VIA-SD: Verification via Intra-Model Routing for Speculative Decoding
cs.CL, cs.AI
Submitted: 2026-06-10
Updated: 2026-06-10
Project page: https://zju-xyc.github.io/VIA-SD-Project-Page
Terminology
Sources
- Program Synthesis with Large Language Models
- Qwen Technical Report
- Accelerating Large Language Model Decoding with Speculative Sampling
- Training Verifiers to Solve Math Word Problems
- Distilling the Knowledge in a Neural Network
- Fast Transformer Decoding: One Write-Head is All You Need
- Gemma 2: Improving Open Language Models at a Practical Size
- Llama 2: Open Foundation and Fine-Tuned Chat Models
- Dataset Distillation
- Reinforcement Learning with Reference-Based Rewards for Language Model Reasoning and Alignment
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