Energy-navigated trajectory shaping during training produces 8-step discrete flow matching students that achieve 32% lower perplexity than 1024-step teachers on 170M language models with unchanged inference cost.
The Thirteenth International Conference on Learning Representations , year=
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 4years
2026 4roles
background 1polarities
unclear 1representative citing papers
SSOPD converts intra-group correct-wrong contrast into process supervision by distilling a teacher distribution from the shortest correct completion into prefixes of the longest wrong completion, improving GRPO on AIME and HMMT benchmarks.
Byte modeling incurs greater scaling overhead for masked diffusion than autoregressive models because the diffusion objective destroys local byte contiguity needed to resolve semantics.
citing papers explorer
-
Trajectory as the Teacher: Few-Step Discrete Flow Matching via Energy-Navigated Distillation
Energy-navigated trajectory shaping during training produces 8-step discrete flow matching students that achieve 32% lower perplexity than 1024-step teachers on 170M language models with unchanged inference cost.
-
Self-Supervised On-Policy Distillation for Reasoning Language Models
SSOPD converts intra-group correct-wrong contrast into process supervision by distilling a teacher distribution from the shortest correct completion into prefixes of the longest wrong completion, improving GRPO on AIME and HMMT benchmarks.
-
The Efficiency Gap in Byte Modeling
Byte modeling incurs greater scaling overhead for masked diffusion than autoregressive models because the diffusion objective destroys local byte contiguity needed to resolve semantics.