Ripple-Pivot Search: Active Parallel Decoding for Diffusion Large Language Models
Ranking
Overall
77
Content
95
Popularity
34
Observed public metrics from 1 member.
Merged summary
TL;DR - Ripple-Pivot Search is a training-free parallel decoding method for diffusion LLMs that proactively commits selected mid-entropy tokens to reduce uncertainty elsewhere. It accelerates inference substantially while preserving generation quality.
- Uses lookahead evaluation to select pivot positions and token assignments with the greatest downstream benefit.
- Achieves 4–10× wall-clock speedups across three dLLMs and four reasoning/code benchmarks.
- Improves accuracy over a prior lookahead baseline by up to 5.49%.
- Combined with KV caching, reaches up to an 18× speedup over standard decoding.
Sources (1)
Ripple-Pivot Search: Active Parallel Decoding for Diffusion Large Language Models
Public signals
Semantic Scholar citations 0 · Semantic Scholar influential citations 0
TL;DR - Ripple-Pivot Search is a training-free parallel decoding method for diffusion LLMs that proactively commits selected mid-entropy tokens to reduce uncertainty elsewhere. It accelerates inference substantially while preserving generation quality.
- Uses lookahead evaluation to select pivot positions and token assignments with the greatest downstream benefit.
- Achieves 4–10× wall-clock speedups across three dLLMs and four reasoning/code benchmarks.
- Improves accuracy over a prior lookahead baseline by up to 5.49%.
- Combined with KV caching, reaches up to an 18× speedup over standard decoding.