curius graph

all pages

showing 160551-160600 of 200407 pages (sorted by popularity)
On PHATGOOSE: The Challenge of Recycling PEFT Modules for Zero-Shot Generalization
Phind-70b
Google Wave Developer Preview at Google I/O 2009
explained: latent consistency models
Work Items · tinygrad 1.0
Was Merlin a Real Person? - YouTube
The Unbelievable Truth and the Dilemmas of Ignorance
The Dicethrow, §11, in Deleuze, Nietzsche & Philosophy
Sampling-Bias-Corrected Neural Modeling for Large Corpus Item Recommendations
CPU vs FPGA
How to actually make people like you.
So, what is a physics-informed neural network? - Ben Moseley
Language model self-teaching for domain adaptation | Morph
[2311.08105] DiLoCo: Distributed Low-Communication Training of Language Models
A Novel Measure Inspired by Lyapunov Exponents for the Characterization of Dynamics in State-Transition Networks
alena titova
pixelogik/NearPy: fast (approximated) nn search in large, high-dimensional data sets using different locality-sensitive hashes.
HI-FIVE | The best design newsletter | Inspiration for creatives
On the Existence of Powerful Natural Languages · Gwern.net
On religion - Richard Feynman
x86 Registers
google-deepmind/xmanager: A platform for managing machine learning experiments
mosaicml/streaming: A Data Streaming Library for Efficient Neural Network Training
How to help someone use a computer
caseploeg.com
RoFormer
Sparse Distributed Memory and Hopfield Networks – Trenton Bricken
1940's a Summer evening sitting on a porch and it's raining (oldies music from another room) ASMR - YouTube
[2401.06118] Extreme Compression of Large Language Models via Additive Quantization
[2405.04517] xLSTM: Extended Long Short-Term Memory
Considering C99 for curl | daniel.haxx.se
christine-sites
jzarnett/ece459: ECE 459: Programming for Performance
efeslab/Nanoflow: A throughput-oriented high-performance serving framework for LLMs
Footer | Typographic Footers — The only footer gallery on earth.
LLMs: Understanding Code Syntax and Semantics for Code Analysis
tianyi-lab/Reflection_Tuning: [ACL'24] Selective Reflection-Tuning: Student-Selected Data Recycling for LLM Instruction-Tuning
zml/zml: High performance AI inference stack. Built for production. @ziglang / @openxla / MLIR / @bazelbuild
a phoneless summer - YouTube
[1911.01547] On the Measure of Intelligence
Design patterns — Gordon Brander
The Practitioner’s Guide to the Maximal Update Parameterization - Cerebras
[2409.14586] Backtracking Improves Generation Safety
Skeleton loading trick CSS
William Gedney's Timelessly Intimate Photographs of San Francisco in the 1960s
slyd0g/SwiftSpy: macOS keylogger, clipboard monitor, and screenshotter
[2409.20370] The Perfect Blend: Redefining RLHF with Mixture of Judges
Fully Sharded Data Parallel - CUDA
expose ports in Colab
Emmett Shear on X: "This sent me down a rabbit hole. The first three were clear, but the fourth was hard to pick out… https://t.co/wJbMGoG9lg" / X