Microsoft AI’s first in-house image generator MAI-Image-1 is now available
🎧Learned Audio
Flag this post
[D][P] PKBoost v2 is out! An entropy-guided boosting library with a focus on drift adaptation and multiclass/regression support.
🌀Brotli Dictionary
Flag this post
Readable Code Is Unreadable
📊APL Heritage
Flag this post
AI Summarization Optimization
📊Feed Optimization
Flag this post
Good abstractions for humans turn out to be good abstractions for LLMs
✨Effect Handlers
Flag this post
AI Progress Should Be Measured by Capability-Per-Resource, Not Scale Alone: A Framework for Gradient-Guided Resource Allocation in LLMs
arxiv.org·19h
🧠Intelligence Compression
Flag this post
HyFormer-Net: A Synergistic CNN-Transformer with Interpretable Multi-Scale Fusion for Breast Lesion Segmentation and Classification in Ultrasound Images
arxiv.org·19h
🧠Machine Learning
Flag this post
Cross-Corpus Validation of Speech Emotion Recognition in Urdu using Domain-Knowledge Acoustic Features
arxiv.org·1d
🎵Audio ML
Flag this post
"Less is More": Reducing Cognitive Load and Task Drift in Real-Time Multimodal Assistive Agents for the Visually Impaired
arxiv.org·19h
✋Tactile Computing
Flag this post
Hyper Hawkes Processes: Interpretable Models of Marked Temporal Point Processes
arxiv.org·19h
🔍Vector Forensics
Flag this post
FreeSliders: Training-Free, Modality-Agnostic Concept Sliders for Fine-Grained Diffusion Control in Images, Audio, and Video
arxiv.org·19h
📊Learned Metrics
Flag this post
Ariadne: A Controllable Framework for Probing and Extending VLM Reasoning Boundaries
arxiv.org·19h
🎯Proof Tactics
Flag this post
MedRECT: A Medical Reasoning Benchmark for Error Correction in Clinical Texts
arxiv.org·19h
✅Format Verification
Flag this post
Wave-Particle (Continuous-Discrete) Dualistic Visual Tokenization for Unified Understanding and Generation
arxiv.org·19h
🤖Advanced OCR
Flag this post
Generative human motion mimicking through feature extraction in denoising diffusion settings
arxiv.org·19h
📊Learned Metrics
Flag this post
Loquetier: A Virtualized Multi-LoRA Framework for Unified LLM Fine-tuning and Serving
arxiv.org·19h
💻Local LLMs
Flag this post
ParaScopes: What do Language Models Activations Encode About Future Text?
arxiv.org·19h
🔗Monadic Parsing
Flag this post
Loading...Loading more...