Status II
andyjohnson.uk·4h
📄Document Digitization
Generative Art
4rknova.com·1d·
Discuss: Hacker News
📐Mathematical Art
Mathematical model of memory suggests 7 senses are optimal
skoltech.ru·1d·
Discuss: Hacker News
🔲Cellular Automata
InferenceMAX: Open-Source Inference Benchmarking
newsletter.semianalysis.com·18h·
Discuss: Hacker News
📊Performance Profiling
Opinion | The A.I. Prompt That Could End the World
future.forem.com·4h·
Discuss: DEV
🤖AI Curation
Sub-Field Selection & Research Topic Generation:
dev.to·19h·
Discuss: DEV
🌀Differential Geometry
Which Heads Matter for Reasoning? RL-Guided KV Cache Compression
arxiv.org·13h
📼Cassette Combinators
DeepEN: Personalized Enteral Nutrition for Critically Ill Patients using Deep Reinforcement Learning
arxiv.org·13h
🧠Machine Learning
Latency vs. Accuracy for LLM Apps — How to Choose and How a Memory Layer Lets You Win Both
dev.to·3d·
Discuss: DEV
⚡Performance Mythology
PEaRL: Pathway-Enhanced Representation Learning for Gene and Pathway Expression Prediction from Histology
arxiv.org·3d
📐Vector Dimensionality
Visual Representations inside the Language Model
arxiv.org·3d
🧮Vector Embeddings
Decrypt Modality Gap in Multimodal Contrastive Learning: From Convergent Representation to Pair Alignment
arxiv.org·3d
🧠Machine Learning
Compressed Convolutional Attention: Efficient Attention in a Compressed Latent Space
arxiv.org·3d
⧗Information Bottleneck
InstaGeo: Compute-Efficient Geospatial Machine Learning from Data to Deployment
arxiv.org·2d
🔶Voronoi Diagrams
Efficient Conditional Generation on Scale-based Visual Autoregressive Models
arxiv.org·2d
📊Learned Metrics
Making Machines Sound Sarcastic: LLM-Enhanced and Retrieval-Guided Sarcastic Speech Synthesis
arxiv.org·1d
🎙️Whisper
RareGraph-Synth: Knowledge-Guided Diffusion Models for Generating Privacy-Preserving Synthetic Patient Trajectories in Ultra-Rare Diseases
arxiv.org·1d
🔒Privacy Archives
Scaling LLM Multi-turn RL with End-to-end Summarization-based Context Management
arxiv.org·1d
💻Local LLMs
Enhanced SoC Design via Adaptive Topology Optimization with Reinforcement Learning
dev.to·14h·
Discuss: DEV
🧩RISC-V
Krish Naik: Complete RAG Crash Course With Langchain In 2 Hours
dev.to·21h·
Discuss: DEV
📊Multi-vector RAG