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
Spaces:
batesm
/
repro-dmpo
like
0
Running
App
Files
Files
Community
main
repro-dmpo
/
pages
66.8 kB
Ctrl+K
Ctrl+K
1 contributor
History:
1 commit
batesm
Update logbook: Repro - Enhancing Reasoning for Diffusion LLMs via Distribution Matching Policy Optimization
e15d864
verified
about 1 month ago
claim-1-dmpo-distribution-matching-via-cross-entropy
Update logbook: Repro - Enhancing Reasoning for Diffusion LLMs via Distribution Matching Policy Optimization
about 1 month ago
claim-2-weight-baseline-subtraction-for-small-batch-training
Update logbook: Repro - Enhancing Reasoning for Diffusion LLMs via Distribution Matching Policy Optimization
about 1 month ago
claim-3-r1-zero-like-recipe-without-sft
Update logbook: Repro - Enhancing Reasoning for Diffusion LLMs via Distribution Matching Policy Optimization
about 1 month ago
claim-4-benchmark-comparison-against-baselines
Update logbook: Repro - Enhancing Reasoning for Diffusion LLMs via Distribution Matching Policy Optimization
about 1 month ago
claim-5-accuracy-gains-up-to-54-3-over-sota
Update logbook: Repro - Enhancing Reasoning for Diffusion LLMs via Distribution Matching Policy Optimization
about 1 month ago
conclusion
Update logbook: Repro - Enhancing Reasoning for Diffusion LLMs via Distribution Matching Policy Optimization
about 1 month ago
index.md
Safe
695 Bytes
Update logbook: Repro - Enhancing Reasoning for Diffusion LLMs via Distribution Matching Policy Optimization
about 1 month ago
