CompVis

university

https://ommer-lab.com/

CompVis

AI & ML interests

Generative approaches for visual synthesis, Invertible deep models for explainable AI, Deep metric and representation learning, self-supervised learning paradigms

Recent Activity

lvwerra authored a paper about 1 month ago

FineWeb2: One Pipeline to Scale Them All -- Adapting Pre-Training Data Processing to Every Language

stellaathena authored a paper about 2 months ago

Emergent and Predictable Memorization in Large Language Models

stellaathena authored a paper about 2 months ago

KMMLU: Measuring Massive Multitask Language Understanding in Korean

View all activity

lvwerra

authored a paper about 1 month ago

FineWeb2: One Pipeline to Scale Them All -- Adapting Pre-Training Data Processing to Every Language

Paper • 2506.20920 • Published Jun 26 • 64

multimodalart

posted an update about 1 month ago

Post

8491

Self-Forcing - a real-time video distilled model from Wan 2.1 by @adobe is out, and they open sourced it 🐐

I've built a live real time demo on Spaces 📹💨

multimodalart/self-forcing

5 replies

·

stellaathena

authored 10 papers about 2 months ago

Emergent and Predictable Memorization in Large Language Models

Paper • 2304.11158 • Published Apr 21, 2023

KMMLU: Measuring Massive Multitask Language Understanding in Korean

Paper • 2402.11548 • Published Feb 18, 2024

Eagle and Finch: RWKV with Matrix-Valued States and Dynamic Recurrence

Paper • 2404.05892 • Published Apr 8, 2024 • 39

The Responsible Foundation Model Development Cheatsheet: A Review of Tools & Resources

Paper • 2406.16746 • Published Jun 24, 2024

Consent in Crisis: The Rapid Decline of the AI Data Commons

Paper • 2407.14933 • Published Jul 20, 2024 • 12

Lessons from the Trenches on Reproducible Evaluation of Language Models

Paper • 2405.14782 • Published May 23, 2024

Bridging the Data Provenance Gap Across Text, Speech and Video

Paper • 2412.17847 • Published Dec 19, 2024 • 10

Recite, Reconstruct, Recollect: Memorization in LMs as a Multifaceted Phenomenon

Paper • 2406.17746 • Published Jun 25, 2024

When AI Co-Scientists Fail: SPOT-a Benchmark for Automated Verification of Scientific Research

Paper • 2505.11855 • Published May 17 • 10

The Common Pile v0.1: An 8TB Dataset of Public Domain and Openly Licensed Text

Paper • 2506.05209 • Published Jun 5 • 44

dimakot55

in CompVis/EDGS 2 months ago

Apply for community grant: Academic project (gpu)

#1 opened 4 months ago by

magistrkoljan

in CompVis/EDGS 2 months ago

Update app.py

#5 opened 3 months ago by

dimakot55

in CompVis/EDGS 3 months ago

تخت بستری بیمار

#4 opened 3 months ago by

Differences with the Colab

#3 opened 3 months ago by

SomeoneSomething

magistrkoljan

authored 2 papers 3 months ago

EDGS: Eliminating Densification for Efficient Convergence of 3DGS

Paper • 2504.13204 • Published Apr 15 • 3

WaSt-3D: Wasserstein-2 Distance for Scene-to-Scene Stylization on 3D Gaussians

Paper • 2409.17917 • Published Sep 26, 2024

magistrkoljan

updated a Space 3 months ago

EDGS

Create 3D models from videos or images

magistrkoljan

in CompVis/EDGS 3 months ago

Apply for community grant: Academic project (gpu)

#1 opened 4 months ago by