Teaching Diffusion to Speculate Left-to-Right
cs.CL, cs.LG
Submitted: 2026-06-10
Updated: 2026-11-04
Code: https://github.com/sbintuitions/TeachingDiffusionToSpeculateLeftToRight
Terminology
Sources
- SARATHI: Efficient LLM Inference by Piggybacking Decodes with Chunked Prefills
- Program Synthesis with Large Language Models
- Accelerating Large Language Model Decoding with Speculative Sampling
- Evaluating Large Language Models Trained on Code
- Training Verifiers to Solve Math Word Problems
- DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
- Efficient-DLM: From Autoregressive to Diffusion Language Models, and Beyond in Speed
- The Llama 3 Herd of Models
- Distilling the Knowledge in a Neural Network
- LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code
- EAGLE-3: Scaling up Inference Acceleration of Large Language Models via Training-Time Test
- TiDAR: Think in Diffusion, Talk in Autoregression
- Decoupled Weight Decay Regularization
- Large Language Diffusion Models
- OpenAI o1 System Card
- Accelerating Speculative Decoding with Block Diffusion Draft Trees
- Code Llama: Open Foundation Models for Code
- SpecDiff-2: Scaling Diffusion Drafter Alignment For Faster Speculative Decoding
- DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter
- D-PACE: Dynamic Position-Aware Cross-Entropy for Parallel Speculative Drafting
Related papers
- ALARM: Audio-Language Alignment for Reasoning Models
- ThinkSum: Probabilistic reasoning over sets using large language models
- Coherence boosting: When your pretrained language model is not paying enough attention
- From Facts to Insights: A Persona-Driven Dual Memory Framework and Dataset for Role-Playing Agents
- Improving General Role-Playing Agents via Psychology-Grounded Reasoning and Role-Aware Policy Optimization
- The Art of Asking: Multilingual Prompt Optimization for Synthetic Data