Hacker Newsnew | past | comments | ask | show | jobs | submit | fromlogin
Embedded Universal Predictive Intelligence: a coherent framework for multi-agent (arxiviq.substack.com)
1 point by che_shr_cat 10 days ago | past | discuss
Arc Is a Vision Problem (arxiviq.substack.com)
1 point by che_shr_cat 25 days ago | past
AlphaResearch: Accelerating New Algorithm Discovery with Language Models (arxiviq.substack.com)
1 point by che_shr_cat 31 days ago | past
LeJEPA: Provable and Scalable Self-Supervised Learning Without the Heuristics (arxiviq.substack.com)
2 points by che_shr_cat 34 days ago | past | 1 comment
Nested Learning: The Illusion of Deep Learning Architectures (arxiviq.substack.com)
6 points by che_shr_cat 37 days ago | past
Context Engineering 2.0: The Context of Context Engineering (arxiviq.substack.com)
2 points by che_shr_cat 41 days ago | past
A Practitioner's Guide to Kolmogorov-Arnold Networks (arxiviq.substack.com)
1 point by che_shr_cat 45 days ago | past
Kimi Linear: An Expressive, Efficient Attention Architecture (arxiviq.substack.com)
1 point by che_shr_cat 46 days ago | past
The Principles of Diffusion Models (470-pages) (arxiviq.substack.com)
2 points by che_shr_cat 46 days ago | past
CaT Replaces CoT-SC / Compute as Teacher: Turning Inference Compute Into (arxiviq.substack.com)
2 points by che_shr_cat 55 days ago | past
Barbarians at the Gate: How AI Is Upending Systems Research (arxiviq.substack.com)
2 points by che_shr_cat 63 days ago | past
Evolution Strategies at Scale: LLM Fine-Tuning Beyond Reinforcement Learning (arxiviq.substack.com)
2 points by che_shr_cat 69 days ago | past
Autoreview: The Dragon Hatchling – The Missing Link Between the Transformer and (arxiviq.substack.com)
2 points by che_shr_cat 73 days ago | past
LLM-JEPA: Large Language Models Meet Joint Embedding Predictive Architectures (arxiviq.substack.com)
1 point by che_shr_cat 86 days ago | past
Review: SpikingBrain Technical Spiking Brain-Inspired Large Models (arxiviq.substack.com)
2 points by che_shr_cat 3 months ago | past
K2-Think: A Parameter-Efficient Reasoning System (arxiviq.substack.com)
2 points by che_shr_cat 3 months ago | past | 1 comment
Canaries in the Coal Mine? Six Facts about the Recent Employment Effects of AI (arxiviq.substack.com)
1 point by che_shr_cat 3 months ago | past
Fantastic Pretraining Optimizers and Where to Find Them (arxiviq.substack.com)
2 points by che_shr_cat 3 months ago | past
Solving the compute crisis with physics-based ASICs (arxiviq.substack.com)
5 points by che_shr_cat 3 months ago | past
Critiques of World Models (arxiviq.substack.com)
2 points by che_shr_cat 3 months ago | past
DeepConf: Scaling LLM reasoning with confidence, not just compute (arxiviq.substack.com)
98 points by che_shr_cat 3 months ago | past | 35 comments
Speed Always Wins: A Survey on Efficient Architectures for Large Language Models (arxiviq.substack.com)
3 points by che_shr_cat 4 months ago | past
Einstein Fields: A Neural Perspective to Computational General Relativity (arxiviq.substack.com)
2 points by che_shr_cat 4 months ago | past
Tversky Neural Networks: Psychologically Plausible Deep Learning With (arxiviq.substack.com)
2 points by che_shr_cat 4 months ago | past
GEPA: Reflective prompt evolution can outperform reinforcement learning (arxiviq.substack.com)
92 points by che_shr_cat 4 months ago | past | 25 comments
Subliminal Learning: Language models transmit behavioral traits via hidden (arxiviq.substack.com)
2 points by che_shr_cat 4 months ago | past
AlphaGo Moment for Model Architecture Discovery (arxiviq.substack.com)
1 point by che_shr_cat 4 months ago | past
Early Signs of Steganographic Capabilities in Frontier LLMs (arxiviq.substack.com)
2 points by che_shr_cat 5 months ago | past
Text-to-LoRA Enables On-the-Fly Model Adaptation (arxiviq.substack.com)
3 points by che_shr_cat 6 months ago | past

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: