← Back to List
⚠
Notice:This resource is provided by a third-party author. Please review the code with AI tools or manually before use to ensure security and compatibility.
PythonGen-Verse/dLLM-RL

dLLM-RL

[ICLR 2026] Official code for TraceRL: Revolutionizing post-training for Diffusion LLMs, powering the SOTA TraDo series.

52.0/100
★ 500Forks: 41
View on GitHub →Homepage →
Loading report...

Similar Projects

align-anything

54

Align Anything: Training All-modality Model with Feedback

Python★ 4.7K

llm-sandbox

82

Lightweight and portable LLM sandbox runtime (code interpreter) Python library.

Python★ 1.1K

langflow

95

Langflow is a powerful tool for building and deploying AI-powered agents and workflows.

Python★ 147.9K

LlamaFactory

92

Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

Python★ 71.1K
← Back to List