BG
Bernard Ghanem
cs.CVcs.LGcs.AIcs.CLcs.CReess.IVstat.MLcs.ROcs.MMmath.OC
On Valency
published · living versionsW_akpmrw4a·v1 · currentpublished
VidDub: Replacement-Aware Distillation for Two-Step Video Dubbing
with Yexin Liu, Yunlong Lin, Zehan Wang, Guangxin He +9
1 version
W_y957pfby·v1published
Preprints & journals
318 papers in the corpus · 2011–2026ShadowNet for Data-Centric Quantum System Learning.42599854 · Du, Yuxuan, Yang, Yibo, Liu, Tongliang et al.2026 · 1 citationIEEE transactions on pattern analysis and machine intelligence. 2026;48(11):15506-15522
Self-Distillation for Supervised Fine-Tuning2610.25497v1 · Wenxuan Zhu, Bang An, Shuming Liu et al.2026 · 0 citationsarXivon Valency
COMPASS: Contextual Moment Prior Alignment for Generalizable AIGI Detection2610.18034v1 · Zhan Yang, Tiancheng Shen, Weijie Lyu et al.2026 · 0 citationsarXiv
APEX-Harm: Evaluating Agent Safety in Shared Professional Workspaces2610.13623v1 · Ziyi Yang, Adel Bibi, Guohao Li et al.2026 · 0 citationsarXiv
The Thinking Leakage in Reinforcement Learning for LLMs2610.14270v1 · Wenxuan Zhu, Shuming Liu, Bang An et al.2026 · 0 citationsarXiv
SoccerNet-FoulRet: Retrieving Semantically Similar Soccer Foul Videos2610.09742v2 · Jacobus Arthur, Ahmad Sait, Batool Hani et al.2026 · 0 citationsarXiv
Self-Generated Feedback Destabilizes Test-Time Training: A Causal Decomposition of Long-Horizon Adaptation2610.05076v1 · Cheng Luo, Bing Li, Bernard Ghanem2026 · 0 citationsarXiv
Composition, Not Conversation: VLMs Lose the Scene, Not the Thread2609.38368v1 · L. D. M. S. Sai Teja, Ufaq Khan, N. Siva Gopala Krishna et al.2026 · 0 citationsarXiv
Advancing Video-Text Pretraining with Multi-View Captions2609.35090v1 · Fida M. Thoker, Renaud Vandeghen, Karen Sanchez et al.2026 · 0 citationsarXiv
AlexandriaX 2026: The First Shared Task on Dialectal Arabic Machine Translation2609.22796v1 · Abdellah El Mekki, AbdelRahim A. Elmadany, Samar M. Magdy et al.2026 · 0 citationsarXiv
ContextFlow: In-Context Flow Matching for Robot Manipulation2609.06852v1 · Jian Ding, Xianjie Dai, Roei Herzig et al.2026 · 0 citationsarXiv
B-MIM: Biased Masked Image Modeling for Generalizable Segmentation of Fine-Grained Anatomical Structures2608.24364v1 · Sebasti'an Gonz'alez, Karen Sanchez, Jos'e M. Saavedra et al.2026 · 0 citationsarXiv
DiSCO: Defending text-to-image generation through distribution-guided contrastive prompt optimization2608.17067v1 · Tong Zhang, Motasem Alfarra, Carlos Hinojosa et al.2026 · 0 citationsarXiv
EgoPlay: Event-Triggered Video Editing for Egocentric Streams2607.24560v1 · Jinjie Mai, Gordon Guocheng Qian, Willi Menapace et al.2026 · 0 citationsarXiv
HyperSafe: Inference-Time Safety Recovery for Fine-Tuned Language Models2607.11475v1 · Aznaur Aliev, Carlos Hinojosa, Abdelrahman Eldesokey et al.2026 · 0 citationsarXiv
HyperGS: Fast and Generalizable Gaussian Video Representation2607.11500v2 · Fatimah Zohra, Chen Zhao, Shuming Liu et al.2026 · 0 citationsarXiv
