Imagen de Portada

SpecReason: Fast and Accurate Inference-Time Compute via Speculative Reasoning

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Pan, Rui, Dai, Yinwei, Zhang, Zhihao, Oliaro, Gabriele, Jia, Zhihao, Netravali, Ravi
Formato:	Preprint
Publicado:	2025
Materias:	Machine Learning Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

SuffixDecoding: Extreme Speculative Decoding for Emerging AI Applications
por: Oliaro, Gabriele, et al.
Publicado: (2024)

Fail Fast, Win Big: Rethinking the Drafting Strategy in Speculative Decoding via Diffusion LLMs
por: Pan, Rui, et al.
Publicado: (2025)

Less Is More: Fast and Accurate Reasoning with Cross-Head Unified Sparse Attention
por: Yang, Lijie, et al.
Publicado: (2025)

Quantized Side Tuning: Fast and Memory-Efficient Tuning of Quantized Large Language Models
por: Zhang, Zhengxin, et al.
Publicado: (2024)

TidalDecode: Fast and Accurate LLM Decoding with Position Persistent Sparse Attention
por: Yang, Lijie, et al.
Publicado: (2024)

FastKernels: Benchmarking GPU Kernel Generation in Production
por: Oliaro, Gabriele, et al.
Publicado: (2026)

SpecExit: Accelerating Large Reasoning Model via Speculative Exit
por: Yang, Rubing, et al.
Publicado: (2025)

Towards Efficient Generative Large Language Model Serving: A Survey from Algorithms to Systems
por: Miao, Xupeng, et al.
Publicado: (2023)

SpecMoE: A Fast and Efficient Mixture-of-Experts Inference via Self-Assisted Speculative Decoding
por: Bang, Jehyeon, et al.
Publicado: (2026)

BanditSpec: Adaptive Speculative Decoding via Bandit Algorithms
por: Hou, Yunlong, et al.
Publicado: (2025)

Slipstream: Trajectory-Grounded Compaction Validation for Long-Horizon Agents
por: Chen, Zhuofu, et al.
Publicado: (2026)

AdaServe: Accelerating Multi-SLO LLM Serving with SLO-Customized Speculative Decoding
por: Li, Zikun, et al.
Publicado: (2025)

CAS-Spec: Cascade Adaptive Self-Speculative Decoding for On-the-Fly Lossless Inference Acceleration of LLMs
por: Ning, Zhiyuan, et al.
Publicado: (2025)

SpecInfer: Accelerating Generative Large Language Model Serving with Tree-based Speculative Inference and Verification
por: Miao, Xupeng, et al.
Publicado: (2023)

Geometry Guided Self-Consistency for Physical AI
por: Dai, Yinwei, et al.
Publicado: (2026)

Accelerating Large-Scale Reasoning Model Inference with Sparse Self-Speculative Decoding
por: Zhao, Yilong, et al.
Publicado: (2025)

Apparate: Rethinking Early Exits to Tame Latency-Throughput Tensions in ML Serving
por: Dai, Yinwei, et al.
Publicado: (2023)

DistillSpec: Improving Speculative Decoding via Knowledge Distillation
por: Zhou, Yongchao, et al.
Publicado: (2023)

SpecMD: A Comprehensive Study On Speculative Expert Prefetching
por: Hoang, Duc, et al.
Publicado: (2026)

FR-Spec: Accelerating Large-Vocabulary Language Models via Frequency-Ranked Speculative Sampling
por: Zhao, Weilin, et al.
Publicado: (2025)

Inference-Time Computations for LLM Reasoning and Planning: A Benchmark and Insights
por: Parashar, Shubham, et al.
Publicado: (2025)

A Survey of Test-Time Compute: From Intuitive Inference to Deliberate Reasoning
por: Ji, Yixin, et al.
Publicado: (2025)

Fractional Reasoning via Latent Steering Vectors Improves Inference Time Compute
por: Liu, Sheng, et al.
Publicado: (2025)

HiSpec: Hierarchical Speculative Decoding for LLMs
por: Kumar, Avinash, et al.
Publicado: (2025)

Skim: Speculative Execution for Fast and Efficient Web Agents
por: Wong, Mike, et al.
Publicado: (2026)

SpecDec++: Boosting Speculative Decoding via Adaptive Candidate Lengths
por: Huang, Kaixuan, et al.
Publicado: (2024)

KnapSpec: Self-Speculative Decoding via Adaptive Layer Selection as a Knapsack Problem
por: Cha, Seongjin, et al.
Publicado: (2026)

Accurate and Scalable Graph Neural Networks via Message Invariance
por: Shi, Zhihao, et al.
Publicado: (2025)

QuantSpec: Self-Speculative Decoding with Hierarchical Quantized KV Cache
por: Tiwari, Rishabh, et al.
Publicado: (2025)

FastVLM: Self-Speculative Decoding for Fast Vision-Language Model Inference
por: Bajpai, Divya Jyoti, et al.
Publicado: (2025)

TS-Reasoner: Domain-Oriented Time Series Inference Agents for Reasoning and Automated Analysis
por: Ye, Wen, et al.
Publicado: (2024)

Arbitrage: Efficient Reasoning via Advantage-Aware Speculation
por: Maheswaran, Monishwaran, et al.
Publicado: (2025)

Spec-VLA: Speculative Decoding for Vision-Language-Action Models with Relaxed Acceptance
por: Wang, Songsheng, et al.
Publicado: (2025)

Clover-2: Accurate Inference for Regressive Lightweight Speculative Decoding
por: Xiao, Bin, et al.
Publicado: (2024)

SpecForge: A Flexible and Efficient Open-Source Training Framework for Speculative Decoding
por: Li, Shenggui, et al.
Publicado: (2026)

Legilimens: Performant Video Analytics on the System-on-Chip Edge
por: Ramanujam, Murali, et al.
Publicado: (2025)

Improving LLM Reasoning through Scaling Inference Computation with Collaborative Verification
por: Liang, Zhenwen, et al.
Publicado: (2024)

SpecMemo: Speculative Decoding is in Your Pocket
por: Yildirim, Selin, et al.
Publicado: (2025)

Experience-Guided Adaptation of Inference-Time Reasoning Strategies
por: Stein, Adam, et al.
Publicado: (2025)

LongSpec: Long-Context Lossless Speculative Decoding with Efficient Drafting and Verification
por: Yang, Penghui, et al.
Publicado: (2025)