💬 NLP - aibrain0x01 · Scour

matthewworner/spike: Spike is a weight block pager for large language models. 📝LLMs

github.com·6d·Hacker News

Market Trend Analysis: The Impact of Recent Advances on the Large Language Model Evaluation As A Service Market 📝LLMs

Prompting language influences diagnostic reasoning and accuracy of large language models 📝LLMs

chiennv2000/orthrus: Fast, lossless LLM inference via dual-view diffusion decoding. 📝LLMs

github.com·5d·Hacker News

ReacTOD: Bounded Neuro-Symbolic Agentic NLU for Zero-Shot Dialogue State Tracking 📝LLMs

Autonomous AI needs safeguards beyond model-level guardrails, study finds 🛡️AI Safety

tech.yahoo.com·2d

ERFSL: An Efficient Reward Function Searcher via Language Models for Custom-Environment Multi-Objective Optimization (Student Abstract) 🎮Reinforcement Learning

MelikaSepidband/Code-Generation-Complexity-Metrics 📝LLMs

Multilingual jailbreaking of LLMs using low-resource languages 📝LLMs

MegaTrain Full Precision Training of 100B+ Parameter LLMs on a Single GPU ⚙️MLOps

github.com·3d·Hacker News

From Node2Vec to GPT-based GraphRAG: scientific impact prediction across graph and language models 🔍RAG

Enhancing Metacognitive AI: Knowledge-Graph Population with Graph-Theoretic LLM Enrichment 📝LLMs

Traditional statistical representations outperform generative AI in identifying expert peer reviewers ✨Generative AI

A Hormone-inspired Emotion Layer for Transformer language models (HELT) ⚙️Transformers

DMN: A Compositional Framework for Jailbreaking Multimodal LLMs with Multi-Image Inputs 📝LLMs

Language Models as Efficient Reward Function Searchers for Custom-Environment Multi-Objective Reinforcement 🎮Reinforcement Learning

Graphs of Research: Citation Evolution Graphs as Supervision for Research Idea Generation ✨Generative AI

Babel: Jailbreaking Safety Attention via Obfuscation Distribution Optimized Sampling 📝LLMs

VerifyMAS: Hypothesis Verification for Failure Attribution in LLM Multi-Agent Systems 📝LLMs

ArtifactLinker: Linking Scientific Artifacts for Automatic State-of-the-Art Discovery 🔍RAG

Sign up or log in to see more results

Log in to enable infinite scrolling