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.
Title resolution pending
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 3verdicts
UNVERDICTED 3roles
background 1polarities
background 1representative citing papers
On-policy distillation gains efficiency from early foresight in module allocation and low-rank update directions, enabling EffOPD to accelerate training by 3x via adaptive extrapolation without extra modules or tuning.
SHRED achieves retain-set-free LLM unlearning by selecting high-Shannon-information tokens for logit demotion in a single self-distillation KL objective, yielding a superior forget-utility Pareto front on four benchmarks.
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.
-
Learning to Foresee: Unveiling the Unlocking Efficiency of On-Policy Distillation
On-policy distillation gains efficiency from early foresight in module allocation and low-rank update directions, enabling EffOPD to accelerate training by 3x via adaptive extrapolation without extra modules or tuning.
-
SHRED: Retain-Set-Free Unlearning via Self-Distillation with Logit Demotion
SHRED achieves retain-set-free LLM unlearning by selecting high-Shannon-information tokens for logit demotion in a single self-distillation KL objective, yielding a superior forget-utility Pareto front on four benchmarks.