ChainFlow: Few-Step Latent Flow Matching for Speculative Decoding
cs.AI, cs.CL
Submitted: 2026-11-05
Updated: 2026-11-05
Code: https://github.com/sahil280114/codealpaca
Terminology
Sources
- PARD: Accelerating LLM Inference with Low-Cost PARallel Draft Model Adaptation
- Hydra: Sequentially-Dependent Draft Heads for Medusa Decoding
- Accelerating Large Language Model Decoding with Speculative Sampling
- DFlash: Block Diffusion for Flash Speculative Decoding
- Evaluating Large Language Models Trained on Code
- LangFlow: Continuous Diffusion Rivals Discrete in Language Modeling
- DSpark: Confidence-Scheduled Speculative Decoding with Semi-Autoregressive Generation
- Training Verifiers to Solve Math Word Problems
- Flow Matching in Latent Space
- Enhancing Chat Language Models by Scaling High-quality Instructional Conversations
- Scaling Rectified Flow Transformers for High-Resolution Image Synthesis
- Break the Sequential Dependency of LLM Inference Using Lookahead Decoding
- JetSpec: Breaking the Scaling Ceiling of Speculative Decoding with Parallel Tree Drafting
- Domino: Decoupling Causal Modeling from Autoregressive Drafting in Speculative Decoding
- Flow Map Language Models: One-step Language Modeling via Continuous Denoising
- DiffuSpec: Unlocking Diffusion Language Models for Speculative Decoding
- EAGLE-3: Scaling up Inference Acceleration of Large Language Models via Training-Time Test
- Flow Matching Guide and Code
- DART: Diffusion-Inspired Speculative Decoding for Fast LLM Inference
- Large Language Diffusion Models
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