Google's Imagen 4 text-to-image model promises 'significantly improved' boring images
engadget.comΒ·23h
πŸ“ΈTIFF Evolution
Experimenting with Apple’s AI models inside Shortcuts
sixcolors.comΒ·19h
⚑Proof Automation
The most efficient algorithm for detecting claws in general graphs, with a runtime of O(m Ξ”) β€” where m is the number of edges and Ξ” is the maximum degree β€” is n...
dev.toΒ·1dΒ·
Discuss: DEV
πŸ”—Topological Sorting
The Internal Inconsistency of Large Language Models
blog.kortlepel.comΒ·1dΒ·
Discuss: Hacker News
πŸ’»Local LLMs
Which Vision Language Models Should You Use for Your Apps
thenewstack.ioΒ·2d
πŸ€–Advanced OCR
Memory-Augmented Incomplete Multimodal Survival Prediction via Cross-Slide and Gene-Attentive Hypergraph Learning
arxiv.orgΒ·1d
🧠Machine Learning
General Methods Make Great Domain-specific Foundation Models: A Case-study on Fetal Ultrasound
arxiv.orgΒ·1d
πŸ“ŠLearned Metrics
UltraAD: Fine-Grained Ultrasound Anomaly Classification via Few-Shot CLIP Adaptation
arxiv.orgΒ·1d
🧠Machine Learning
CPAM: Context-Preserving Adaptive Manipulation for Zero-Shot Real Image Editing
arxiv.orgΒ·2d
πŸ“„Document Digitization
StoryGem: Voronoi treemap Approach for Semantics-Preserving Text Visualization
arxiv.orgΒ·2d
πŸ”ΆVoronoi Diagrams
BPCLIP: A Bottom-up Image Quality Assessment from Distortion to Semantics Based on CLIP
arxiv.orgΒ·2d
πŸ–ΌοΈJPEG XL
Brain Mapping with Dense Features: Grounding Cortical Semantic Selectivity in Natural Images With Vision Transformers
arxiv.orgΒ·1d
πŸ“ŠLearned Metrics
Scaffolding Dexterous Manipulation with Vision-Language Models
arxiv.orgΒ·1d
πŸ€–Advanced OCR
MTSIC: Multi-stage Transformer-based GAN for Spectral Infrared Image Colorization
arxiv.orgΒ·2d
🧠Neural Codecs
Language Modeling by Language Models
arxiv.orgΒ·6h
πŸ€–Grammar Induction
CBF-AFA: Chunk-Based Multi-SSL Fusion for Automatic Fluency Assessment
arxiv.orgΒ·6h
πŸŽ™οΈWhisper
COIN: Uncertainty-Guarding Selective Question Answering for Foundation Models with Provable Risk Guarantees
arxiv.orgΒ·6h
🧠Intelligence Compression
QuranMorph: Morphologically Annotated Quranic Corpus
arxiv.orgΒ·2d
πŸ“‹Document Grammar
PDF Retrieval Augmented Question Answering
arxiv.orgΒ·2d
πŸ“ŠMulti-vector RAG
SACL: Understanding and Combating Textual Bias in Code Retrieval with Semantic-Augmented Reranking and Localization
arxiv.orgΒ·6h
πŸ”BitFunnel