This thesis aimstoinvestigate thepotential of discrete diffusion models in the context ofnaturallanguagegeneration.
Dream-Coder 7B is a diffusion LLM for code trained exclusively on open-source data across its development stages—adaptation, supervised fine-tuning, and reinforcement learning. It achieves an impressive 21.4% pass@1 on LiveCodeBench (2410-2505), outperforming other open-source diffusion LLMs by…
2026-04-07 Our Paper is accepted to ACL 2026 (main)! - 2026-01-13 Code of EvoToken-DLM Released! - 2026-01-12 Paper Released!