AI研究論文デイリー

The Prompt Report: A Systematic Survey of Prompting Techniques

An Image is Worth 32 Tokens for Reconstruction and Generation

McEval: Massively Multilingual Code Evaluation

Zero-shot Image Editing with Reference Imitation

TextGrad: Automatic "Differentiation" via Text

Improve Mathematical Reasoning in Language Models by Automated Process Supervision

Accessing GPT-4 level Mathematical Olympiad Solutions via Monte Carlo Tree Self-refine with LLaMa-3 8B

Skywork-MoE: A Deep Dive into Training Techniques for Mixture-of-Experts Language Models

SEE-2-SOUND: Zero-Shot Spatial Environment-to-Spatial Sound

4Real: Towards Photorealistic 4D Scene Generation via Video Diffusion Models

AsyncDiff: Parallelizing Diffusion Models by Asynchronous Denoising

Simple and Effective Masked Diffusion Language Models

MedFuzz: Exploring the Robustness of Large Language Models in Medical Question Answering

Separating the "Chirp" from the "Chat": Self-supervised Visual Grounding of Sound and Language

Neural Gaffer: Relighting Any Object via Diffusion

Merging Improves Self-Critique Against Jailbreak Attacks