original ↗
manton.org·1d
The Kepler Problem (Part 11)
johncarlosbaez.wordpress.com·2d
Multi-head Transformers Provably Learn Symbolic Multi-step Reasoning via Gradient Descent
arxiv.org·10h
What Makes "Good" Distractors for Object Hallucination Evaluation in Large Vision-Language Models?
arxiv.org·10h
Deep Ignorance: Filtering Pretraining Data Builds Tamper-Resistant Safeguards into Open-Weight LLMs
arxiv.org·10h
Pushing the Envelope of LLM Inference on AI-PC
arxiv.org·10h
Memory Enhanced Fractional-Order Dung Beetle Optimization for Photovoltaic Parameter Identification
arxiv.org·10h
Loading...Loading more...