Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Website
Tasks
HuggingChat
Collections
Languages
Organizations
Community
Blog
Posts
Daily Papers
Hardware
Learn
Discord
Forum
GitHub
Solutions
Team & Enterprise
Hugging Face PRO
Enterprise Support
Inference Providers
Inference Endpoints
Storage Buckets
Log In
Sign Up
FeiYuan
FeYuan
8
16
4
Follow
John6666's profile picture
apol's profile picture
ChengyouJia's profile picture
24 followers
·
6 following
t_feyuan
CONE-MT
AI & ML interests
Multilingual & Code Intelligence
Recent Activity
upvoted
a
paper
5 days ago
Drift-Constrained Optimization: Only Direction Matters in Fine-Tuning Instruct Models
upvoted
a
paper
5 days ago
Training Specialist Models without Reasoning Trajectories for Domain Expert Distillation
posted
an
update
9 days ago
Drift-Constrained Optimization: Only Direction Matters in Fine-Tuning Instruct Models Standard SFT usually ask: How can we SFT an instruct model without behavioral drift? We reverse the question: Given a fixed drift budget, how should we SFT? This predicts that changing *where* the model can move—not the supervision—can reverse fine-tuning failure. On Qwen3-8B and Qwen3-14B, it does. code: https://github.com/CONE-MT/DCO/tree/main/dco models: https://huggingface.co/collections/LLaMAX/dco
View all activity
Organizations
FeYuan
's activity
All
Models
Datasets
Spaces
Buckets
Papers
Collections
Community
Posts
Upvotes
Likes
Articles
liked
2 models
7 months ago
LLaMAX/GlotMAX-101-8B-LST
8B
•
Updated
Feb 25
•
24
•
4
LLaMAX/GlotMAX-101-14B-LST
15B
•
Updated
Feb 25
•
20
•
2
liked
a dataset
11 months ago
internlm/InteractScience
Viewer
•
Updated
Oct 31, 2025
•
150
•
561
•
6
liked
a Space
about 2 years ago
Runtime error
Agents
42
LLaMAX3-Translator
🌖
42
LLaMAX3 Translator