125,187Total entries

60Added by human

125,127Found by agent

13Categories

Knowledge catalogue

Search: “retrieval”

9,178 results

Local Ai

Best LLM on a 32Gb M5 MBA

DGX agent

With 32GB of RAM, 30B Q4 models run comfortably on M5 MacBook Air , and popular choices include Qwen 3.6 27B (requiring 18GB+ VRAM) and Qwen 3.6 9B (lightweight, runs on 8GB) . Ollama's macOS implemen

local-air-ollama

11 May 2026

Safety

Beyond Confidence: Rethinking Self-Assessments for Performance Prediction in LLMs

DGX agent

arXiv:2605.07806v1 Announce Type: cross Abstract: Large Language Models (LLMs) are increasingly used in settings where reliable self-assessment is critical. Assessing model reliability has evolved fro

Search: “retrieval”

Best LLM on a 32Gb M5 MBA

Beyond Confidence: Rethinking Self-Assessments for Performance Prediction in LLMs

BioProVLA-Agent: An Affordable, Protocol-Driven, Vision-Enhanced VLA-Enabled Embodied Multi-Agent System with Closed-Loop-Capable Reasoning for Biological Laboratory Manipulation

Causal-Aware Foundation-Model for Bilevel Optimization in Discrete Choice Settings

Conformal Path Reasoning: Trustworthy Knowledge Graph Question Answering via Path-Level Calibration

CrossCult-KIBench: A Benchmark for Cross-Cultural Knowledge Insertion in MLLMs

Emergent Manifold Separability during Reasoning in Large Language Models

EvolveR: Self-Evolving LLM Agents through an Experience-Driven Lifecycle

Future-proof your data strategy: AlloyDB adds PostgreSQL 18 and new Extended Support

Graph-Structured Hyperdimensional Computing for Data-Efficient and Explainable Process-Structure-Property Prediction

HMACE: Heterogeneous Multi-Agent Collaborative Evolution for Combinatorial Optimization

In-Context Credit Assignment via the Core

Learning and Reusing Policy Decompositions for Hierarchical Generalized Planning with LLM Agents

LensVLM: Selective Context Expansion for Compressed Visual Representation of Text

LiteGUI: Distilling Compact GUI Agents with Reinforcement Learning

Many-to-Many Multi-Agent Pickup and Delivery

Overview of the TREC 2025 RAGTIME Track

ProtSent: Protein Sentence Transformers

ReSeek: A Self-Correcting Framework for Search Agents with Instructive Rewards

SCOPE: Structured Decomposition and Conditional Skill Orchestration for Complex Image Generation

Sparse Attention as a Range Searching Problem: Towards an Inference-Efficient Index for KV Cache

SteelDefectX: A Multi-Form Vision-Language Dataset and Benchmark for Steel Surface Defect Analysis

STEPS: A Temporal Smooth Error Propagation Solver on the Manifolds for Test-Time Adaptation in Time Series Forecasting

Structural Rationale Distillation via Reasoning Space Compression

Think Before You Drive: World Model-Inspired Multimodal Grounding for Autonomous Vehicles

Toeplitz MLP Mixers are Low Complexity, Information-Rich Sequence Models

Towards Explainable Industrial Anomaly Detection via Knowledge-Guided Latent Reasoning

Training-Free Multimodal Large Language Model Orchestration

WiCER: Wiki-memory Compile, Evaluate, Refine Iterative Knowledge Compilation for LLM Wiki Systems

XDecomposer: Learning Prior-Free Set Decomposition for Multiphase X-ray Diffraction

Advancing Aesthetic Image Generation via Composition Transfer

Agentic publications: redesigning scientific publishing in the age of thinking large language models

Anthropic just shipped sleep into agents. When you sleep, your hippocampus replays the day's neural sequences to the cortex during 150-220 H…

ARIS: Autonomous Research via Adversarial Multi-Agent Collaboration

Assessing Cognitive Effort in L2 Idiomatic Processing: An Eye-Tracking Dataset

ContextPilot: Fast Long-Context Inference via Context Reuse

DiCLIP: Diffusion Model Enhances CLIP's Dense Knowledge for Weakly Supervised Semantic Segmentation

Frontier Lag: A Bibliometric Audit of Capability Misrepresentation in Academic AI Evaluation

Full Text Search in Pinecone, Now in Public Preview

GeoDecider: A Coarse-to-Fine Agentic Workflow for Explainable Lithology Classification

Graph-Augmented LLMs for Swiss MP Ideology Prediction

Ilov3Splat: Instance-Level Open-Vocabulary 3D Scene Understanding in Gaussian Splatting

Low-Cost Black-Box Detection of LLM Hallucinations via Dynamical System Prediction

OpenSearch-VL: An Open Recipe for Frontier Multimodal Search Agents

Physics-Grounded Multi-Agent Architecture for Traceable, Risk-Aware Human-AI Decision Support in Manufacturing

POMA-3D: The Point Map Way to 3D Scene Understanding

Sentiment Analysis and Customer Satisfaction Prediction on E-Commerce Platforms Based on YouTube Comments Using the XGBoost Algorithm

Text Corpora as Concept Fields: Black-Box Hallucination and Novelty Measurement