Search: aqrxiv.org | Heykuki News

Heykuki News

Top New Best Ask Show Jobs

Top New Best Ask Show Jobs

481.

MegaTrain: Full Precision Training of 100B+ Parameter LLMs on a Single GPU (arxiv.org)

326 points

2 months ago

482.

Impact of a Night of Sleep Deprivation on Novice Developers’ Performance (2018) (arxiv.org)

324 points

7 years ago

483.

AbsenceBench: Language models can't tell what's missing (arxiv.org)

324 points

a year ago

484.

Huawei releases an open weight model trained on Huawei Ascend GPUs (arxiv.org)

321 points

a year ago

485.

Explainable Deep Learning: A Field Guide for the Uninitiated (arxiv.org)

321 points

6 years ago

486.

Statistical Analysis shows Echos process voice to serve ads (arxiv.org)

318 points

4 years ago

487.

StarCoder and StarCoderBase: 15.5B parameter models with 8K context length (arxiv.org)

317 points

3 years ago

488.

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

315 points

4 years ago

489.

QLoRA: Efficient Finetuning of Quantized LLMs (arxiv.org)

315 points

3 years ago

490.

QUIC is not quick enough over fast internet (arxiv.org)

313 points

2 years ago

491.

Beyond A*: Better Planning with Transformers (arxiv.org)

313 points

2 years ago

492.

SATAn: Air-Gap Exfiltration Attack via Radio Signals from SATA Cables (arxiv.org)

312 points

4 years ago

493.

Orca 2: Teaching Small Language Models How to Reason (arxiv.org)

310 points

3 years ago

494.

What if an SQL statement returned a database? (arxiv.org)

309 points

2 years ago

495.

Hallucination is inevitable: An innate limitation of large language models (arxiv.org)

308 points

2 years ago

496.

Fitting an elephant with four non-zero parameters (arxiv.org)

307 points

2 years ago

497.

Adversarial policies beat superhuman Go AIs (2023) (arxiv.org)

306 points

a year ago

498.

“I’ll Finish It This Week” and Other Lies (arxiv.org)

306 points

5 years ago

499.

Infinite Photorealistic Worlds Using Procedural Generation (arxiv.org)

306 points

3 years ago

500.

A definition of AGI (arxiv.org)

305 points

7 months ago

501.

Chameleon: Meta’s New Multi-Modal LLM (arxiv.org)

304 points

gabrielbirnbaum

2 years ago

502.

LLMs should not replace therapists (arxiv.org)

303 points

a year ago

503.

Jewish problems (arxiv.org)

303 points

15 years ago

504.

Better and Faster Large Language Models via Multi-Token Prediction (arxiv.org)

302 points

2 years ago

505.

Automated Unit Test Improvement Using Large Language Models at Meta (arxiv.org)

301 points

2 years ago

506.

Exponentially faster language modelling (arxiv.org)

301 points

3 years ago

507.

Zip Trees (arxiv.org)

301 points

8 years ago

508.

Best Practices for Applying Deep Learning to Novel Applications (arxiv.org)

300 points

9 years ago

509.

PowerHammer: Exfiltrating Data from Air-Gapped Computers Through Power Lines (arxiv.org)

298 points

8 years ago

510.

Deterministic Fully-Static Whole-Binary Translation Without Heuristics (arxiv.org)

298 points

a month ago