🥤 Cola [NeurIPS 2023]
Large Language Models are Visual Reasoning Coordinators
Liangyu Chen*,†,♥ Bo Li*,♥ Sheng Shen♣ Jingkang Yang♥
Chunyuan Li♠ Kurt Keutzer♣ Trevor Darrell♣ Ziwei Liu✉,♥
♥S-Lab, Nanyang Technological University
♣University of California, Berkeley ♠Microsoft Research, Redmond
*Equal Contribution †Project Lead ✉Corresponding Author... See more
Large Language Models are Visual Reasoning Coordinators
Liangyu Chen*,†,♥ Bo Li*,♥ Sheng Shen♣ Jingkang Yang♥
Chunyuan Li♠ Kurt Keutzer♣ Trevor Darrell♣ Ziwei Liu✉,♥
♥S-Lab, Nanyang Technological University
♣University of California, Berkeley ♠Microsoft Research, Redmond
*Equal Contribution †Project Lead ✉Corresponding Author... See more
cliangyu • GitHub - cliangyu/Cola: [NeurIPS2023] Official implementation of the paper "Large Language Models are Visual Reasoning Coordinators"
The Dawn of LMMs: Preliminary Explorations with GPT-4V(ision)
An analysis of GPT-4V, a large multimodal model with visual understanding, discussing its capabilities, input modes, working modes, prompting techniques, and potential applications in various domains.
browse.arxiv.org
Key unlock: Multimodal models can reason about images, video, or even physical environments without significant tailoring.
Sarah Wang • The Next Token of Progress: 4 Unlocks on the Generative AI Horizon
探索机器学习的宇宙：全面解析流行模型
这幅图详细展示了各种流行的机器学习模型及其分类，帮助我们理解每种方法的应用场景和特点：
1. 监督学习：
- 分类：用于将数据点分入预定义的类别中，如kNN、逻辑回归、朴素贝叶斯、决策树和支持向量机（SVM）。
- 回归：预测连续值输出，包括线性回归、多项式回归、Lasso和Ridge。
2. 无监督学习：
- 聚类：将数据分组为自然形成的集群，如k-means、DBSCAN和模糊C均值。
- 模式搜索：如Apriori和ECLAT，用于发现数据中的频繁模式。
- 降维技术：PCA、LDA等，用于减少特征数量，提高计算效率。
3. 强化学习：
- 使用如Q-Learning和深度Q网络（DQN），用于训练智能体... See more