Vectorless: open-source PDF chatbot without RAG
news.ycombinator.com·1d·
Discuss: Hacker News
✨UI generation
Accelerating Video Quality Control at Netflix with Pixel Error Detection
netflixtechblog.com·1d·
Discuss: Hacker News
🧠AI
Self-Avoiding Walk
en.wikipedia.org·1d·
Discuss: Hacker News
🤝Multi-Agent Systems
Launch HN: Design Arena (YC S25) – Head-to-Head AI Benchmark for Aesthetics
news.ycombinator.com·8h·
Discuss: Hacker News
✨UI generation
Diffusion Language Models Are Super Data Learners
jinjieni.notion.site·3d·
Discuss: Hacker News, Hacker News
🧠AI
Evaluating LLMs Playing Text Adventures
entropicthoughts.com·8h·
Discuss: Lobsters, Hacker News
🧠AI
The Beauty of Anisotropic Mesh Refinement: Omnitrees for Efficient Dyadic Discretizations
arxiv.org·1d
✨UI generation
KIRETT: Knowledge-Graph-Based Smart Treatment Assistant for Intelligent Rescue Operations
arxiv.org·20h
🧠AI
ASLSL: Adaptive shared latent structure learning with incomplete multi-modal physiological data for multi-dimensional emotional feature selection
arxiv.org·1d
🧠AI
Open-Source Agentic Hybrid RAG Framework for Scientific Literature Review
arxiv.org·1d
🕷️GraphRAG
How Effectively Can Large Language Models Connect SNP Variants and ECG Phenotypes for Cardiovascular Risk Prediction?
arxiv.org·20h
🧠AI
Explaining Similarity in Vision-Language Encoders with Weighted Banzhaf Interactions
arxiv.org·4d
🎛️interfaces
ClimateSOM: A Visual Analysis Workflow for Climate Ensemble Datasets
arxiv.org·20h
✨UI generation
CISO: Species Distribution Modeling Conditioned on Incomplete Species Observations
arxiv.org·20h
🤝Multi-Agent Systems
Onsager Principle-Based Domain Embedding for Thermodynamically Consistent Cahn-Hilliard Model in Arbitrary Domain
arxiv.org·20h
🗃️databases
Parametric Matrix Models
nature.com·5d·
Discuss: Hacker News
🤝Multi-Agent Systems
BharatBBQ: A Multilingual Bias Benchmark for Question Answering in the Indian Context
arxiv.org·20h
✨UI generation
Investigating Intersectional Bias in Large Language Models using Confidence Disparities in Coreference Resolution
arxiv.org·20h
✨UI generation
Deep Ignorance: Filtering Pretraining Data Builds Tamper-Resistant Safeguards into Open-Weight LLMs
arxiv.org·20h
🧠AI
VQAThinker: Exploring Generalizable and Explainable Video Quality Assessment via Reinforcement Learning
arxiv.org·1d
🧠AI