DataComp

dclm's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Articles

richardaecn 

authored 13 papers 2 days ago

Unified Visual Relationship Detection with Vision and Language Models

Paper • 2303.08998 • Published Mar 16, 2023

The iNaturalist Species Classification and Detection Dataset

Paper • 1707.06642 • Published Jul 20, 2017

Alternating Gradient Descent and Mixture-of-Experts for Integrated Multimodal Perception

Paper • 2305.06324 • Published May 10, 2023 • 1

Fashionpedia: Ontology, Segmentation, and an Attribute Localization Dataset

Paper • 2004.12276 • Published Apr 26, 2020 • 1

Spatiotemporal Contrastive Video Representation Learning

Paper • 2008.03800 • Published Aug 9, 2020

Simple Copy-Paste is a Strong Data Augmentation Method for Instance Segmentation

Paper • 2012.07177 • Published Dec 13, 2020

DaTaSeg: Taming a Universal Multi-Dataset Multi-Task Segmentation Model

Paper • 2306.01736 • Published Jun 2, 2023 • 1

Open-vocabulary Object Detection via Vision and Language Knowledge Distillation

Paper • 2104.13921 • Published Apr 28, 2021

VideoGLUE: Video General Understanding Evaluation of Foundation Models

Paper • 2307.03166 • Published Jul 6, 2023 • 5

A Simple Zero-shot Prompt Weighting Technique to Improve Prompt Ensembling in Text-Image Models

Paper • 2302.06235 • Published Feb 13, 2023

Edify Image: High-Quality Image Generation with Pixel Space Laplacian Diffusion Models

Paper • 2411.07126 • Published Nov 11, 2024 • 30

Edify 3D: Scalable High-Quality 3D Asset Generation

Paper • 2411.07135 • Published Nov 11, 2024

Cosmos-Reason1: From Physical Common Sense To Embodied Reasoning

Paper • 2503.15558 • Published 7 days ago • 39

thomwolf 

posted an update 14 days ago

view post

Post

2585

We've kept pushing our Open-R1 project, an open initiative to replicate and extend the techniques behind DeepSeek-R1.

And even we were mind-blown by the results we got with this latest model we're releasing: ⚡️OlympicCoder ( open-r1/OlympicCoder-7B and open-r1/OlympicCoder-32B)

It's beating Claude 3.7 on (competitive) programming –a domain Anthropic has been historically really strong at– and it's getting close to o1-mini/R1 on olympiad level coding with just 7B parameters!

And the best part is that we're open-sourcing all about its training dataset, the new IOI benchmark, and more in our Open-R1 progress report #3: https://huggingface.co/blog/open-r1/update-3

Datasets are are releasing:
- open-r1/codeforces
- open-r1/codeforces-cots
- open-r1/ioi
- open-r1/ioi-test-cases
- open-r1/ioi-sample-solutions
- open-r1/ioi-cots
- open-r1/ioi-2024-model-solutions

See translation

• 

🔥

9

9

🚀

6

6

❤️

1

1

+

Reply

orionweller 

authored a paper 15 days ago

Beyond RAG: Task-Aware KV Cache Compression for Comprehensive Knowledge Reasoning

Paper • 2503.04973 • Published 20 days ago • 21

Wanfq 

authored a paper 19 days ago

FuseChat-3.0: Preference Optimization Meets Heterogeneous Model Fusion

Paper • 2503.04222 • Published 20 days ago • 13

AmeyaPrabhu 

authored 4 papers 27 days ago

A Practitioner's Guide to Continual Multimodal Pretraining

Paper • 2408.14471 • Published Aug 26, 2024

CiteME: Can Language Models Accurately Cite Scientific Claims?

Paper • 2407.12861 • Published Jul 10, 2024

Open Problems in Machine Unlearning for AI Safety

Paper • 2501.04952 • Published Jan 9 • 2

Humanity's Last Exam

Paper • 2501.14249 • Published Jan 24 • 71