Yijun Liao

YijunLiao's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted a paper 26 days ago

IndexCache: Accelerating Sparse Attention via Cross-Layer Index Reuse

Paper • 2603.12201 • Published 28 days ago • 53

upvoted 2 papers about 2 months ago

GLM-5: from Vibe Coding to Agentic Engineering

Paper • 2602.15763 • Published Feb 17 • 136

SpargeAttention2: Trainable Sparse Attention via Hybrid Top-k+Top-p Masking and Distillation Fine-Tuning

Paper • 2602.13515 • Published Feb 13 • 44

updated 2 models 4 months ago

YijunLiao/DZ-TDPO-Phi-3.5-mini-instruct

Text Generation • 4B • Updated Dec 24, 2025 • 4

YijunLiao/DZ-TDPO-Qwen2.5-7B-Instruct

Text Generation • 8B • Updated Dec 24, 2025 • 3

New activity in YijunLiao/DZ-TDPO-Phi-3.5-mini-instruct 4 months ago

Improve model card: Add pipeline tag, library name, and GitHub link

1

#1 opened 4 months ago by

nielsr

published 2 models 4 months ago

YijunLiao/DZ-TDPO-Qwen2.5-7B-Instruct

Text Generation • 8B • Updated Dec 24, 2025 • 3

YijunLiao/DZ-TDPO-Phi-3.5-mini-instruct

Text Generation • 4B • Updated Dec 24, 2025 • 4

upvoted a paper 4 months ago

DZ-TDPO: Non-Destructive Temporal Alignment for Mutable State Tracking in Long-Context Dialogue

Paper • 2512.03704 • Published Dec 3, 2025 • 2

commented a paper 4 months ago

DZ-TDPO: Non-Destructive Temporal Alignment for Mutable State Tracking in Long-Context Dialogue

Paper • 2512.03704 • Published Dec 3, 2025 • 2 •

2

authored a paper 4 months ago

DZ-TDPO: Non-Destructive Temporal Alignment for Mutable State Tracking in Long-Context Dialogue

Paper • 2512.03704 • Published Dec 3, 2025 • 2