Speculative sampling accelerates LLM decoding 2-2.5x by letting a draft model propose short sequences that the target model scores in parallel, then applies modified rejection sampling to keep the exact target distribution.
Sequence-level knowledge distillation
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
representative citing papers
In on-policy distillation, tokens with high student entropy or low entropy plus high teacher divergence provide dense corrective signal, allowing effective training on under 20% of tokens across math and planning tasks.
NPD accelerates on-policy distillation 8.1 times faster than baselines by using asynchronous SFT with Δ-IFD filtering, outperforming standard SFT and enabling a 1B model to achieve 68.73% SOTA score.
citing papers explorer
-
Accelerating Large Language Model Decoding with Speculative Sampling
Speculative sampling accelerates LLM decoding 2-2.5x by letting a draft model propose short sequences that the target model scores in parallel, then applies modified rejection sampling to keep the exact target distribution.
-
TIP: Token Importance in On-Policy Distillation
In on-policy distillation, tokens with high student entropy or low entropy plus high teacher divergence provide dense corrective signal, allowing effective training on under 20% of tokens across math and planning tasks.
-
Near-Policy: Accelerating On-Policy Distillation via Asynchronous Generation and Selective Packing
NPD accelerates on-policy distillation 8.1 times faster than baselines by using asynchronous SFT with Δ-IFD filtering, outperforming standard SFT and enabling a 1B model to achieve 68.73% SOTA score.