Gen-Verse/dLLM-RL

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

LLM & foundation modelsPython Apache-2.0 45created 2025-08-26

Stars

523

1-day growth

7-day growth

—

30-day growth

—

Star history

Tracked since 2026-11-13

#code-generation#diffusion-language-models#large-language-models#llm-reasoning#mathmatical-reasoning#reinforcement-learning-algorithms#rlhf

Top contributors

Not collected yet (contributors job).