PetiteTech

non-profit

Activity Feed Request to join this org

AI & ML interests

None defined yet.

Recent Activity

ldwang authored a paper 1 day ago

MassAlloc Attention: Let Attention Allocate Its Own Compute

ldwang authored a paper 1 day ago

CoWindow Attention: Full Causal Coverage Is a Collective Property

ldwang authored a paper about 1 year ago

Trainable Dynamic Mask Sparse Attention

View all activity

authored 2 papers 1 day ago

MassAlloc Attention: Let Attention Allocate Its Own Compute

Paper • 2609.32712 • Published 6 days ago • 74

CoWindow Attention: Full Causal Coverage Is a Collective Property

Paper • 2609.32704 • Published 6 days ago • 66

authored a paper about 1 year ago

Trainable Dynamic Mask Sparse Attention

Paper • 2508.02124 • Published Aug 4, 2025 • 19

authored 2 papers over 1 year ago

Infinity Instruct: Scaling Instruction Selection and Synthesis to Enhance Language Models

Paper • 2506.11116 • Published Jun 9, 2025 • 5

CCI4.0: A Bilingual Pretraining Dataset for Enhancing Reasoning in Large Language Models

Paper • 2506.07463 • Published Jun 9, 2025 • 12

authored 3 papers almost 2 years ago

CCI3.0-HQ: a large-scale Chinese dataset of high quality designed for pre-training large language models

Paper • 2410.18505 • Published Oct 24, 2024 • 11

Infinity-MM: Scaling Multimodal Performance with Large-Scale and High-Quality Instruction Data

Paper • 2410.18558 • Published Oct 24, 2024 • 19

Emu3: Next-Token Prediction is All You Need

Paper • 2409.18869 • Published Sep 27, 2024 • 99

authored 2 papers about 2 years ago

AquilaMoE: Efficient Training for MoE Models with Scale-Up and Scale-Out Strategies

Paper • 2408.06567 • Published Aug 13, 2024 • 2

Aquila2 Technical Report

Paper • 2408.07410 • Published Aug 14, 2024 • 15