418 citations · 3.5k across the 221 of their papers we have counts for
248 papers
COMPASS: Contextual Moment Prior Alignment for Generalizable AIGI Detection
Zhan Yang, Tiancheng Shen, Weijie Lyu +4
Generalizable AI-generated image (AIGI) and deepfake detection remain challenging due to the asymmetry phenomenon, where adaptation to limited training distributions can degrade th…
The Thinking Leakage in Reinforcement Learning for LLMs
Wenxuan Zhu, Shuming Liu, Bang An +4
Hybrid reasoning models such as the Qwen3 series switch between a THINK mode and a NO-THINK mode through a few chat-template tokens. A popular recipe trains such models with reinfo…
SoccerNet-FoulRet: Retrieving Semantically Similar Soccer Foul Videos
Jacobus Arthur, Ahmad Sait, Batool Hani +6
Refereeing decisions in professional soccer remain inconsistent because referees cannot easily compare a contentious foul against similar past cases. We cast this as a retrieval pr…
Self-Generated Feedback Destabilizes Test-Time Training: A Causal Decomposition of Long-Horizon Adaptation
Cheng Luo, Bing Li, Bernard Ghanem
Test-time training (TTT) lets a model store information in its weights during inference. When the model learns from its own output, however, each update also changes the model that…
Composition, Not Conversation: VLMs Lose the Scene, Not the Thread
L. D. M. S. Sai Teja, Ufaq Khan, N. Siva Gopala Krishna +5
Vision-language models (VLMs) increasingly reason over visual evidence that is cropped, segmented, retrieved, or revealed over time. Yet most VQA benchmarks present the complete im…
Advancing Video-Text Pretraining with Multi-View Captions
Fida M. Thoker, Renaud Vandeghen, Karen Sanchez +2
Video-text pretraining has achieved remarkable progress through the scaling of models and datasets, yet the quality of language supervision remains underexplored. Existing web-scal…
AlexandriaX 2026: The First Shared Task on Dialectal Arabic Machine Translation
Abdellah El Mekki, AbdelRahim A. Elmadany, Samar M. Magdy +6
Dialectal Arabic machine translation (MT) remains challenging despite recent progress in Arabic language technologies, particularly because effective translation requires modeling…
ContextFlow: In-Context Flow Matching for Robot Manipulation
Jian Ding, Xianjie Dai, Roei Herzig +5
Although highly effective in vision and language domains, applying in-context learning to robotics remains challenging. Existing autoregressive in-context imitation methods discret…
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…
B-MIM: Biased Masked Image Modeling for Generalizable Segmentation of Fine-Grained Anatomical Structures
Sebastián González, Karen Sanchez, José M. Saavedra +2
Self-supervised pretraining enables transferable representations for medical imaging, yet most CT encoders remain biased toward coarse semantic understanding, limiting their sensit…
Telco-GAIA: Bilingual Benchmark for Agents in Telecom Domain
Dmitrii Khizbullin, Zaid Alyafeai, Abdelrahman Eldesokey +4
We introduce Telco-GAIA, a bilingual, multi-modal benchmark for evaluating tool-using agents on the data of a real-world telecommunications operator. Telco-GAIA comprises 100 human…
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…
HyperGS: Fast and Generalizable Gaussian Video Representation
Fatimah Zohra, Chen Zhao, Shuming Liu +2
Gaussian Splatting has emerged as an effective representation for video, but existing methods rely on per-video optimization. This leads to slow encoding and limits generalization…
EgoPlay: Event-Triggered Video Editing for Egocentric Streams
Jinjie Mai, Gordon Guocheng Qian, Willi Menapace +8
We introduce EgoPlay, an event-triggered video-to-video editor for egocentric streams, obtained by fine-tuning a pretrained V2V diffusion transformer on event-conditioned data buil…
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…
Sparse Attention for Dense Open-Vocabulary Prediction in CLIP
Fatimah Zohra, Chen Zhao, Shuming Liu +1
Contrastive Language-Image Pre-training (CLIP) relies on softmax-based self-attention, a strictly positive distribution that assigns probability mass to every pair of tokens-even s…
SETA: Scaling Environments for Terminal Agents
Qijia Shen, Zhiqi Huang, Vamsidhar Kamanuru +19
Large language models (LLMs) are rapidly shifting toward agents that solve tasks through diverse interfaces, including web and graphical user interfaces (GUIs). Among these, the te…
SoccerNet 2026 Challenges Results
Anthony Cioppa, Silvio Giancola, Håkan Ardö +102
The SoccerNet 2026 Challenges constitute the sixth annual edition of the SoccerNet open benchmarking effort, dedicated to advancing computer vision research in sports video underst…
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…
MedCTA: A Benchmark for Clinical Tool Agents
Tajamul Ashraf, Hyewon Jeong, Fida Mohammad Thoker +1
To make clinically grounded decisions, medical AI agents are expected to go beyond simple recognition and be capable of tool retrieval, evidence acquisition, and integration. Exist…
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 the risks posed by prompt injection, indirect instructio…
FLORO: A Multimodal Geospatial Foundation Model for Ecological Remote Sensing Across Sensors and Scales
Jorge L. Rodriguez, Victor Angulo Morales, Areej Alwahas +6
Foundation models offer a promising route to transferable remote sensing representations, but many current approaches depend on very large pretraining datasets and fixed sensor con…
GoTTA be Diverse: Rethinking Memory Policies for Test-Time Adaptation
Shyma Alhuwaider, Yasmeen Alsaedy, Merey Ramazanova +2
Test-time adaptation (TTA) enables a pre-trained model to adapt online to an unlabeled test stream under distribution shift. While most TTA research focuses on the adaptation objec…
CounterCount: Diagnosing Knowledge Bias in How Vision-Language Models Count Attributes
Reem Alzahrani, Hassan Alshanqiti, Bushra Bin Hemid +4
Do Vision-Language Models (VLMs) count what they see, or what they know about the world? We introduce CounterCount, a diagnostic dataset of paired factual and counterfactual (CF) i…