Aurora-M

community

https://aurora-lm.github.io/posts/about-us/

Activity Feed Request to join this org

AI & ML interests

Omni Lingual Models

Recent Activity

Taishi-N324 authored a paper 6 days ago

On the Optimal Reasoning Length for RL-Trained Language Models

felfri authored a paper 29 days ago

Who Evaluates AI's Social Impacts? Mapping Coverage and Gaps in First and Third Party Evaluations

felfri authored a paper 29 days ago

ActivationReasoning: Logical Reasoning in Latent Activation Spaces

View all activity

ajibawa-2023

posted an update about 5 hours ago

Post

219

Java-Code-Large ( ajibawa-2023/Java-Code-Large)

Java-Code-Large is a large-scale corpus of publicly available Java source code comprising more than 15 million java codes. The dataset is designed to support research in large language model (LLM) pretraining, code intelligence, software engineering automation, and program analysis.

By providing a high-volume, language-specific corpus, Java-Code-Large enables systematic experimentation in Java-focused model training, domain adaptation, and downstream code understanding tasks.

Taishi-N324

authored a paper 6 days ago

On the Optimal Reasoning Length for RL-Trained Language Models

Paper • 2602.09591 • Published 7 days ago • 3

felfri

authored 3 papers 29 days ago

Who Evaluates AI's Social Impacts? Mapping Coverage and Gaps in First and Third Party Evaluations

Paper • 2511.05613 • Published Nov 6, 2025

ActivationReasoning: Logical Reasoning in Latent Activation Spaces

Paper • 2510.18184 • Published Oct 21, 2025

Inference-time Physics Alignment of Video Generative Models with Latent World Models

Paper • 2601.10553 • Published Jan 15 • 12

Ziyang

authored a paper about 1 month ago

DiffCoT: Diffusion-styled Chain-of-Thought Reasoning in LLMs

Paper • 2601.03559 • Published Jan 7 • 14

terryyz

authored a paper 3 months ago

From Code Foundation Models to Agents and Applications: A Practical Guide to Code Intelligence

Paper • 2511.18538 • Published Nov 23, 2025 • 296

Locutusque

posted an update 3 months ago

Post

2755

🚀 AutoXLA - Accelerating Large Models on TPU
AutoXLA is an experimental library that automates the distribution, optimization, and quantization of large language models for TPUs using PyTorch/XLA. It extends the Hugging Face Transformers interface with TPU-aware features such as automatic sharding, custom attention kernels, and quantization-aware loading, making large-scale deployment and training both simpler and faster.
With quantization and Splash Attention kernels, AutoXLA achieves up to 4× speedups over standard Flash Attention implementations, significantly improving throughput for both inference and training workloads.
Whether you’re experimenting with distributed setups (FSDP, 2D, or 3D sharding) or optimizing memory via LanguageModelQuantizer, AutoXLA is built to make scaling LLMs on TPU seamless.
⚠️ Note: This is an experimental repository. Expect rough edges! Please report bugs or unexpected behavior through GitHub issues.
🔗 GitHub Repository: https://github.com/Locutusque/AutoXLA