Can AI Co-Design Distributed Systems? Scaling from 1 GPU to 1k
harvard-edge.github.io·7h·
Discuss: Hacker News
🎯Performance Proofs
Out-of-Distribution Generalization in Climate-Aware Yield Prediction with Earth Observation Data
arxiv.org·1d
🧠Machine Learning
Neuro-Symbolic AI
en.wikipedia.org·14h·
Discuss: Hacker News
🔲Cellular Automata
Quantifying the Accuracy-Interpretability Trade-Off in Concept-Based Sidechannel Models
arxiv.org·3d
🧠Machine Learning
Homomorphism Problems in Graph Databases and Automatic Structures
arxiv.org·1d
🔗Graph Isomorphism
Nearest Neighbor CCP-Based Molecular Sequence Analysis
arxiv.org·1d
🔄Burrows-Wheeler
On Convex Functions of Gaussian Variables
arxiv.org·2d
📐Compression Mathematics
TRIM: Token-wise Attention-Derived Saliency for Data-Efficient Instruction Tuning
arxiv.org·2d
🔨Compilers
Why LLMs cannot reach GenAI, but why it looked like they could
haversine.substack.com·6h·
Discuss: Substack
🧠Intelligence Compression
Spectral Graph Clustering under Differential Privacy: Balancing Privacy, Accuracy, and Efficiency
arxiv.org·2d
📈Spectral Graph Theory
The Hidden Oracle Inside Your AI: Unveiling Data Density with Latent Space Magic by Arvind Sundararajan
dev.to·2d·
Discuss: DEV
🧠Machine Learning
Scaling LLM Multi-turn RL with End-to-end Summarization-based Context Management
arxiv.org·2d
💻Local LLMs
Title: The Complexity of ChatGPT's Model Picker: A Comprehensive Analysis
dev.to·1d·
Discuss: DEV
🌳Context free grammars
Fast-Convergent Proximity Graphs for Approximate Nearest Neighbor Search
arxiv.org·3d
📏Range Queries
Operationalizing Data Minimization for Privacy-Preserving LLM Prompting
arxiv.org·4d
💻Local LLMs
StruSR: Structure-Aware Symbolic Regression with Physics-Informed Taylor Guidance
arxiv.org·2d
🧠Machine Learning
Model-free generalized fiducial inference
arxiv.org·3d
🧮Kolmogorov Complexity
Memory Retrieval and Consolidation in Large Language Models through Function Tokens
arxiv.org·1d
💻Programming languages
The Hidden Bias: A Study on Explicit and Implicit Political Stereotypes in Large Language Models
arxiv.org·1d
🤖Grammar Induction
Is Architectural Complexity Always the Answer? A Case Study on SwinIR vs. an Efficient CNN
arxiv.org·1d
🤖Advanced OCR