Linear Probes to Bayesian Manifolds: Geometry of Arithmetic in Large Language Models
Abstract page for arXiv paper 2611.12998: Linear Probes to Bayesian Manifolds: Geometry of Arithmetic in Large Language Models
Source feed
2464 items
The world's AI knowledge in one place. AI RSS feed aggregator monitoring OpenAI, Anthropic, Google AI, Meta, Hugging Face. Tutorials, news, and insights — as they happen.
Abstract page for arXiv paper 2611.12998: Linear Probes to Bayesian Manifolds: Geometry of Arithmetic in Large Language Models
Abstract page for arXiv paper 2611.12990: Multimodal Graph Learning: A Survey of Models, Benchmarks, and Frontiers
Abstract page for arXiv paper 2611.12988: Third Eye: Beyond Immediate Gains in Recursive Self-Improvement
Abstract page for arXiv paper 2611.12974: StatPrompt-LLM: A Lightweight Statistical Refinement for Foundation-Style Time-Series Forecasting
Abstract page for arXiv paper 2611.12950: SetPrint: Black-Box LLM Fingerprinting via Setwise Correspondence of Response Changes
Abstract page for arXiv paper 2611.12941: AI Governance Should Prioritize Control and Knowledge Boundaries Over Limiting Intelligence
Abstract page for arXiv paper 2611.12938: Graph Visualizations in Prompts for Knowledge Graph Question Answering
Abstract page for arXiv paper 2611.12937: Tracing Psychometric Inference in Large Language Models
Abstract page for arXiv paper 2611.12936: LandslideFM: A Foundation Model Towards Unified Landslide Perception and Understanding
Abstract page for arXiv paper 2611.12935: Train on prefill, monitor at decode: Using sparse autoencoders for topic monitoring
Abstract page for arXiv paper 2611.12933: Auditable Human-Agent Teams for Autonomous X-ray Experimentation
On the first day of AIE Code Summit, OpenAI showed how developers can steer Codex by voice, hand off work to the cloud, and make use of dots.
Topics: Code Assistants
Entities: OpenAICode Assistants