curius graph

all pages

showing 151701-151750 of 200407 pages (sorted by popularity)
Beyond Linear Steering: Unified Multi-Attribute Control for Language Models
[2206.00759] Interpretability Guarantees with Merlin-Arthur Classifiers
The StoryGraph | Because life's too short for a book you're not in the mood for
Now — Arjun
How and why to make a /now page on your site | Derek Sivers
Louis Kirsch | My mission is to automate AI research to generate superintelligence (ASI), for the benefit of humanity and the proliferation of intelligence. Currently, I am a Research Scientist at Google DeepMind.
Taylor expansion of the accumulated rounding error
history - When was the ReLU function first used in a neural network? - Cross Validated
The Universal Weight Subspace Hypothesis | alphaXiv
Alston Scott Householder - Wikipedia
A Logical Calculus of the Ideas Immanent in Nervous Activity - Wikipedia
Connectionism - Wikipedia
A Theory of Formalisms for Representing Knowledge | Proceedings of the AAAI Conference on Artificial Intelligence
A theory of steady-state activity in nerve-fiber networks: I. Definitions and preliminary lemmas | Bulletin of Mathematical Biology
Peter Eckersley (computer scientist) - Wikipedia
Hanna Pálya | Hanna Pálya’s personal site: PhD student at Warwick, researching biosecurity, syndromic surveillance, and ML for early detection.
Celine Li
Useful starting code for interpretability — LessWrong
Demonstrably Safe AI For Autonomous Driving
You should publish your Stack - by Daniel Paleka
[2310.03693] Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!
[2404.01099] What is in Your Safe Data? Identifying Benign Data that Breaks Safety
[2507.14805v1] Subliminal Learning: Language models transmit behavioral traits via hidden signals in data
‪Juergen Schmidhuber‬ - ‪Google Scholar‬
‪Allen Newell‬ - ‪Google Scholar‬
‪vapnik‬ - ‪Google Scholar‬
Hyperstition AI
Self-Interpretability: LLMs Can Describe Complex Internal Processes that Drive Their Decisions
LitmusValues-Pranav/run_stated_preferences_controlled.py at main · SPAR-SvR/LitmusValues-Pranav
[2507.01098] Proof of a perfect platonic representation hypothesis
LLM Judges Are Unreliable — The Collective Intelligence Project
[2009.11162] Implicit Gradient Regularization
Proof of a perfect platonic representation hypothesis
[2106.07682] Revisiting Model Stitching to Compare Neural Representations
2106.07682
[1806.07572] Neural Tangent Kernel: Convergence and Generalization in Neural Networks
Neural Tangent Kernel: Convergence and Generalization in Neural Networks
Analyzing long agent transcripts (Docent)
Robotics - Jacob Steinhardt
[2201.03544] The Effects of Reward Misspecification: Mapping and Mitigating Misaligned Models
[2301.05217] Progress measures for grokking via mechanistic interpretability
Lawrence Chan
2209.11895
2201.02177
[2005.14165] Language Models are Few-Shot Learners
[2207.08799] Hidden Progress in Deep Learning: SGD Learns Parities Near the Computational Limit
Not all bits are made equal - by Shashwat Goel
[2511.08579] Training Language Models to Explain Their Own Computations
Inversion Research
Why Reality has a Well-Known Math Bias - The Linchpin