Mubeen AI: A Specialized Arabic Language Model for Heritage Preservation and User Intent Understanding
arxiv.org·1d
🤖Paleographic ML
Flag this post
Beyond the Magic: How LLMs Work
💻Local LLMs
Flag this post
Wednesday 26 November - 11am
informatics.ed.ac.uk·23h
🎵Audio ML
Flag this post
New Dataset PerSense-D Enables Model-Agnostic Dense Object Segmentation
hackernoon.com·13h
📊Learned Metrics
Flag this post
Everything You Need to Know About Character AI
🎙️Whisper
Flag this post
Algorithmic Bias Mitigation via Contrastive Fairness Learning with Adaptive Data Augmentation
📊Learned Metrics
Flag this post
SPARTA: Evaluating Reasoning Segmentation Robustness through Black-Box Adversarial Paraphrasing in Text Autoencoder Latent Space
arxiv.org·4h
🧠Machine Learning
Flag this post
CURVETE: Curriculum Learning and Progressive Self-supervised Training for Medical Image Classification
arxiv.org·1d
🌀Differential Geometry
Flag this post
Sparse Adaptive Attention “MoE”: How I Solved OpenAI’s $650B Problem With a £700 GPU
🌊Streaming Algorithms
Flag this post
Amazon Nova Multimodal Embeddings: State-of-the-art embedding model for agentic RAG and semantic search
🧮Vector Embeddings
Flag this post
Advancing cybersecurity a comprehensive review of AI-driven detection techniques
🎯Threat Hunting
Flag this post
Do We Still Need OCR?
🤖Advanced OCR
Flag this post
ARES: Multimodal Adaptive Reasoning via Difficulty-Aware Token-Level EntropyShaping
⚡Proof Automation
Flag this post
Quantifying the Effects of Word Length, Frequency, and Predictability on Dyslexia
arxiv.org·4h
🧠Intelligence Compression
Flag this post
DeepSeek-OCR: Images Simplify Text for Large Language Models
heise.de·4d
🤖Advanced OCR
Flag this post
Long-Context Modeling with Dynamic Hierarchical Sparse Attention for On-Device LLMs
arxiv.org·4h
💻Local LLMs
Flag this post
Abjad AI at NADI 2025: CATT-Whisper: Multimodal Diacritic Restoration Using Text and Speech Representations
arxiv.org·4h
🎙️Whisper
Flag this post
Loading...Loading more...