Machine Learning

machinelearning@kbin.social

PostsComments

nsa@kbin.social · 2 years ago

What's In My Big Data?

0

2

What's In My Big Data?

nsa@kbin.social · 2 years ago

0

nsa@kbin.social · 2 years ago

The Data Provenance Initiative: A Large Scale Audit of Dataset Licensing & Attribution in AI

0

2

The Data Provenance Initiative: A Large Scale Audit of Dataset Licensing & Attribution in AI

nsa@kbin.social · 2 years ago

0

KingsmanVince@kbin.social · 2 years ago

MM-SHAP: A Performance-agnostic Metric for Measuring Multimodal Contributions in Vision and Language Models & Tasks

aclanthology.org

0

2

MM-SHAP: A Performance-agnostic Metric for Measuring Multimodal Contributions in Vision and Language Models & Tasks

aclanthology.org

KingsmanVince@kbin.social · 2 years ago

0

KingsmanVince@kbin.social · 2 years ago

Demystifying CLIP Data

0

2

Demystifying CLIP Data

KingsmanVince@kbin.social · 2 years ago

0

nsa@kbin.social · 2 years ago

GPT-4 Doesn't Know It's Wrong: An Analysis of Iterative Prompting for Reasoning Problems

0

1

GPT-4 Doesn't Know It's Wrong: An Analysis of Iterative Prompting for Reasoning Problems

nsa@kbin.social · 2 years ago

0

KingsmanVince@kbin.social · 2 years ago

PaLI-3 Vision Language Models: Smaller, Faster, Stronger

3

2

PaLI-3 Vision Language Models: Smaller, Faster, Stronger

KingsmanVince@kbin.social · 2 years ago

3

KingsmanVince@kbin.social · 2 years ago

MiniGPT-v2: large language model as a unified interface for vision-language multi-task learning

0

3

MiniGPT-v2: large language model as a unified interface for vision-language multi-task learning

KingsmanVince@kbin.social · 2 years ago

0

KingsmanVince@kbin.social · 2 years ago

Finetune Like You Pretrain: Improved Finetuning of Zero-Shot Vision Models

openaccess.thecvf.com

0

2

Finetune Like You Pretrain: Improved Finetuning of Zero-Shot Vision Models

openaccess.thecvf.com

KingsmanVince@kbin.social · 2 years ago

0

nsa@kbin.social · 2 years ago

A Long Way to Go: Investigating Length Correlations in RLHF

0

2

A Long Way to Go: Investigating Length Correlations in RLHF

nsa@kbin.social · 2 years ago

0

nsa@kbin.social · 2 years ago

Think before you speak: Training Language Models With Pause Tokens

1

3

Think before you speak: Training Language Models With Pause Tokens

nsa@kbin.social · 2 years ago

1

KingsmanVince@kbin.social · 2 years ago

CLIPN for Zero-Shot OOD Detection: Teaching CLIP to Say No

0

3

CLIPN for Zero-Shot OOD Detection: Teaching CLIP to Say No

KingsmanVince@kbin.social · 2 years ago

0

nsa@kbin.social · 2 years ago

Language Modeling Is Compression

0

2

Language Modeling Is Compression

nsa@kbin.social · 2 years ago

0

KingsmanVince@kbin.social · 2 years ago

Scaling Vision-Language Models with Sparse Mixture of Experts

0

3

Scaling Vision-Language Models with Sparse Mixture of Experts

KingsmanVince@kbin.social · 2 years ago

0

KingsmanVince@kbin.social · 2 years ago

Hydra-MoE: A new class of Open-Source Mixture of Experts

0

4

Hydra-MoE: A new class of Open-Source Mixture of Experts

KingsmanVince@kbin.social · 2 years ago

0

KingsmanVince@kbin.social · 2 years ago

Bridging the Gap: Exploring the Capabilities of Bridge-Architectures for Complex Visual Reasoning Tasks

0

3

Bridging the Gap: Exploring the Capabilities of Bridge-Architectures for Complex Visual Reasoning Tasks

KingsmanVince@kbin.social · 2 years ago

0

KingsmanVince@kbin.social · 2 years ago

Foundational Models Defining a New Era in Vision: A Survey and Outlook

0

3

Foundational Models Defining a New Era in Vision: A Survey and Outlook

KingsmanVince@kbin.social · 2 years ago

0

KingsmanVince@kbin.social · 2 years ago

Unifying Cross-Lingual and Cross-Modal Modeling Towards Weakly Supervised Multilingual Vision-Language Pre-training

aclanthology.org

1

5

Unifying Cross-Lingual and Cross-Modal Modeling Towards Weakly Supervised Multilingual Vision-Language Pre-training

aclanthology.org

KingsmanVince@kbin.social · 2 years ago

1

KingsmanVince@kbin.social · 2 years ago

MaMMUT: A Simple Architecture for Joint Learning for MultiModal Tasks

1

3

MaMMUT: A Simple Architecture for Joint Learning for MultiModal Tasks

KingsmanVince@kbin.social · 2 years ago

1

KingsmanVince@kbin.social · 2 years ago

Vision Language Transformers: A Survey

0

3

Vision Language Transformers: A Survey

KingsmanVince@kbin.social · 2 years ago

0

Lenguador@kbin.social · 2 years ago

Real-Time Radiance Field Rendering

0

1

Real-Time Radiance Field Rendering

Lenguador@kbin.social · 2 years ago

0

Machine Learning@kbin.social

machinelearning@kbin.social

You are not logged in. However you can subscribe from another Fediverse account, for example Lemmy or Mastodon. To do this, paste the following into the search field of your instance: !machinelearning@kbin.social

Machine learning (ML) is a field devoted to understanding and building methods that let machines “learn” – that is, methods that leverage data to improve computer performance on some set of tasks. Machine learning algorithms build a model based on sample data, known as training data, in order to make predictions or decisions without being explicitly programmed to do so. Machine learning algorithms are used in a wide variety of applications, such as in medicine, email filtering, speech recognition, agriculture, and computer vision, where it is difficult or unfeasible to develop conventional algorithms to perform the needed tasks.

Visibility: Public

This community can be federated to other instances and be posted/commented in by their users.

1 user / day
1 user / week
1 user / month
1 user / 6 months
2 local subscribers
2 subscribers
22 Posts
8 Comments
Modlog

mods: