
GaitPT: Skeletons Are All You Need For Gait Recognition
Andy Catruna, Adrian Cosma, Emilian Radoi
The analysis of patterns of walking is an important area of research that has numerous applications in security, healthcare, sports and human-computer interaction. Lately, walking…
Learning to Simplify Spatial-Temporal Graphs in Gait Analysis
Adrian Cosma, Emilian Radoi
Gait analysis leverages unique walking patterns for person identification and assessment across multiple domains. Among the methods used for gait analysis, skeleton-based approache…
Dr.Copilot: A Multi-Agent Prompt Optimized Assistant for Improving Patient-Doctor Communication in Romanian
Andrei Niculae, Adrian Cosma, Cosmin Dumitrache +1
Text-based telemedicine has become increasingly common, yet the quality of medical advice in doctor-patient interactions is often judged more on how advice is communicated rather t…
An In-Vitro Study on Cross-Lingual Generalization in Language Models
Adrian Cosma
Cross-lingual transfer in language models is difficult to study in natural corpora because lexical overlap, morphology, data imbalance, and tokenization are entangled. We introduce…
Sequence-to-Sequence Lexical Normalization with Multilingual Transformers
Ana-Maria Bucur, Adrian Cosma, Liviu P. Dinu
Current benchmark tasks for natural language processing contain text that is qualitatively different from the text used in informal day to day digital communication. This discrepan…
A Retrieval-Based Approach to Medical Procedure Matching in Romanian
Andrei Niculae, Adrian Cosma, Emilian Radoi
Accurately mapping medical procedure names from healthcare providers to standardized terminology used by insurance companies is a crucial yet complex task. Inconsistencies in namin…
Life is not Always Depressing: Exploring the Happy Moments of People Diagnosed with Depression
Ana-Maria Bucur, Adrian Cosma, Liviu P. Dinu
In this work, we explore the relationship between depression and manifestations of happiness in social media. While the majority of works surrounding depression focus on symptoms,…
BLUE at Memotion 2.0 2022: You have my Image, my Text and my Transformer
Ana-Maria Bucur, Adrian Cosma, Ioan-Bogdan Iordache
Memes are prevalent on the internet and continue to grow and evolve alongside our culture. An automatic understanding of memes propagating on the internet can shed light on the gen…
PsyMo: A Dataset for Estimating Self-Reported Psychological Traits from Gait
Adrian Cosma, Emilian Radoi
Psychological trait estimation from external factors such as movement and appearance is a challenging and long-standing problem in psychology, and is principally based on the psych…
From Face to Gait: Weakly-Supervised Learning of Gender Information from Walking Patterns
Andy Catruna, Adrian Cosma, Ion Emilian Radoi
Obtaining demographics information from video is valuable for a range of real-world applications. While approaches that leverage facial features for gender inference are very succe…
Black-Box Ripper: Copying black-box models using generative evolutionary algorithms
Antonio Barbalau, Adrian Cosma, Radu Tudor Ionescu +1
We study the task of replicating the functionality of black-box neural models, for which we only know the output class probabilities provided for a set of input images. We assume b…
Training Language Models with homotokens Leads to Delayed Overfitting
Adrian Cosma, Stefan Ruseti, Emilian Radoi +1
Subword tokenization introduces a computational layer in language models where many distinct token sequences decode to the same surface form and preserve meaning, yet induce differ…
RoCode: A Dataset for Measuring Code Intelligence from Problem Definitions in Romanian
Adrian Cosma, Bogdan Iordache, Paolo Rosso
Recently, large language models (LLMs) have become increasingly powerful and have become capable of solving a plethora of tasks through proper instructions in natural language. How…
The Paradox of Motion: Evidence for Spurious Correlations in Skeleton-based Gait Recognition Models
Andy CÄtrunÄ, Adrian Cosma, Emilian RÄdoi
Gait, an unobtrusive biometric, is valued for its capability to identify individuals at a distance, across external outfits and environmental conditions. This study challenges the…
GaitFormer: Learning Gait Representations with Noisy Multi-Task Learning
Adrian Cosma, Emilian Radoi
Gait analysis is proven to be a reliable way to perform person identification without relying on subject cooperation. Walking is a biometric that does not significantly change in s…
Database-Agnostic Gait Enrollment using SetTransformers
Nicoleta Basoc, Adrian Cosma, Andy CÇtrunÇ +1
Gait recognition has emerged as a powerful tool for unobtrusive and long-range identity analysis, with growing relevance in surveillance and monitoring applications. Although recen…
On Model and Data Scaling for Skeleton-based Self-Supervised Gait Recognition
Adrian Cosma, Andy CÇtrunÇ, Emilian RÇdoi
Gait recognition from video streams is a challenging problem in computer vision biometrics due to the subtle differences between gaits and numerous confounding factors. Recent adva…
WildGait: Learning Gait Representations from Raw Surveillance Streams
Adrian Cosma, Emilian Radoi
The use of gait for person identification has important advantages such as being non-invasive, unobtrusive, not requiring cooperation and being less likely to be obscured compared…
Improving Medical Communication using Rubric-Guided Counterfactual Recommendations
Adrian Cosma, Nicoleta-Nina Basoc, Andrei Niculae +2
Text-based telemedicine increasingly relies on lightweight patient feedback, however, such feedback primarily reflects perceived communication quality rather than medical accuracy.…
An End-to-End Set Transformer for User-Level Classification of Depression and Gambling Disorder
Ana-Maria Bucur, Adrian Cosma, Liviu P. Dinu +1
This work proposes a transformer architecture for user-level classification of gambling addiction and depression that is trainable end-to-end. As opposed to other methods that oper…
CamLoc: Pedestrian Location Detection from Pose Estimation on Resource-constrained Smart-cameras
Adrian Cosma, Ion Emilian Radoi, Valentin Radu
Recent advancements in energy-efficient hardware technology is driving the exponential growth we are experiencing in the Internet of Things (IoT) space, with more pervasive computa…
RoMath: A Mathematical Reasoning Benchmark in Romanian
Adrian Cosma, Ana-Maria Bucur, Emilian Radoi
Mathematics has long been conveyed through natural language, primarily for human understanding. With the rise of mechanized mathematics and proof assistants, there is a growing nee…
How Hard is this Test Set? NLI Characterization by Exploiting Training Dynamics
Adrian Cosma, Stefan Ruseti, Mihai Dascalu +1
Natural Language Inference (NLI) evaluation is crucial for assessing language understanding models; however, popular datasets suffer from systematic spurious correlations that arti…
Prompting Complexity: Shortest Prompts for Texts and Behaviors in LLMs
Adrian Cosma
In this paper, we define the quantity of prompting complexity: for a fixed instruction-tuned language model, what is the shortest plausible prompt that makes deterministic decoding…
GaitMorph: Transforming Gait by Optimally Transporting Discrete Codes
Adrian Cosma, Emilian Radoi
Gait, the manner of walking, has been proven to be a reliable biometric with uses in surveillance, marketing and security. A promising new direction for the field is training gait…
Early Risk Detection of Pathological Gambling, Self-Harm and Depression Using BERT
Ana-Maria Bucur, Adrian Cosma, Liviu P. Dinu
Early risk detection of mental illnesses has a massive positive impact upon the well-being of people. The eRisk workshop has been at the forefront of enabling interdisciplinary res…
What Makes a Good Doctor Response? A Study on Text-Based Telemedicine
Adrian Cosma, Cosmin Dumitrache, Emilian Radoi
Text-based telemedicine has become an increasingly used mode of care, requiring clinicians to deliver medical advice clearly and effectively in writing. As platforms increasingly r…