2024.11.13 每日AI论文 | 三维物体分割新框架，多模态理解生成模型
Listen now
Description
本期的 6 篇论文如下：
[00:28] 🔍 SAMPart3D: Segment Any Part in 3D Objects（SAMPart3D：三维物体任意部分分割）
[01:06] 🌐 JanusFlow: Harmonizing Autoregression and Rectified Flow for Unified Multimodal Understanding and Generation（JanusFlow：统一自回归与校正流的多模态理解与生成）
[01:42] 🤔 Stronger Models are NOT Stronger Teachers for Instruction Tuning（更强的模型并非更强的指令调优教师）
[02:21] 🌐 Wavelet Latent Diffusion (Wala): Billion-Parameter 3D Generative Model with Compact Wavelet Encodings（小波潜在扩散（WaLa）：具有紧凑小波编码的十亿参数3D生成模型）
[03:02] 📚 BLIP3-KALE: Knowledge Augmented Large-Scale Dense Captions（BLIP3-KALE：知识增强的大规模密集字幕）
[03:55] 🔍 Hardware and Software Platform Inference（硬件与软件平台推断）
【关注我们】
您还可以在以下平台找到我们，获得播客内容以外更多信息
小红书: AI速递
More Episodes
本期的 5 篇论文如下：
[00:41] TOP1(🔥93) | 🧠 LLaVA-o1: Let Vision Language Models Reason Step-by-Step（LLaVA-o1：让视觉语言模型逐步推理）
[02:41] TOP2(🔥55) | 🌍 Generative World Explorer（生成世界探索者）
[05:00] TOP3(🔥44) | 🧠 Enhancing the Reasoning Ability of Multimodal Large Language Models via Mixed Preference...
Published 11/23/24
Published 11/23/24
本期的 14 篇论文如下：
[00:26] 🧠 Enhancing the Reasoning Ability of Multimodal Large Language Models via Mixed Preference Optimization（通过混合偏好优化提升多模态大语言模型的推理能力）
[01:12] 🌐 Multimodal Autoregressive Pre-training of Large Vision Encoders（大规模视觉编码器多模态自回归预训练）
[01:55] 🧠 Marco-o1: Towards Open Reasoning Models for...
Published 11/22/24
Links
Twitter
Facebook
Instagram
Patreon
Genres
Artwork or description wrong?
Request an update »
Updates may take a few minutes.
Do you host a podcast?
Track your ranks and reviews from Spotify, Apple Podcasts and more.
