Diffusion Models
PulseAugur coverage of Diffusion Models — every cluster mentioning Diffusion Models across labs, papers, and developer communities, ranked by signal.
7 天有情绪数据
-
Researchers unveil new stealthy backdoor attacks on AI models using diffusion and style features
Researchers have developed new methods for backdoor attacks on advanced AI models, specifically targeting Vision-Language Models (VLMs) and Diffusion Models (DMs). One approach, CBV, uses diffusion models to create natu…
-
Anthropic's Claude Code boosts developer workflow; new research explores decision trees and diffusion models
A user shared their positive experience transitioning their entire coding workflow to Anthropic's Claude Code, finding it highly effective and satisfying. Separately, new research proposes integrating decision trees and…
-
Diffusion models can now harmonize 3D Gaussian Splatting scenes
Researchers have developed a new method, D3DR, that leverages diffusion models to seamlessly insert 3D objects into existing 3D scenes rendered with Gaussian Splatting. The technique utilizes the diffusion model's impli…
-
New research explores advanced reward modeling for LLMs and diffusion models
Several new research papers explore advancements in reward modeling for AI alignment, particularly for large language models and diffusion models. One paper introduces SelectiveRM, a framework using optimal transport to…
-
扩散模型增强了贝叶斯雨场重建和高斯过程推理
研究人员开发了一种使用商用微波链路和扩散模型作为空间先验来重建降雨场的新方法。该方法将雨场估计视为一个贝叶斯逆问题，与现有方法相比，在降雨统计数据的保留方面有所提高。该技术允许无训练的后验采样，并在合成和真实数据集上展示了一致的改进。
-
AI generates custom Pokemon trading cards, enhancing player engagement
This paper explores using Large Language Models and Diffusion Models to procedurally generate trading card game content, specifically for Pokémon cards. The research proposes a pipeline that combines player co-creation …
-
Data Balancing Strategies: A Systematic Survey of Resampling and Augmentation Methods
This paper presents a systematic review of data balancing strategies for machine learning, covering resampling and augmentation techniques. It categorizes methods from foundational approaches like SMOTE to advanced deep…
-
New AI methods enhance image, time-series inpainting and model analysis
Researchers have developed new methods for improving generative models in various domains. One approach, "Free Decompression," uses algebraic spectral curve theory to enable extrapolation of spectral information across …
-
DreamAudio model enables customized text-to-audio generation with diffusion models
Researchers have introduced DreamAudio, a new framework for customized text-to-audio generation. This system allows models to identify and incorporate specific acoustic characteristics from user-provided reference audio…
-
New AI models enhance image and video super-resolution with diffusion and efficient architectures
Researchers are developing new methods for image and video super-resolution using advanced AI techniques. Several papers explore diffusion models for joint spatiotemporal super-resolution, enabling adaptation across dif…
-
AI learners seek foundational knowledge beyond hands-on guides
A user on Hacker News is seeking recommendations for learning AI from first principles, specifically requesting resources that focus on foundational concepts rather than practical implementation guides or LLM-specific m…
-
Diffusion Models for Video Generation
Researchers are exploring advanced diffusion models for video generation, addressing challenges like temporal consistency and data scarcity. New methods focus on improving parameterization, such as the v-prediction tech…