Cohere Labs Community

community

https://cohere.com/research

Cohere-Labs-Community

Activity Feed Request to join this org

AI & ML interests

None defined yet.

Recent Activity

jjzha authored a paper 2 days ago

Multilingual GSM-Symbolic: What determines capability transfer across languages?

aashiqmuhamed authored a paper 20 days ago

Decoy Direction Optimization: A Post-Hoc Defense Against LLM Abliteration

aashiqmuhamed authored a paper 20 days ago

Pick Your Poison: Learning to Select Poison Sets for Stronger LLM Backdoor Attacks

View all activity

posted an update about 2 hours ago

Post

48

OneDecision-VisionGuard-Demo is now available on Hugging Face Spaces!

🤗 Space: prithivMLmods/OneDecision-VisionGuard-Demo

This demo showcases the OneDecision-VisionGuard family of multimodal image classification models for detecting NSFW and other sensitive visual content, with structured JSON reasoning, improved accuracy, and better handling of edge cases such as sensitive imagery, uncensored analysis, scene descriptions, and classification reasoning.

📦 Models: 27B, 9B, 4B — prithivMLmods/OneDecision-VisionGuard-27B-SFT, prithivMLmods/OneDecision-VisionGuard-9B-SFT, prithivMLmods/OneDecision-VisionGuard-4B-SFT

↗️ Collection: https://huggingface.co/collections/prithivMLmods/onedecision-visionguard

To learn more, visit the app page or the respective model pages.

authored a paper 2 days ago

Multilingual GSM-Symbolic: What determines capability transfer across languages?

Paper • 2610.03367 • Published 5 days ago • 47

posted an update 14 days ago

Post

3892

Qwen-Image-2.1 Plug and Play LoRA App is now live on Hugging Face Spaces.

🔗 Space: prithivMLmods/Qwen-Image-2.1-LoRAs-PnP

It supports standard inference, 4-step Turbo inference, custom LoRA lazy repacks, and LoRA Plug and Play (PnP), all in one setting!

🔗 Qwen-Image-2.1 Image-to-Image LoRAs: https://huggingface.co/collections/prithivMLmods/qwen-image-21-image-to-image-loras

🔗 GitHub: https://github.com/PRITHIVSAKTHIUR/Qwen-Image-2.1-LoRAs-PnP

To learn more, visit the app page or the respective model pages.

posted an update 21 days ago

Post

837

VisionGuardrail EVO-2, a multimodal image-classification content-safety model based on Qwen/Qwen3.8-27B, is now available on the Hub!

Stricter image classification than before, with a dense 27-billion-parameter multimodal model, more precise reasoning, and improved captions for classifying visual media.

➠ Models: prithivMLmods/VisionGuardrail-Evo2-27B, prithivMLmods/VisionGuardrail-Evo2-27B-GGUF

➠ Collection: https://huggingface.co/collections/prithivMLmods/visionguardrail-evo2

➠ Previous Models: https://huggingface.co/collections/prithivMLmods/visionguardrail-collection

⤷ To learn more, visit the app page or the respective model pages.

JuliaKreutzerCohere

authored 16 papers 21 days ago

Building Multilingual Bridges: Data Mixing as the Pillar of Generalization for In-Language Reasoning

Paper • 2609.10445 • Published 28 days ago • 35

The Culture Funnel: You Can't Align What isn't in the Data

Paper • 2606.13808 • Published Jun 11

Tiny Aya: Bridging Scale and Multilingual Depth

Paper • 2603.11510 • Published Mar 12 • 10

The Art of Asking: Multilingual Prompt Optimization for Synthetic Data

Paper • 2510.19806 • Published Oct 22, 2025 • 1

Making, not Taking, the Best of N

Paper • 2510.00931 • Published Oct 1, 2025 • 11

When Life Gives You Samples: The Benefits of Scaling up Inference Compute for Multilingual LLMs

Paper • 2506.20544 • Published Jun 25, 2025 • 11

Treasure Hunt: Real-time Targeting of the Long Tail using Training-Time Markers

Paper • 2506.14702 • Published Jun 17, 2025 • 3

LLM See, LLM Do: Guiding Data Generation to Target Non-Differentiable Objectives

Paper • 2407.01490 • Published Jul 1, 2024 • 1

The Multilingual Alignment Prism: Aligning Global and Local Preferences to Reduce Harm

Paper • 2406.18682 • Published Jun 26, 2024 • 1

A Few Thousand Translations Go a Long Way! Leveraging Pre-trained Models for African News Translation

Paper • 2205.02022 • Published May 4, 2022

Revisiting the Weaknesses of Reinforcement Learning for Neural Machine Translation

Paper • 2106.08942 • Published Jun 16, 2021

Quality at a Glance: An Audit of Web-Crawled Multilingual Datasets

Paper • 2103.12028 • Published Mar 22, 2021 • 3

MasakhaNER: Named Entity Recognition for African Languages

Paper • 2103.11811 • Published Mar 22, 2021

KINNEWS and KIRNEWS: Benchmarking Cross-Lingual Text Classification for Kinyarwanda and Kirundi

Paper • 2010.12174 • Published Oct 23, 2020

Participatory Research for Low-resourced Machine Translation: A Case Study in African Languages

Paper • 2010.02353 • Published Oct 5, 2020

Masakhane -- Machine Translation For Africa

Paper • 2003.11529 • Published Mar 13, 2020