Search: asxiv.org | Heykuki News

Heykuki News

Top New Best Ask Show Jobs

Top New Best Ask Show Jobs

691.

Agents Are Not Enough (arxiv.org)

207 points

a year ago

692.

Chronos: Learning the Language of Time Series (arxiv.org)

207 points

2 years ago

693.

Machine Theory of Mind (arxiv.org)

207 points

8 years ago

694.

Chronofold: A data structure for versioned text (2020) (arxiv.org)

207 points

5 years ago

695.

Adaptive LLM routing under budget constraints (arxiv.org)

206 points

9 months ago

696.

Inverted Transformers Are Effective for Time Series Forecasting (arxiv.org)

206 points

3 years ago

697.

Stealing Machine Learning Models via Prediction APIs (arxiv.org)

206 points

10 years ago

698.

Edward – A Turing-Complete Language for Deep Probabilistic Programming (arxiv.org)

206 points

9 years ago

699.

Why AI systems don't learn – On autonomous learning from cognitive science (arxiv.org)

205 points

3 months ago

700.

Imminent merger of a supermassive black hole binary (arxiv.org)

205 points

4 years ago

701.

Yi: Open Foundation Models by 01.AI (arxiv.org)

205 points

2 years ago

702.

Scalable MatMul-Free Language Modeling (arxiv.org)

205 points

2 years ago

703.

Boltzmann Encoded Adversarial Machines (arxiv.org)

205 points

8 years ago

704.

Bugs in our pockets: the risks of client-side scanning (arxiv.org)

204 points

5 years ago

705.

ISO C became unusable for operating systems development (arxiv.org)

203 points

4 years ago

706.

An Attempt to Catch Up with JIT Compilers (arxiv.org)

203 points

a year ago

707.

Universal optimality of Dijkstra via beyond-worst-case heaps (arxiv.org)

203 points

2 years ago

708.

GPT-4 Can Almost Perfectly Handle Unnatural Scrambled Text (arxiv.org)

202 points

3 years ago

709.

Optical Transformers (arxiv.org)

202 points

3 years ago

710.

A Computer Scientist’s View of Life, the Universe, and Everything (1999) (arxiv.org)

202 points

9 years ago

711.

What Is Applied Category Theory? (2018) (arxiv.org)

202 points

5 years ago

712.

Beating the World’s Best at Super Smash Bros. with Deep Reinforcement Learning (arxiv.org)

202 points

9 years ago

713.

X X^t can be faster (arxiv.org)

201 points

a year ago

714.

We're afraid language models aren't modeling ambiguity (arxiv.org)

200 points

3 years ago

715.

Feasibility study of a mission to Sedna – Nuclear propulsion and solar sailing (arxiv.org)

200 points

a year ago

716.

Majority is not Enough: Bitcoin Mining is Vulnerable (arxiv.org)

200 points

13 years ago

717.

Outrageously Large Neural Networks: The Sparsely-Gated Mixture-Of-Experts Layer (arxiv.org)

200 points

9 years ago

718.

The boundary of neural network trainability is fractal (arxiv.org)

200 points

2 years ago

719.

Thermodynamic Natural Gradient Descent (arxiv.org)

200 points

2 years ago

720.

Self-Retrieval: Building an information retrieval system with one LLM (arxiv.org)

200 points

2 years ago