SpecPilot: Autonomous Algorithm Discovery and Systems Optimization for Speculative Decoding
cs.LG
Submitted: 2026-11-02
Updated: 2026-11-02
Terminology
Sources
- Accelerating Large Language Model Decoding with Speculative Sampling
- DSpark: Confidence-Scheduled Speculative Decoding with Semi-Autoregressive Generation
- Accelerating Speculative Decoding with Block Diffusion Draft Trees
- TurboSpec: Closed-loop Speculation Control System for Optimizing LLM Serving Goodput
- D-cut: Adaptive Verification Depth Pruning for Batched Speculative Decoding
- AlphaEvolve: A coding agent for scientific and algorithmic discovery
- Barbarians at the Gate: How AI is Upending Systems Research
- Concrete Problems in AI Safety
- TreeWY: Speculative Verification for Gated DeltaNet Hybrids
- Gemma 4 Technical Report
- Training Verifiers to Solve Math Word Problems
- Evaluating Large Language Models Trained on Code
- Program Synthesis with Large Language Models
- Cost-Aware Diffusion Draft Trees for Speculative Decoding
- From Chains to Trees: Parent-Conditioned Drafting for Semi-Autoregressive Speculative Decoding
- ML-SpecQD: Multi-Level Speculative Decoding with Quantized Drafts
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