On the Design of Qwen3.8-Next Architecture: Evaluation, Efficiency, and Training Stability
Paper • 2608.30320 • Published • 57
🔄 In a Training Loop
Vikash Kr
vkshdev
AI & ML interests
NLP, CV, transformers, LLMs, fine‑tuning, modeling, validation, MLOps
Recent Activity
liked a model about 23 hours ago
google/timesfm-3.0-pytorch updated a bucket about 23 hours ago
vkshdev/MiniCPM5-2B published a bucket about 23 hours ago
vkshdev/MiniCPM5-2BOrganizations
upvoted a paper 2 days ago
upvoted an article 3 days ago
Article
NeoMME: an efficient Multimodal-native and Multilingual Encoder
Hcompany
• • 89 upvoted an article 5 days ago
Article
Fine-tuning a 350M Model for Better Structured Outputs in 100 GRPO Steps
- +1
iamleonie, burtenshaw, sergiopaniego
• • 88 upvoted a paper 5 days ago
upvoted 2
papers 8 days ago
upvoted a paper 9 days ago