The paper introduces Manta-LM, which approximates the Hamilton-Jacobi-Bellman optimal policy via Flow Matching in a rectified latent control space to enable high-fidelity parallel language generation.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
representative citing papers
Speculative decoding accelerates exact sampling from large autoregressive models by 2-3x on T5-XXL by running smaller approximation models in parallel to propose token sequences that the large model then verifies in batches while preserving the original output distribution.
citing papers explorer
-
Language Generation as Optimal Control: Closed-Loop Diffusion in Latent Control Space
The paper introduces Manta-LM, which approximates the Hamilton-Jacobi-Bellman optimal policy via Flow Matching in a rectified latent control space to enable high-fidelity parallel language generation.
-
Fast Inference from Transformers via Speculative Decoding
Speculative decoding accelerates exact sampling from large autoregressive models by 2-3x on T5-XXL by running smaller approximation models in parallel to propose token sequences that the large model then verifies in batches while preserving the original output distribution.