SETA: Scaling Environments for Terminal Agents2607.10891v2 · Qijia Shen, Zhiqi Huang, Vamsidhar Kamanuru et al.2026 · 0 citationsarXiv
Sparse Attention for Dense Open-Vocabulary Prediction in CLIP2607.07135v2 · Fatimah Zohra, Chen Zhao, Shuming Liu et al.2026 · 0 citationsarXiv
SoccerNet 2026 Challenges Results2607.07320v1 · Anthony Cioppa, Silvio Giancola, H\aakan Ardo et al.2026 · 3 citationsarXiv
Telco-GAIA: Bilingual Benchmark for Agents in Telecom Domain2607.20510v2 · Dmitrii Khizbullin, Zaid Alyafeai, Abdelrahman Eldesokey et al.2026 · 0 citationsarXiv
Defending Against Harmful Supervision Hidden in Benign Samples2606.30263v1 · Bang An, Yibo Yang, Dandan Guo et al.2026 · 0 citationsarXiv
GoTTA be Diverse: Rethinking Memory Policies for Test-Time Adaptation2605.19890v1 · Shyma Alhuwaider, Yasmeen Alsaedy, Merey Ramazanova et al.2026 · 0 citationsarXiv
CounterCount: Diagnosing Knowledge Bias in How Vision-Language Models Count Attributes2605.17826v2 · Reem Alzahrani, Bushra Bin Hemid, Hassan Alshanqiti et al.2026 · 0 citationsarXiv
Skill-Aligned Annotation for Reliable Evaluation in Text-to-Image Generation2605.13223v1 · Abdelrahman Eldesokey, Merey Ramazanova, Ahmad Sait et al.2026 · 0 citationsarXiv
SoccerLens: Grounded Soccer Video Understanding Beyond Accuracy2605.09598v2 · Ismael Elsharkawi, Ahmed Sait, Silvio Giancola et al.2026 · 0 citationsarXiv
NearID: Identity Representation Learning via Near-identity Distractors2604.01973v2 · Aleksandar Cvejic, Rameen Abdal, Abdelrahman Eldesokey et al.2026 · 0 citationsComputer Vision - ECCV 2026, LNCS 17015, pp. 427-446, Springer 2026
TrackMAE: Video Representation Learning via Track Mask and Predict2603.27268v1 · Renaud Vandeghen, Fida Mohammad Thoker, Marc Van Droogenbroeck et al.2026 · 0 citationsarXiv
TAPS: Task Aware Proposal Distributions for Speculative Sampling2603.27027v1 · Mohamad Zbib, Mohamad Bazzi, Ammar Mohanna et al.2026 · 0 citationsarXiv
QuanBench+: A Unified Multi-Framework Benchmark for LLM-Based Quantum Code Generation2604.08570v2 · Ali Slim, Haydar Hamieh, Jawad Kotaich et al.2026 · 0 citationsarXiv
SAVeS: Steering Safety Judgments in Vision-Language Models via Semantic Cues2603.19092v1 · Carlos Hinojosa, Clemens Grange, Bernard Ghanem2026 · 0 citationsarXiv
ReactMotion: Generating Reactive Listener Motions from Speaker Utterance2603.15083v1 · Cheng Luo, Bizhu Wu, Bing Li et al.2026 · 0 citationsarXiv
CURE: Curriculum-guided Multi-task Training for Reliable Anatomy Grounded Report Generation2601.15408v2 · Pablo Messina, Andr'es Villa, Juan Le'on Alc'azar et al.2026 · 0 citationsProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2026, pp. 36279-36289
VideoAuto-R1: Video Auto Reasoning via Thinking Once, Answering Twice2601.05175v2 · Shuming Liu, Mingchen Zhuge, Changsheng Zhao et al.2026 · 0 citationsarXiv
-CLIP: Text-Conditioned Contrastive Learning for Multi-Granular Vision-Language Alignment2512.12678v2 · Fatimah Zohra, Chen Zhao, Hani Itani et al.2025 · 0 citationsarXiv
