Heykuki News

TopNewBestAskShowJobs
TopNewBestAskShowJobs
631.
TopoNets: High performing vision and language models with brain-like topography (arxiv.org)
225 points
mayukhdeb
a year ago
68 comments
632.
Horcrux: A Password Manager for Paranoids (arxiv.org)
224 points
lainon
9 years ago
165 comments
633.
Do transformers need three projections? Systematic study of QKV variants (arxiv.org)
224 points
Anon84
6 days ago
47 comments
634.
Neural Network Diffusion (arxiv.org)
223 points
vagabund
2 years ago
86 comments
635.
Sending a Spacecraft to the Interstellar Asteroid (arxiv.org)
223 points
DanielleMolloy
9 years ago
73 comments
636.
Oxide: A Formal Semantics for Rust (arxiv.org)
223 points
rachitnigam
7 years ago
30 comments
637.
Solving a million-step LLM task with zero errors (arxiv.org)
222 points
Anon84
7 months ago
95 comments
638.
The Principles of Deep Learning Theory (arxiv.org)
221 points
Anon84
4 years ago
139 comments
639.
Dissecting Ponzi schemes on Ethereum: identification, analysis, and impact (arxiv.org)
221 points
moh_maya
9 years ago
121 comments
640.
Tutorial on diffusion models for imaging and vision (arxiv.org)
221 points
Anon84
2 years ago
18 comments
641.
Toolformer: Language Models Can Teach Themselves to Use Tools (arxiv.org)
220 points
jasondavies
3 years ago
45 comments
642.
Mathematics of Deep Learning [pdf] (arxiv.org)
220 points
magoghm
8 years ago
38 comments
643.
Wikidata, with 12B facts, can ground LLMs to improve their factuality (arxiv.org)
219 points
raybb
3 years ago
84 comments
644.
Foundations of Large Language Models (arxiv.org)
219 points
pkoird
a year ago
20 comments
645.
Self-Normalizing Neural Networks (arxiv.org)
219 points
MrQuincle
9 years ago
12 comments
646.
How real are real numbers? (2004) (arxiv.org)
218 points
caustic
9 years ago
265 comments
647.
Reasoning models reason well, until they don't (arxiv.org)
218 points
optimalsolver
7 months ago
217 comments
648.
Accidentally quadratic: When Python is faster than C++ (arxiv.org)
218 points
mehrdadn
5 years ago
213 comments
649.
TinyStories: How Small Can Language Models Be and Still Speak Coherent English? (2023) (arxiv.org)
218 points
tzury
a year ago
104 comments
650.
Mathematical methods and human thought in the age of AI (arxiv.org)
218 points
zaikunzhang
2 months ago
93 comments
651.
Why Does It Take So Long to Connect to a WiFi Access Point? (arxiv.org)
218 points
2dvisio
9 years ago
60 comments
652.
Stealing Part of a Production Language Model (arxiv.org)
218 points
alphabetting
2 years ago
51 comments
653.
Professional software developers don't vibe, they control (arxiv.org)
217 points
dpflan
5 months ago
247 comments
654.
Next-Paradigm Programming Languages: What Will They Look Like? (arxiv.org)
217 points
furcyd
7 years ago
226 comments
655.
Comparing humans, GPT-4, and GPT-4V on abstraction and reasoning tasks (arxiv.org)
217 points
mpweiher
3 years ago
177 comments
656.
How to fit any dataset with a single parameter (arxiv.org)
217 points
tambourine_man
5 years ago
146 comments
657.
Gravitational Machines (arxiv.org)
217 points
sohkamyung
3 years ago
103 comments
658.
Mexican Computers: A Brief Technical and Historical Overview (arxiv.org)
217 points
belter
2 years ago
37 comments
659.
Is artificial consciousness achievable? Lessons from the human brain (arxiv.org)
216 points
wonderlandcal
2 years ago
578 comments
660.
Regularization is all you need: simple neural nets can excel on tabular data (arxiv.org)
216 points
tracyhenry
5 years ago
93 comments
More