Learned Relay Representations add a differentiable per-token channel to masked diffusion models so they can propagate latent information across iterative denoising steps, yielding better coding performance and up to 32% lower latency on Fast-dLLM v2 than standard supervised finetuning.
There is no 16-clue sudoku: Solving the sudoku minimum number of clues problem via hitting set enumeration
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
Derives explicit formula for updated boundary and coboundary operators after critical pair cancellation in discrete Morse theory using original operators.
citing papers explorer
-
Learned Relay Representations for Forward-Thinking Discrete Diffusion Models
Learned Relay Representations add a differentiable per-token channel to masked diffusion models so they can propagate latent information across iterative denoising steps, yielding better coding performance and up to 32% lower latency on Fast-dLLM v2 than standard supervised finetuning.