Image and Video Understanding Lab

university

https://ivul.kaust.edu.sa/

Activity Feed Request to join this org

AI & ML interests

Video Understanding; 3D Computer Vision; Continual Learning; AI Safety; Graph Neural Networks; Agentic AI; AI4Science

Recent Activity

sming256 authored a paper 9 days ago

The Thinking Leakage in Reinforcement Learning for LLMs

vxuanz submitted a paper 10 days ago

The Thinking Leakage in Reinforcement Learning for LLMs

zbeeb authored a paper 12 days ago

Arabic Safety Alignment as Selective Refusal: An Empirical Study of SFT, DPO, and Guard Calibration

View all activity

Papers

TAPS: Task Aware Proposal Distributions for Speculative Sampling

CAPTAIN: Semantic Feature Injection for Memorization Mitigation in Text-to-Image Diffusion Models

View all Papers

authored a paper 9 days ago

The Thinking Leakage in Reinforcement Learning for LLMs

Paper • 2610.14270 • Published 16 days ago • 33

submitted a paper to Daily Papers 10 days ago

The Thinking Leakage in Reinforcement Learning for LLMs

Paper • 2610.14270 • Published 16 days ago • 33

authored a paper 12 days ago

Arabic Safety Alignment as Selective Refusal: An Empirical Study of SFT, DPO, and Guard Calibration

Paper • 2608.29378 • Published Aug 29

authored a paper 2 months ago

DiSCO: Defending text-to-image generation through distribution-guided contrastive prompt optimization

Paper • 2608.17067 • Published Aug 17 • 23

submitted a paper to Daily Papers 2 months ago

DiSCO: Defending text-to-image generation through distribution-guided contrastive prompt optimization

Paper • 2608.17067 • Published Aug 17 • 23

updated a dataset 5 months ago

IVUL-KAUST/MedCTA

Viewer • Updated May 24 • 107 • 366 • 2

published a dataset 5 months ago

IVUL-KAUST/MedCTA

Viewer • Updated May 24 • 107 • 366 • 2

Zaid

updated a dataset 5 months ago

IVUL-KAUST/mextract_dpo_filtered_errors

Viewer • Updated May 21 • 541 • 12

Zaid

published a dataset 5 months ago

IVUL-KAUST/mextract_dpo_filtered_errors

Viewer • Updated May 21 • 541 • 12

authored 2 papers 6 months ago

Neural Computers

Paper • 2604.06425 • Published Apr 7 • 30

Small Vision-Language Models are Smart Compressors for Long Video Understanding

Paper • 2604.08120 • Published Apr 9 • 20

authored a paper 7 months ago

TAPS: Task Aware Proposal Distributions for Speculative Sampling

Paper • 2603.27027 • Published Mar 27 • 146

authored a paper 7 months ago

TAPS: Task Aware Proposal Distributions for Speculative Sampling

Paper • 2603.27027 • Published Mar 27 • 146

submitted a paper to Daily Papers 7 months ago

TAPS: Task Aware Proposal Distributions for Speculative Sampling

Paper • 2603.27027 • Published Mar 27 • 146

authored a paper 7 months ago

ReactMotion: Generating Reactive Listener Motions from Speaker Utterance

Paper • 2603.15083 • Published Mar 16 • 24

submitted a paper to Daily Papers 7 months ago

ReactMotion: Generating Reactive Listener Motions from Speaker Utterance

Paper • 2603.15083 • Published Mar 16 • 24

authored a paper 7 months ago

Generative Visual Chain-of-Thought for Image Editing

Paper • 2603.01893 • Published Mar 2 • 1

authored 3 papers 9 months ago

Mindstorms in Natural Language-Based Societies of Mind

Paper • 2305.17066 • Published May 26, 2023 • 4

ColorMAE: Exploring data-independent masking strategies in Masked AutoEncoders

Paper • 2407.13036 • Published Jul 17, 2024 • 4

Mixture of States: Routing Token-Level Dynamics for Multimodal Generation

Paper • 2511.12207 • Published Nov 15, 2025 • 10