28 citations · 29 across the 18 of their papers we have counts for
19 papers
Last Translation Benchmark
Vilém Zouhar, Niyati Bafna, Mukund Choudhary +263
For scientific progress, we need benchmarks that test the limits of state-of-the-art models, and evaluation methods that inform us about failure cases. As models get stronger, stan…
LUTSeg: A Longitudinal Multi-Expert Dataset for Ulcer Tissue Segmentation
Karen Sanchez, Carlos Hinojosa, Albert A. Ávila +5
Quantifying wound tissue composition is essential for monitoring chronic ulcer progression and guiding treatment decisions. However, pixel-level annotations are costly, and multi-t…
DiSCO: Defending text-to-image generation through distribution-guided contrastive prompt optimization
Tong Zhang, Motasem Alfarra, Carlos Hinojosa +2
As text-to-image generative models advance, they raise critical safety concerns, particularly the generation of Not-Safe-For-Work (NSFW) content such as violence and nudity, furthe…
HyperSafe: Inference-Time Safety Recovery for Fine-Tuned Language Models
Aznaur Aliev, Carlos Hinojosa, Abdelrahman Eldesokey +3
Safety alignment in large language models can be fragile under fine-tuning, as even benign task adaptation may increase harmful compliance. Existing defenses mainly follow two dire…
SGA: Plug&Play Geometric Verification for Educational Video Synthesis
Jhon Lopez, Carlos Hinojosa, Bernard Ghanem
Recent work leverages Large Language Models (LLMs) to generate executable code for pedagogical animations using libraries such as Manim. However, ensuring spatial correctness and v…
Defending Against Harmful Supervision Hidden in Benign Samples
Bang An, Yibo Yang, Dandan Guo +3
Existing defenses are effective when harmful content is explicitly mixed into downstream fine-tuning data, but crafted samples can instead hide harmful supervision inside benign ta…
ProjGuard: Safety Monitoring for Computer-Use Agents via Low-Dimensional Projections
Kebin Contreras, Carlos Hinojosa, Jorge Bacca +1
Computer-use agents are increasingly capable of operating on real operating systems, but this capability has also increased their exposure to prompt injection and other adversarial…
SAVeS: Steering Safety Judgments in Vision-Language Models via Semantic Cues
Carlos Hinojosa, Clemens Grange, Bernard Ghanem
Vision-language models (VLMs) are increasingly deployed in real-world and embodied settings where safety decisions depend on visual context. However, it remains unclear which visua…
CURE: Curriculum-guided Multi-task Training for Reliable Anatomy Grounded Report Generation
Pablo Messina, Andrés Villa, Juan León Alcázar +5
Medical vision-language models can automate the generation of radiology reports but struggle with accurate visual grounding and factual consistency. Existing models often misalign…
CAPTAIN: Semantic Feature Injection for Memorization Mitigation in Text-to-Image Diffusion Models
Tong Zhang, Carlos Hinojosa, Bernard Ghanem
Diffusion models can unintentionally reproduce training examples, raising privacy and copyright concerns as these systems are increasingly deployed at scale. Existing inference-tim…
Multimodal Safety Evaluation in Generative Agent Social Simulations
Alhim Vera, Karen Sanchez, Carlos Hinojosa +3
Can generative agents be trusted in multimodal environments? Despite advances in large language and vision-language models that enable agents to act autonomously and pursue goals i…
SoccerNet 2025 Challenges Results
Silvio Giancola, Anthony Cioppa, Marc Gutiérrez-Pérez +115
The SoccerNet 2025 Challenges mark the fifth annual edition of the SoccerNet open benchmarking effort, dedicated to advancing computer vision research in football video understandi…
UnMix-NeRF: Spectral Unmixing Meets Neural Radiance Fields
Fabian Perez, Sara Rojas, Carlos Hinojosa +2
Neural Radiance Field (NeRF)-based segmentation methods focus on object semantics and rely solely on RGB data, lacking intrinsic material properties. This limitation restricts accu…
Structured-Noise Masked Modeling for Video, Audio and Beyond
Aritra Bhowmik, Fida Mohammad Thoker, Carlos Hinojosa +2
Masked modeling has emerged as a robust self-supervised learning framework. However, most methods rely on random masking, which disregards the structural properties of different da…
OpenTAD: A Unified Framework and Comprehensive Study of Temporal Action Detection
Shuming Liu, Chen Zhao, Fatimah Zohra +10
Temporal action detection (TAD) is a fundamental video understanding task that aims to identify human actions and localize their temporal boundaries in videos. Although this field…
SoccerNet 2024 Challenges Results
Anthony Cioppa, Silvio Giancola, Vladimir Somers +81
The SoccerNet 2024 challenges represent the fourth annual video understanding challenges organized by the SoccerNet team. These challenges aim to advance research across multiple t…
ColorMAE: Exploring data-independent masking strategies in Masked AutoEncoders
Carlos Hinojosa, Shuming Liu, Bernard Ghanem
Masked AutoEncoders (MAE) have emerged as a robust self-supervised framework, offering remarkable performance across a wide range of downstream tasks. To increase the difficulty of…
SoccerNet 2023 Challenges Results
Anthony Cioppa, Silvio Giancola, Vladimir Somers +99
The SoccerNet 2023 challenges were the third annual video understanding challenges organized by the SoccerNet team. For this third edition, the challenges were composed of seven vi…
Learning Semantic Segmentation with Query Points Supervision on Aerial Images
Santiago Rivier, Carlos Hinojosa, Silvio Giancola +1
Semantic segmentation is crucial in remote sensing, where high-resolution satellite images are segmented into meaningful regions. Recent advancements in deep learning have signific…