Image de couverture de livre

Fast and Slow Generating: An Empirical Study on Large and Small Language Models Collaborative Decoding

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Zhang, Kaiyan, Wang, Jianyu, Ding, Ning, Qi, Biqing, Hua, Ermo, Lv, Xingtai, Zhou, Bowen
Format:	Preprint
Publié:	2024
Sujets:	Computation and Language
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

CoGenesis: A Framework Collaborating Large and Small Language Models for Secure Context-Aware Instruction Following
par: Zhang, Kaiyan, et autres
Publié: (2024)

Intuitive Fine-Tuning: Towards Simplifying Alignment into a Single Process
par: Hua, Ermo, et autres
Publié: (2024)

Scalable Efficient Training of Large Language Models with Low-dimensional Projected Attention
par: Lv, Xingtai, et autres
Publié: (2024)

Fourier Position Embedding: Enhancing Attention's Periodic Extension for Length Generalization
par: Hua, Ermo, et autres
Publié: (2024)

Large Language Models as Biomedical Hypothesis Generators: A Comprehensive Evaluation
par: Qi, Biqing, et autres
Publié: (2024)

Retrieval-Augmented Visual Question Answering via Built-in Autoregressive Search Engines
par: Long, Xinwei, et autres
Publié: (2025)

Online DPO: Online Direct Preference Optimization with Fast-Slow Chasing
par: Qi, Biqing, et autres
Publié: (2024)

How to Synthesize Text Data without Model Collapse?
par: Zhu, Xuekai, et autres
Publié: (2024)

Towards Building Specialized Generalist AI with System 1 and System 2 Fusion
par: Zhang, Kaiyan, et autres
Publié: (2024)

UltraMedical: Building Specialized Generalists in Biomedicine
par: Zhang, Kaiyan, et autres
Publié: (2024)

Technologies on Effectiveness and Efficiency: A Survey of State Spaces Models
par: Lv, Xingtai, et autres
Publié: (2025)

PaD: Program-aided Distillation Can Teach Small Models Reasoning Better than Chain-of-thought Fine-tuning
par: Zhu, Xuekai, et autres
Publié: (2023)

Towards a Unified View of Large Language Model Post-Training
par: Lv, Xingtai, et autres
Publié: (2025)

Accelerating Diffusion Large Language Models with SlowFast Sampling: The Three Golden Principles
par: Wei, Qingyan, et autres
Publié: (2025)

Self Speculative Decoding for Diffusion Large Language Models
par: Gao, Yifeng, et autres
Publié: (2025)

MedXpertQA: Benchmarking Expert-Level Medical Reasoning and Understanding
par: Zuo, Yuxin, et autres
Publié: (2025)

TTRL: Test-Time Reinforcement Learning
par: Zuo, Yuxin, et autres
Publié: (2025)

Mastering Text, Code and Math Simultaneously via Fusing Highly Specialized Language Models
par: Ding, Ning, et autres
Publié: (2024)

Generative Multi-Modal Knowledge Retrieval with Large Language Models
par: Long, Xinwei, et autres
Publié: (2024)

GenPRM: Scaling Test-Time Compute of Process Reward Models via Generative Reasoning
par: Zhao, Jian, et autres
Publié: (2025)

Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling
par: Liu, Runze, et autres
Publié: (2025)

Fast Large Language Model Collaborative Decoding via Speculation
par: Fu, Jiale, et autres
Publié: (2025)

On Large Language Models' Hallucination with Regard to Known Facts
par: Jiang, Che, et autres
Publié: (2024)

Leveraging Adaptive Group Negotiation for Heterogeneous Multi-Robot Collaboration with Large Language Models
par: Song, Siqi, et autres
Publié: (2025)

DePass: Unified Feature Attributing by Simple Decomposed Forward Pass
par: Hong, Xiangyu, et autres
Publié: (2025)

MARS$^2$: Scaling Multi-Agent Tree Search via Reinforcement Learning for Code Generation
par: Li, Pengfei, et autres
Publié: (2026)

Prompting Large Language Models for Counterfactual Generation: An Empirical Study
par: Li, Yongqi, et autres
Publié: (2023)

Automating Exploratory Proteomics Research via Language Models
par: Ding, Ning, et autres
Publié: (2024)

Automating Exploratory Multiomics Research via Language Models
par: Qu, Shang, et autres
Publié: (2025)

Fast-Slow-Thinking: Complex Task Solving with Large Language Models
par: Sun, Yiliu, et autres
Publié: (2025)

A Survey of Reinforcement Learning for Large Reasoning Models
par: Zhang, Kaiyan, et autres
Publié: (2025)

Fast-Slow Thinking RM: Efficient Integration of Scalar and Generative Reward Models
par: Wu, Jiayun, et autres
Publié: (2026)

DynaThink: Fast or Slow? A Dynamic Decision-Making Framework for Large Language Models
par: Pan, Jiabao, et autres
Publié: (2024)

Learning Evaluation Models from Large Language Models for Sequence Generation
par: Wang, Chenglong, et autres
Publié: (2023)

Interactive Continual Learning: Fast and Slow Thinking
par: Qi, Biqing, et autres
Publié: (2024)

Recurrent Drafter for Fast Speculative Decoding in Large Language Models
par: Cheng, Yunfei, et autres
Publié: (2024)

FlowRL: Matching Reward Distributions for LLM Reasoning
par: Zhu, Xuekai, et autres
Publié: (2025)

Adaptive Draft-Verification for Efficient Large Language Model Decoding
par: Liu, Xukun, et autres
Publié: (2024)

DARE: Diffusion Large Language Models Alignment and Reinforcement Executor
par: Yang, Jingyi, et autres
Publié: (2026)

Large Language Models as Universal Predictors? An Empirical Study on Small Tabular Datasets
par: Pavlidis, Nikolaos, et autres
Publié: (2025)