BASTION is a budget-aware speculative decoding framework with adaptive tree-structured block diffusion drafting that reports up to 6.61x speedup and 39% improvement over block-diffusion baselines.
Judge decoding: Faster speculative sampling requires going beyond model alignment
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
representative citing papers
WISV uses a channel-aware semantic acceptance policy on hidden representations to boost accepted sequence length by up to 60.8% and cut interaction rounds by 37.3% in distributed speculative decoding, with under 1% accuracy loss.
CoSpec uses RL to arbitrate between draft and target tokens in speculative decoding, maintaining speedups while exceeding target-only performance.
FLy is a training-free method that speeds up LLM generation by accepting semantically correct but non-exact draft tokens via an entropy gate and deferred verification window.
Speculative Coupled Decoding stabilizes draft sampling in Speculative Jacobi Decoding via an information-theoretic coupling step, delivering up to 4.2x image and 13.6x video speedups with no quality loss or training.
LogitSpec accelerates retrieval-based speculative decoding by speculating the next-next token from the last logit and retrieving relevant references for both next and next-next tokens, reporting up to 2.61x speedup and 3.28 mean accepted tokens.
Speculative decoding plus top-K compressed transmission with two reconstruction strategies cuts federated LLM communication while bounding reconstruction, aggregation, and acceptance-rate bias.
citing papers explorer
-
Bastion: Budget-Aware Speculative Decoding with Tree-structured Block Diffusion Drafting
BASTION is a budget-aware speculative decoding framework with adaptive tree-structured block diffusion drafting that reports up to 6.61x speedup and 39% improvement over block-diffusion baselines.
-
WISV: Wireless-Informed Semantic Verification for Distributed Speculative Decoding in Device-Edge LLM Inference
WISV uses a channel-aware semantic acceptance policy on hidden representations to boost accepted sequence length by up to 60.8% and cut interaction rounds by 37.3% in distributed speculative decoding, with under 1% accuracy loss.
-
Beyond the Target: From Imitation to Collaboration in Speculative Decoding
CoSpec uses RL to arbitrate between draft and target tokens in speculative decoding, maintaining speedups while exceeding target-only performance.
-
Training-Free Loosely Speculative Decoding: Accepting Semantically Correct Drafts Beyond Exact Match
FLy is a training-free method that speeds up LLM generation by accepting semantically correct but non-exact draft tokens via an entropy gate and deferred verification window.
-
Speculative Coupled Decoding for Training-Free Lossless Acceleration of Autoregressive Visual Generation
Speculative Coupled Decoding stabilizes draft sampling in Speculative Jacobi Decoding via an information-theoretic coupling step, delivering up to 4.2x image and 13.6x video speedups with no quality loss or training.
-
LogitSpec: Accelerating Retrieval-based Speculative Decoding via Next Next Token Speculation
LogitSpec accelerates retrieval-based speculative decoding by speculating the next-next token from the last logit and retrieving relevant references for both next and next-next tokens, reporting up to 2.61x speedup and 3.28 mean accepted tokens.
-
SpecFed: Accelerating Federated LLM Inference with Speculative Decoding and Compressed Transmission
Speculative decoding plus top-K compressed transmission with two reconstruction strategies cuts federated LLM communication while bounding reconstruction, aggregation, and acceptance-rate bias.