CAPTAIN: Semantic Feature Injection for Memorization Mitigation in Text-to-Image Diffusion Models2512.10655v1 · Tong Zhang, Carlos Hinojosa, Bernard Ghanem2025 · 0 citationsarXiv
Unforgotten Safety: Preserving Safety Alignment of Large Language Models with Continual Learning2512.10150v1 · Lama Alssum, Hani Itani, Hasan Abed Al Kader Hammoud et al.2025 · 1 citationarXiv
Forget Less, Retain More: A Lightweight Regularizer for Rehearsal-Based Continual Learning2512.01818v1 · Lama Alssum, Hasan Abed Al Kader Hammoud, Motasem Alfarra et al.2025 · 0 citationsarXiv
AraLingBench A Human-Annotated Benchmark for Evaluating Arabic Linguistic Capabilities of Large Language Models2511.14295v2 · Mohammad Zbeeb, Hasan Abed Al Kader Hammoud, Sina Mukalled et al.2025 · 1 citationarXiv
Pixels or Positions? Benchmarking Modalities in Group Activity Recognition2511.12606v3 · Drishya Karki, Merey Ramazanova, Anthony Cioppa et al.2025 · 0 citationsarXiv
Ego4D: Around the World in 3,600 Hours of Egocentric Video.39058617 · Grauman, Kristen, Westbury, Andrew, Byrne, Eugene et al.2025 · 16 citationsIEEE transactions on pattern analysis and machine intelligence. 2025;47(11):9468-9509
A data-driven approach to interfacial polymerization exploiting machine learning for predicting thin-film composite membrane formation.41002654 · Ignacz, Gergo, Baig, Muhammad Irshad, Gopalsamy, Karuppasamy et al.2025 · 18 citationsMaterials horizons. 2025;12(21):9009-9025
Mitigating Model Merging Conflicts via Knowledge-Aware Task Vector Purification2510.14697v2 · Bang An, Yibo Yang, Philip Torr et al.2025 · 0 citationsarXiv
Multimodal Safety Evaluation in Generative Agent Social Simulations2510.07709v1 · Alhim Vera, Karen Sanchez, Carlos Hinojosa et al.2025 · 0 citationsarXiv
MeXtract: Light-Weight Metadata Extraction from Scientific Papers2510.06889v1 · Zaid Alyafeai, Maged S. Al-Shaibani, Bernard Ghanem2025 · 0 citationsarXiv
Mind-the-Glitch: Visual Correspondence for Detecting Inconsistencies in Subject-Driven Generation2509.21989v1 · Abdelrahman Eldesokey, Aleksandar Cvejic, Bernard Ghanem et al.2025 · 0 citationsarXiv
Hala Technical Report: Building Arabic-Centric Instruction & Translation Models at Scale2509.14008v1 · Hasan Abed Al Kader Hammoud, Mohammad Zbeeb, Bernard Ghanem2025 · 0 citationsarXiv
ResidualViT for Efficient Temporally Dense Video Encoding2509.13255v1 · Mattia Soldan, Fabian Caba Heilbron, Bernard Ghanem et al.2025 · 0 citationsarXiv
Loong: Synthesize Long Chain-of-Thoughts at Scale through Verifiers2509.03059v2 · Xingyue Huang, Rishabh, Gregor Franke et al.2025 · 0 citationsarXiv
ADVMEM: Adversarial Memory Initialization for Realistic Test-Time Adaptation via Tracklet-Based Benchmarking2509.02182v1 · Shyma Alhuwaider, Motasem Alfarra, Juan C. Perez et al.2025 · 0 citationsarXiv
Imitate Optimal Policy: Prevail and Induce Action Collapse in Policy Gradient2509.02737v1 · Zhongzhu Zhou, Yibo Yang, Ziyan Chen et al.2025 · 0 citationsarXiv
Career total: 485 works. 318 are in this corpus.Showing the 50 most recent.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.