🗄️ Vector Databases - yfff · Scour

al1-nasir/LocalForge: Self-hosted AI control plane for intelligent local LLM orchestration. OpenAI-compatible API · ML-powered multi-model routing · LoRA finetuning · vector memory · RAG 🧠LLM

github.com·1d·Hacker News

Hyperboloid GPLVM for Discovering Continuous Hierarchies via Nonparametric Estimation 📐Optimization Theory

OThink-SRR1: Search, Refine and Reasoning with Reinforced Learning for Large Language Models 💬LLMs

Show HN: Dynamic Hybrid Search That Beats Pure Dense and Fixed Hybrid 🧠LLM

github.com·4d·Hacker News

Knowledge Capsules: Structured Nonparametric Memory Units for LLMs 💬LLMs

Collaborative Filtering Through Weighted Similarities of User and Item Embeddings 🎮Reinforcement Learning

Spectral Embeddings Leak Graph Topology: Theory, Benchmark, and Adaptive Reconstruction 📐Linear Algebra

Towards Universal Tabular Embeddings: A Benchmark Across Data Tasks 🧠LLM

suyash333/india-ai-ecosystem: Discover 110+ AI applications built for India's 1.4 billion users — covering 28 sectors, 22 languages, and a rapidly maturing startup landscape. 🤖AI

github.com·6d·Hacker News

All Languages Matter: Understanding and Mitigating Language Bias in Multilingual RAG 🧠LLM

Learning Behaviorally Grounded Item Embeddings via Personalized Temporal Contexts 💬LLMs

DWTSumm: Discrete Wavelet Transform for Document Summarization 💬LLMs

Self-Describing Structured Data with Dual-Layer Guidance: A Lightweight Alternative to RAG for Precision Retrieval in Large-Scale LLM Knowledge Navigation 💬LLMs

CHOP: Chunkwise Context-Preserving Framework for RAG on Multi Documents 💬LLMs

ESGLens: An LLM-Based RAG Framework for Interactive ESG Report Analysis and Score Prediction 🧠LLM

Matlas: A Semantic Search Engine for Mathematics 💬LLMs

Convergent Evolution: How Different Language Models Learn Similar Number Representations 🧠LLM

arxiv.org·2d·Hacker News

Meta Additive Model: Interpretable Sparse Learning With Auto Weighting 🗜️Compressed Sensing

Mira-Embeddings-V1: Domain-Adapted Semantic Reranking for Recruitment via LLM-Synthesized Data 🧠LLM

MMCORE: MultiModal COnnection with Representation Aligned Latent Embeddings 💬LLMs

Log in to enable infinite scrolling