Search: asxiv.org | Heykuki News

Heykuki News

Top New Best Ask Show Jobs

Top New Best Ask Show Jobs

421.

GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models [pdf] (arxiv.org)

417 points

10 months ago

422.

Pen and Paper Exercises in Machine Learning (2022) (arxiv.org)

413 points

a year ago

423.

TimeGPT-1 (arxiv.org)

411 points

3 years ago

424.

Phi-3 Technical Report (arxiv.org)

411 points

2 years ago

425.

Lossless LLM compression for efficient GPU inference via dynamic-length float (arxiv.org)

411 points

a year ago

426.

Every Model Learned by Gradient Descent Is Approximately a Kernel Machine (arxiv.org)

406 points

6 years ago

427.

OpenVoice: Versatile Instant Voice Cloning (arxiv.org)

399 points

2 years ago

428.

The Case for Learned Index Structures (arxiv.org)

398 points

8 years ago

429.

Origin of correlated isolated flat bands in LK99 (arxiv.org)

397 points

3 years ago

430.

Why is it so hard to find a job now? Enter Ghost Jobs (arxiv.org)

394 points

2 years ago

431.

Accumulation of cognitive debt when using an AI assistant for essay writing task (arxiv.org)

391 points

a year ago

432.

Generative Agents: Interactive Simulacra of Human Behavior (arxiv.org)

391 points

3 years ago

433.

Better Call GPT: Comparing large language models against lawyers [pdf] (arxiv.org)

389 points

2 years ago

434.

C++ patterns for low-latency applications including high-frequency trading (arxiv.org)

389 points

2 years ago

435.

LIMO: Less Is More for Reasoning (arxiv.org)

389 points

a year ago

436.

Adversarial poetry as a universal single-turn jailbreak mechanism in LLMs (arxiv.org)

384 points

7 months ago

437.

Phase behavior of Cacio and Pepe sauce (arxiv.org)

381 points

a year ago

438.

A Differentiable Programming System to Bridge ML and Scientific Computing (arxiv.org)

381 points

ChrisRackauckas

7 years ago

439.

A Brief Introduction to Machine Learning for Engineers (2017) (arxiv.org)

379 points

8 years ago

440.

Fair coins tend to land on the same side they started (arxiv.org)

377 points

3 years ago

441.

Simple tasks showing reasoning breakdown in state-of-the-art LLMs (arxiv.org)

375 points

2 years ago

442.

LLMs get lost in multi-turn conversation (arxiv.org)

374 points

a year ago

443.

Chain-of-thought can hurt performance on tasks where thinking makes humans worse (arxiv.org)

371 points

2 years ago

444.

Pen and paper exercises in machine learning (2021) (arxiv.org)

371 points

4 years ago

445.

Ladder: Self-improving LLMs through recursive problem decomposition (arxiv.org)

370 points

a year ago

446.

Bringing GNU Emacs to Native Code (2020) (arxiv.org)

369 points

5 years ago

447.

The physics of baking good pizza (arxiv.org)

368 points

8 years ago

448.

There Will Be a Scientific Theory of Deep Learning (arxiv.org)

367 points

2 months ago

449.

Player of Games (arxiv.org)

364 points

5 years ago

450.

SkillsBench: Benchmarking how well agent skills work across diverse tasks (arxiv.org)

364 points

4 months ago