Search: asxiv.org | Heykuki News

Heykuki News

Top New Best Ask Show Jobs

Top New Best Ask Show Jobs

511.

Seven Sketches in Compositionality: An Invitation to Applied Category Theory (arxiv.org)

294 points

7 years ago

512.

σ-GPTs: A new approach to autoregressive models (arxiv.org)

293 points

2 years ago

513.

LLMs Will Always Hallucinate, and We Need to Live with This (arxiv.org)

291 points

2 years ago

514.

Compiling C to Safe Rust, Formalized (arxiv.org)

291 points

a year ago

515.

MusicLM: Generating music from text (arxiv.org)

291 points

3 years ago

516.

DeepMind achieves SOTA image recognition with 8.7x faster training (arxiv.org)

291 points

5 years ago

517.

Looking Back at Postgres (arxiv.org)

290 points

6 years ago

518.

How is ChatGPT's behavior changing over time? (arxiv.org)

289 points

3 years ago

519.

More Agents Is All You Need: LLMs performance scales with the number of agents (arxiv.org)

288 points

2 years ago

520.

An abundance of Katherines: The game theory of baby naming (arxiv.org)

288 points

2 years ago

521.

Using Reinforcement Learning in the Algorithmic Trading Problem (arxiv.org)

288 points

6 years ago

522.

Determination of the fifth Busy Beaver value (arxiv.org)

288 points

9 months ago

523.

faulTPM: Exposing AMD fTPMs' Deepest Secrets (arxiv.org)

287 points

3 years ago

524.

Constraint Decay: The Fragility of LLM Agents in Back End Code Generation (arxiv.org)

287 points

17 days ago

525.

What If Planet 9 Is a Primordial Black Hole? (arxiv.org)

285 points

7 years ago

526.

Maximizing Battery Storage Profits via High-Frequency Intraday Trading (arxiv.org)

283 points

a year ago

527.

Training LLMs to Reason in a Continuous Latent Space (arxiv.org)

283 points

a year ago

528.

Graph of Thoughts: Solving Elaborate Problems with Large Language Models (arxiv.org)

283 points

3 years ago

529.

Understanding the Limitations of Mathematical Reasoning in LLMs (arxiv.org)

282 points

2 years ago

530.

Neural programmer better than Quicksort (arxiv.org)

282 points

6 years ago

531.

Mixture-of-Depths: Dynamically allocating compute in transformers (arxiv.org)

281 points

2 years ago

532.

A Wait-Free Stack (arxiv.org)

281 points

10 years ago

533.

Quiet-STaR: Language Models Can Teach Themselves to Think Before Speaking (arxiv.org)

280 points

2 years ago

534.

Cognitive Behaviors That Enable Self-Improving Reasoners (arxiv.org)

279 points

a year ago

535.

How popular media portrays the employability of older software developers (arxiv.org)

278 points

6 years ago

536.

Large language models lack deep insights or a theory of mind (arxiv.org)

277 points

3 years ago

537.

Scaling Transformer to 1M tokens and beyond with RMT (arxiv.org)

277 points

3 years ago

538.

The Modern Mathematics of Deep Learning (arxiv.org)

276 points

5 years ago

539.

Planting Undetectable Backdoors in Machine Learning Models (arxiv.org)

275 points

4 years ago

540.

Recursively summarizing enables long-term dialogue memory in LLMs (arxiv.org)

273 points

3 years ago