Multi-Future Drafting: Mixture Block Drafters for Tree-Verified Speculative Decoding
cs.AI, cs.LG
Submitted: 2026-11-09
Updated: 2026-11-09
Project page: https://hhhhhhy5.github.io/multi-future-drafting
Terminology
Sources
- Faster Language Models with Better Multi-Token Prediction Using Tensor Decomposition
- Accelerating Large Language Model Decoding with Speculative Sampling
- DSpark: Confidence-Scheduled Speculative Decoding with Semi-Autoregressive Generation
- TreeWY: Speculative Verification for Gated DeltaNet Hybrids
- JetSpec: Breaking the Scaling Ceiling of Speculative Decoding with Parallel Tree Drafting
- DBLAST: Dependent Block Drafting for Stochastic Speculative Decoding
- DARTree: Speculative Diffusion Decoding with Autoregressive Draft Trees
- UBTree: Parallel Tree Drafting via Unigram and Bigram Models for Speculative Decoding
- Trees from Marginals: Autoregressive drafting with factorized priors
- FlashMap: Flow Map Speculative Decoding
- Twig: Parallel and Memory-Efficient Tree Speculative Decoding for Hybrid-Attention LLMs
- TreeSpark: Learning to Draft the Trees You Verify for Speculative Decoding
Related papers
- Multi-Objective Structured Pruning of LLMs for Latency and Model Size Optimization
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Embeddings for Preferences, Not Semantics
- Can We Trust Item Response Theory for AI Evaluation?
- Diagnosing Task Insensitivity in Language Agents