Open-ψ (Open-Sci) Collective

non-profit

https://discord.gg/R7Ct3YHJvC

AI & ML interests

Researching and building foundation models with improved generalization and reasoning. LAION & friends spin-off for open-sourcing foundation models with strong generalization and reasoning , including datasets necessary for their creation, to serve as common open, reproducible grounds for further research experiments.

Recent Activity

JJitsev authored a paper about 14 hours ago

Project Alexandria: Towards Freeing Scientific Knowledge from Copyright Burdens via LLMs

Taishi-N324 authored a paper 1 day ago

Drop-Upcycling: Training Sparse Mixture of Experts with Partial Re-initialization

Taishi-N324 authored a paper 4 months ago

Agent Skill Acquisition for Large Language Models via CycleQD

View all activity

open-sci's activity

JJitsev

authored a paper about 14 hours ago

Project Alexandria: Towards Freeing Scientific Knowledge from Copyright Burdens via LLMs

Paper • 2502.19413 • Published 2 days ago • 14

Taishi-N324

authored a paper 1 day ago

Drop-Upcycling: Training Sparse Mixture of Experts with Partial Re-initialization

Paper • 2502.19261 • Published 2 days ago • 4

Taishi-N324

authored a paper 4 months ago

Agent Skill Acquisition for Large Language Models via CycleQD

Paper • 2410.14735 • Published Oct 16, 2024 • 2

JJitsev

authored 8 papers 5 months ago

A Comparative Study on Generative Models for High Resolution Solar Observation Imaging

Paper • 2304.07169 • Published Apr 14, 2023

DataComp: In search of the next generation of multimodal datasets

Paper • 2304.14108 • Published Apr 27, 2023 • 2

LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairs

Paper • 2111.02114 • Published Nov 3, 2021

LAION-5B: An open large-scale dataset for training next generation image-text models

Paper • 2210.08402 • Published Oct 16, 2022 • 4

Reproducible scaling laws for contrastive language-image learning

Paper • 2212.07143 • Published Dec 14, 2022

Alice in Wonderland: Simple Tasks Showing Complete Reasoning Breakdown in State-Of-the-Art Large Language Models

Paper • 2406.02061 • Published Jun 4, 2024 • 1

DataComp-LM: In search of the next generation of training sets for language models

Paper • 2406.11794 • Published Jun 17, 2024 • 50

Resolving Discrepancies in Compute-Optimal Scaling of Language Models

Paper • 2406.19146 • Published Jun 27, 2024

Taishi-N324

authored 3 papers 8 months ago

Continual Pre-Training for Cross-Lingual LLM Adaptation: Enhancing Japanese Language Capabilities

Paper • 2404.17790 • Published Apr 27, 2024 • 5

Building a Large Japanese Web Corpus for Large Language Models

Paper • 2404.17733 • Published Apr 27, 2024 • 4

LLM-jp: A Cross-organizational Project for the Research and Development of Fully Open Japanese LLMs

Paper • 2407.03963 • Published Jul 4, 2024 • 16

TomerPorian

authored a paper 8 months ago

Resolving Discrepancies in Compute-Optimal Scaling of Language Models

Paper • 2406.19146 • Published Jun 27, 2024

Taishi-N324

authored a paper 11 months ago

Aurora-M: The First Open Source Multilingual Language Model Red-teamed according to the U.S. Executive Order

Paper • 2404.00399 • Published Mar 30, 2024 • 42

JJitsev

authored a paper 12 months ago

Language models scale reliably with over-training and on downstream tasks

Paper • 2403.08540 • Published Mar 13, 2024 • 15

marianna13

authored a paper 12 months ago

Language models scale reliably with over-training and on downstream tasks

Paper • 2403.08540 • Published Mar 13, 2024 • 15

marianna13

authored a paper over 1 year ago

MusicLDM: Enhancing Novelty in Text-to-Music Generation Using Beat-Synchronous Mixup Strategies

Paper • 2308.01546 • Published Aug 3, 2023 • 18

JJitsev

authored a paper over 1 year ago

OpenFlamingo: An Open-Source Framework for Training Large Autoregressive Vision-Language Models

Paper • 2308.01390 • Published Aug 2, 2023 • 33