curius graph

all pages

showing 53901-53950 of 200407 pages (sorted by popularity)
Biorisk \ red.anthropic.com
How to become so creative it feels illegal - by DAN KOE
Size Efficient Parallel Algebraic Circuits for Partial Derivatives
Linear ODEs instabilities – Libres pensées d'un mathématicien ordinaire
走向2026：在孩子、写作与AI之间 - by 米米亚娜 - 米坛埋骨
[2603.03612] Why Are Linear RNNs More Parallelizable?
Sigmoid-Weighted Linear Units for Neural Network Function Approximation in Reinforcement Learning
[2412.07752] FlashRNN: I/O-Aware Optimization of Traditional RNNs on modern hardware
[2412.07752] FlashRNN: I/O-Aware Optimization of Traditional RNNs on modern hardware
[2603.14360] M$^2$RNN: Non-Linear RNNs with Matrix-Valued States for Scalable Language Modeling
[2011.01929] The Complexity of Gradient Descent: CLS = PPAD $\cap$ PLS
The Solow Model is overrated (for explaining catch-up growth) — Basil Halperin
The Myth of Asia's Miracle | Foreign Affairs
[2410.18077] ALTA: Compiler-Based Analysis of Transformers
A Foothold on History | Baseball Hall of Fame
China’s Shifting Relationship to the Countryside | The New Yorker
Autoresearching Apple's "LLM in a Flash" to run Qwen 397B locally
[2311.07568] Feature emergence via margin maximization: case studies in algebraic tasks
[2506.06489] Alternating Gradient Flows: A Theory of Feature Learning in Two-layer Neural Networks
[2602.16849] On the Mechanism and Dynamics of Modular Addition: Fourier Features, Lottery Ticket, and Grokking
[2602.01434] Phase Transitions for Feature Learning in Neural Networks
[2603.17074] PRISM: Demystifying Retention and Interaction in Mid-Training
[2507.12709] From SGD to Spectra: A Theory of Neural Network Weight Dynamics
Riva-Melissa Tez - West London Living
[2603.03612] Why Are Linear RNNs More Parallelizable?
Cultured Chicken Production Cost Model – Cultured Chicken Cost Model
Parameter Golf Live AI Commentary + Analysis / Ideas | every 10 minutes · Issue #140 · openai/parameter-golf
parameter-golf/records/track_10min_16mb/2026-03-23_LeakyReLU_LegalTTT_ParallelMuon/train_gpt.py at b08d72a96e98cac8add0543982fccd35bc8f4f4d · abaybektursun/parameter-golf
[2603.16850] Unifying Optimization and Dynamics to Parallelize Sequential Computation: A Guide to Parallel Newton Methods for Breaking Sequential Bottlenecks
[2603.20104] Computation and sampling for Schubert specializations
Space-Track.org
math-inc/OpenGauss ·
Jhumpa Lahiri on Writing for Literary Greats and What Gets Lost in Translation
A Modest Proposal | Project Gutenberg
Course Detail | NVIDIA
Laplace's method
Method of steepest descent
Propagation of uncertainty
[2603.01192] Grokking as a Phase Transition between Competing Basins: a Singular Learning Theory Approach
The 20-year journey to fully autonomous cars with Dmitri Dolgov of Waymo
MR-v2.pdf
Many AI Debates Are Way Too Philosophical and Theoretical
DEF CON 23 - Chris Rock - I Will Kill You - YouTube
Closed-form dynamics beyond quadratics – Machine Learning Research Blog
We (novel)
lectureprospectusht1918decpdf
Home Page | Twenty
Chen Tianqiao
Lab AI Policy | Todd Gureckis
Readers’ wildlife photos – Why Evolution Is True