Iterative Layer Pruning for Efficient Translation Inference Paper β’ 2510.22763 β’ Published Oct 26, 2025
Global PIQA: Evaluating Physical Commonsense Reasoning Across 100+ Languages and Cultures Paper β’ 2510.24081 β’ Published Oct 28, 2025 β’ 18
MeXtract: Light-Weight Metadata Extraction from Scientific Papers Paper β’ 2510.06889 β’ Published Oct 8, 2025 β’ 1
SpeechT: Findings of the First Mentorship in Speech Translation Paper β’ 2502.12050 β’ Published Feb 17, 2025 β’ 1
Bemba Speech Translation: Exploring a Low-Resource African Language Paper β’ 2505.02518 β’ Published May 5, 2025
Efficient Speech Translation through Model Compression and Knowledge Distillation Paper β’ 2505.20237 β’ Published May 26, 2025 β’ 1
Language Modelling Approaches to Adaptive Machine Translation Paper β’ 2401.14559 β’ Published Jan 25, 2024
Masader: Metadata Sourcing for Arabic Text and Speech Data Resources Paper β’ 2110.06744 β’ Published Oct 13, 2021
Rephrasing natural text data with different languages and quality levels for Large Language Model pre-training Paper β’ 2410.20796 β’ Published Oct 28, 2024
Ashaar: Automatic Analysis and Generation of Arabic Poetry Using Deep Learning Approaches Paper β’ 2307.06218 β’ Published Jul 12, 2023
MOLE: Metadata Extraction and Validation in Scientific Papers Using LLMs Paper β’ 2505.19800 β’ Published May 26, 2025 β’ 2
On the Limitations of Vision-Language Models in Understanding Image Transforms Paper β’ 2503.09837 β’ Published Mar 12, 2025 β’ 10
view post Post 6438 πAraClip is now fully integrated with Hugging Face π€AraClip is a specialized CLIP model that was created by @pain and optimized for Arabic text-image retrieval tasksπ₯π Try it out ππ€ model: Arabic-Clip/araclipπ§© Gradio demo: Arabic-Clip/Araclip-Simplifiedπ website: https://arabic-clip.github.io/Arabic-CLIP/ See translation 2 replies Β· π₯ 5 5 β€οΈ 3 3 π 1 1 + Reply
EASY: Ensemble Augmented-Shot Y-shaped Learning: State-Of-The-Art Few-Shot Classification with Simple Ingredients Paper β’ 2201.09699 β’ Published Jan 24, 2022 β’ 2
ProKeR: A Kernel Perspective on Few-Shot Adaptation of Large Vision-Language Models Paper β’ 2501.11175 β’ Published Jan 19, 2025 β’ 3