Gabriel C's picture

Gabriel C PRO

gabrielchua

·

https://gabrielchua.me

AI & ML interests

Large Language Models, AI Safety, Causal Inference

Recent Activity

upvoted a collection 10 days ago

MinorBench 🍎

liked a dataset 10 days ago

govtech/MinorBench

upvoted a paper 13 days ago

MinorBench: A hand-built benchmark for content-based risks for children

View all activity

Organizations

gabrielchua's activity

upvoted a collection 10 days ago

MinorBench 🍎

2 items • Updated 14 days ago • 1

upvoted a paper 13 days ago

MinorBench: A hand-built benchmark for content-based risks for children

Paper • 2503.10242 • Published 15 days ago • 4

upvoted a collection 15 days ago

Gemma 3 Release

17 items • Updated about 12 hours ago • 297

upvoted a paper 29 days ago

Safe at the Margins: A General Approach to Safety Alignment in Low-Resource English Languages -- A Singlish Case Study

Paper • 2502.12485 • Published Feb 18 • 1

upvoted 2 papers 4 months ago

A Flexible Large Language Models Guardrail Development Methodology Applied to Off-Topic Prompt Detection

Paper • 2411.12946 • Published Nov 20, 2024 • 22

PaliGemma 2: A Family of Versatile VLMs for Transfer

Paper • 2412.03555 • Published Dec 4, 2024 • 134

upvoted 3 collections 4 months ago

Coding Assistants in the Public Service 💻

1 item • Updated Nov 25, 2024 • 1

Off Topic Guardrail 🛡️

Fast, lightweight zero-shot classifiers for user prompt's relevance to the system prompt. • 5 items • Updated Nov 25, 2024 • 4

LionGuard 🦁

A Singapore-contextualized moderation classifier. • 2 items • Updated Nov 25, 2024 • 1

upvoted 3 papers 4 months ago

Harnessing the Potential of Gen-AI Coding Assistants in Public Sector Software Development

Paper • 2409.17434 • Published Sep 25, 2024 • 1

LionGuard: Building a Contextualized Moderation Classifier to Tackle Localized Unsafe Content

Paper • 2407.10995 • Published Jun 24, 2024 • 1

Insight-V: Exploring Long-Chain Visual Reasoning with Multimodal Large Language Models

Paper • 2411.14432 • Published Nov 21, 2024 • 25

upvoted 2 collections 7 months ago

1.5-Pints

1.5 Pints is a Large Language Model that significantly advances the efficiency of LLM training by emphasizing data quality over quantity. • 4 items • Updated Aug 8, 2024 • 3

WebInstruct 🌐 Embeddings 🧱 Models

A collection of SoTA embeddings model fine-tuned on WebInstruct dataset to learn to pair instructions with its responses • 3 items • Updated Sep 4, 2024 • 11

upvoted a paper 12 months ago

Sailor: Open Language Models for South-East Asia

Paper • 2404.03608 • Published Apr 4, 2024 • 20

upvoted a collection about 1 year ago

Zeroshot Classifiers

These are my current best zeroshot classifiers. Some of my older models are downloaded more often, but the models in this collection are newer/better. • 12 items • Updated Jan 6 • 129