curius graph

all pages

showing 35701-35750 of 160880 pages (sorted by popularity)
Interactive Scalable Interfaces for Machine Learning Interpretability — Fred Hohman
Simple Long Convolutions for Sequence Modeling · Hazy Research
[2303.03846] Larger language models do in-context learning differently
MosaicBERT: Pretraining BERT from Scratch for $20
[2303.08112] Eliciting Latent Predictions from Transformers with the Tuned Lens
Observability | Practical Observability
Decision Transformer Interpretability - AI Alignment Forum
What Is Bfloat16 Arithmetic? – Nick Higham
[2303.05119] Entropic Wasserstein Component Analysis
TRAK
Why didn't we get GPT-2 in 2005?
Announcing OpenFlamingo: An open-source framework for training vision-language models with in-context learning | LAION
[2303.11249] What Makes Data Suitable for a Locally Connected Neural Network? A Necessary and Sufficient Condition Based on Quantum Entanglement
Actually, Othello-GPT Has A Linear Emergent World Representation — Neel Nanda
Reverse engineering the NTK
On AI Deployment: AI supply chains (and why they matter)
rnoti-p1034.pdf
The Independent Compositional Subspace Hypothesis for the Structure of CLIP's Last Layer | OpenReview
PureJaxRL
When are Neural Networks more powerful than Neural Tangent Kernels? – Off the convex path
AI for General Science - Large language models for scientific hypothesis/research ideas generation | Xinming Tu
Parfit: A Philosopher and His Mission to Save Morality by David Edmonds - review by Jane O’Grady
[2304.03843] Why think step-by-step? Reasoning emerges from the locality of experience
Scaling, emergence, and reasoning (Jason Wei, NYU) - Google Slides
Revisiting the classics: Jensen’s inequality – Machine Learning Research Blog
[2103.00564] An Introduction to Johnson-Lindenstrauss Transforms
[2303.14177] Scaling Expert Language Models with Unsupervised Domain Discovery
PsyArXiv Preprints | Surprisal does not explain syntactic disambiguation difficulty: evidence from a large-scale benchmark
[2303.17951] FP8 versus INT8 for efficient deep learning inference
Seurat CCA? It's just a simple extension of PCA! | Xinming Tu
Niels Bohr's Memorandum to President Roosevelt | The Manhattan Project | Historical Documents | atomicarchive.com
Public Policy for Realists - by Pradyumna Prasad
What Is Iterative Refinement? – Nick Higham
[2305.08809] Interpretability at Scale: Identifying Causal Mechanisms in Alpaca
PsyArXiv Preprints | How hard is cognitive science?
Direct Approach Interactive Model
Playing Doc’s Games—I | The New Yorker
Six Experiments in Action Minimization
Aligning Faithful Interpretations with their Social Attribution - ACL-TACL-2021_2021.tacl-1.18
The longest training run
Learning explanations that are hard to vary | OpenReview
What We Get Wrong About AI & China—Asterisk
What is the curl of a vector field, really? – theHigherGeometer
Lens
What does it mean to understand how a scientific literature is put together? - Marginal REVOLUTION
Inside Argentina's currency exchange black markets | devonzuegel.com
[2307.05599] AlephZero and Mathematical Experience
Can we develop theoretical explanations for today’s AI systems? - generally intelligent
Anthropic \ Studying Large Language Model Generalization with…
Embroid: Correcting and Improving LLM Predictions Without Labels · Hazy Research