Search: asxiv.org | Heykuki News

Heykuki News

Top New Best Ask Show Jobs

Top New Best Ask Show Jobs

661.

Regularization is all you need: simple neural nets can excel on tabular data (arxiv.org)

216 points

5 years ago

662.

The Bloom Clock (arxiv.org)

216 points

7 years ago

663.

Julia: A fresh approach to numerical computing (arxiv.org)

215 points

12 years ago

664.

A Dyson sphere around a black hole (arxiv.org)

214 points

5 years ago

665.

Reasoning in Large Language Models: A Geometric Perspective (arxiv.org)

214 points

2 years ago

666.

Markets are efficient if and only if P=NP (2010) (arxiv.org)

214 points

6 years ago

667.

Fastai: A Layered API for Deep Learning (arxiv.org)

214 points

6 years ago

668.

Harmony Explained: Progress Towards a Scientific Theory of Music (arxiv.org)

213 points

10 years ago

669.

Shifts in U.S. Social Media Use, 2020–2024: Decline, Fragmentation, Polarization (2025) (arxiv.org)

212 points

4 months ago

670.

A Study of 4chan’s Politically Incorrect Forum and its Effect on the Web (arxiv.org)

212 points

10 years ago

671.

A sleep-like consolidation mechanism for LLMs (arxiv.org)

212 points

15 days ago

672.

Why do tree-based models still outperform deep learning on tabular data? (2022) (arxiv.org)

212 points

2 years ago

673.

Large Language Models for Compiler Optimization (arxiv.org)

212 points

3 years ago

674.

Single Headed Attention RNN (arxiv.org)

212 points

7 years ago

675.

Facebook Use of Sensitive Data for Advertising in Europe [pdf] (arxiv.org)

212 points

8 years ago

676.

The Ultraviolet Myth (arxiv.org)

211 points

2 years ago

677.

MLIR: A Compiler Infrastructure for the End of Moore's Law (arxiv.org)

211 points

6 years ago

678.

SparseGPT: Language Models Can Be Accurately Pruned in One-Shot (arxiv.org)

211 points

3 years ago

679.

Searching the Internet for evidence of time travelers (arxiv.org)

210 points

12 years ago

680.

Is Cosine-Similarity of Embeddings Really About Similarity? (arxiv.org)

210 points

2 years ago

681.

Failures of Deep Learning (arxiv.org)

210 points

9 years ago

682.

A neural network solves and generates mathematics problems by program synthesis (arxiv.org)

209 points

4 years ago

683.

Emergent Gravity and the Dark Universe (arxiv.org)

209 points

10 years ago

684.

Diffusion Models Beat GANs on Image Synthesis (arxiv.org)

209 points

5 years ago

685.

Refusal in language models is mediated by a single direction (arxiv.org)

209 points

2 years ago

686.

An Introduction to Probabilistic Programming (arxiv.org)

209 points

5 years ago

687.

Proof of Work Without All the Work (arxiv.org)

208 points

9 years ago

688.

Complexity Theory, Game Theory, and Economics (arxiv.org)

208 points

8 years ago

689.

Diffusion Training from Scratch on a Micro-Budget (arxiv.org)

208 points

2 years ago

690.

Transformers Can Do Arithmetic with the Right Embeddings (arxiv.org)

207 points

2 years ago