Hala Technical Report: Building Arabic-Centric Instruction & Translation Models at Scale
Paper • 2509.14008 • Published • 90
IVUL-KAUST Papers
-
-
Beyond the Last Answer: Your Reasoning Trace Uncovers More than You Think
Paper • 2504.20708 • Published • 23 -
CAMEL: Communicative Agents for "Mind" Exploration of Large Scale Language Model Society
Paper • 2303.17760 • Published • 1 -
4D-Bench: Benchmarking Multi-modal Large Language Models for 4D Object Understanding
Paper • 2503.17827 • Published • 8 -
DiffCLIP: Differential Attention Meets CLIP
Paper • 2503.06626 • Published • 5 -
Towards Data-Efficient Pretraining for Atomic Property Prediction
Paper • 2502.11085 • Published • 3 -
Model Merging and Safety Alignment: One Bad Model Spoils the Bunch
Paper • 2406.14563 • Published • 30 -
SynthCLIP: Are We Ready for a Fully Synthetic CLIP Training?
Paper • 2402.01832 • Published • 6 -
Rapid Adaptation in Online Continual Learning: Are We Evaluating It Right?
Paper • 2305.09275 • Published • 1 -
Structured-Noise Masked Modeling for Video, Audio and Beyond
Paper • 2503.16311 • Published • 1 -
Privacy-preserving Optics for Enhancing Protection in Face De-identification
Paper • 2404.00777 • Published • 1 -
ColorMAE: Exploring data-independent masking strategies in Masked AutoEncoders
Paper • 2407.13036 • Published • 4 -
OpenTAD: A Unified Framework and Comprehensive Study of Temporal Action Detection
Paper • 2502.20361 • Published • 1 -
Vivid-ZOO: Multi-View Video Generation with Diffusion Model
Paper • 2406.08659 • Published • 8 -
SCTN: Sparse Convolution-Transformer Network for Scene Flow Estimation
Paper • 2105.04447 • Published • 1 -
AniGAN: Style-Guided Generative Adversarial Networks for Unsupervised Anime Face Generation
Paper • 2102.12593 • Published • 1 -
Automatic Animation of Hair Blowing in Still Portrait Photos
Paper • 2309.14207 • Published -
BOLT: Boost Large Vision-Language Model Without Training for Long-form Video Understanding
Paper • 2503.21483 • Published • 1 -
MOLE: Metadata Extraction and Validation in Scientific Papers Using LLMs
Paper • 2505.19800 • Published • 2 -
An Embarrassingly Simple Defense Against LLM Abliteration Attacks
Paper • 2505.19056 • Published • 6 -
Motion-Aware Concept Alignment for Consistent Video Editing
Paper • 2506.01004 • Published • 8 -
OmniResponse: Online Multimodal Conversational Response Generation in Dyadic Interactions
Paper • 2505.21724 • Published • 5 -
MatchDiffusion: Training-free Generation of Match-cuts
Paper • 2411.18677 • Published • 1 -
UnMix-NeRF: Spectral Unmixing Meets Neural Radiance Fields
Paper • 2506.21884 • Published • 13 -
Train Long, Think Short: Curriculum Learning for Efficient Reasoning
Paper • 2508.08940 • Published • 27 -
Turning the Spell Around: Lightweight Alignment Amplification via Rank-One Safety Injection
Paper • 2508.20766 • Published • 14 -
Reasoning Vectors: Transferring Chain-of-Thought Capabilities via Task Arithmetic
Paper • 2509.01363 • Published • 61 -
Mind-the-Glitch: Visual Correspondence for Detecting Inconsistencies in Subject-Driven Generation
Paper • 2509.21989 • Published • 23 -
MeXtract: Light-Weight Metadata Extraction from Scientific Papers
Paper • 2510.06889 • Published • 1 -
AraLingBench A Human-Annotated Benchmark for Evaluating Arabic Linguistic Capabilities of Large Language Models
Paper • 2511.14295 • Published • 74 -
End-to-End Temporal Action Detection with 1B Parameters Across 1000 Frames
Paper • 2311.17241 • Published