Give the Drafter a Second Chance to Guess: Parallel Reconsideration for Speculative Decoding
cs.LG
Submitted: 2026-11-03
Updated: 2026-11-03
Terminology
Sources
- PARD: Accelerating LLM Inference with Low-Cost PARallel Draft Model Adaptation
- Hydra: Sequentially-Dependent Draft Heads for Medusa Decoding
- Program Synthesis with Large Language Models
- Evaluating Large Language Models Trained on Code
- DSpark: Confidence-Scheduled Speculative Decoding with Semi-Autoregressive Generation
- Recurrent Drafter for Fast Speculative Decoding in Large Language Models
- Training Verifiers to Solve Math Word Problems
- Attention Drift: What Autoregressive Speculative Decoding Models Learn
- SpecForge: A Flexible and Efficient Open-Source Training Framework for Speculative Decoding
- Let's Verify Step by Step
- Scaling Latent Reasoning via Looped Language Models
- Variational Speculative Decoding: Rethinking Draft Training from Token Likelihood to Sequence Acceptance
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis