๐๐๐
1/ The original GFlowNets paper tried PPO for sampling, but it failed. We figured out why and fixed it. And now PPO beats all objectives on standard problems including molecular graph generation in large spaces.
Masked diffusion can do math in just 8 calls?! ๐คฏ๐คฏ๐คฏ
ReMaRL + frozen LLaDA-8B-Instruct on GSM8K
8 calls: 54%
16 calls: 65%
32 calls: 73%
Our policy learns to unmask and remask with GRPO. We reward only correct answers. A left-to-right bias emerges.
๏ฟฝ๏ฟฝ Recipe & insights โ
Latent diffusion for text usually freezes the encoder before diffusion training, so the diffusion model gets no say in its own latent space. We let its gradient in.
LDLM, NeurIPS 2026. Code and checkpoints below.
At NeurIPS in Paris? Let's grab coffee and talk about latent diffusion and latent communication between models.