Imagen de Portada

Draft on the Fly: Adaptive Self-Speculative Decoding using Cosine Similarity

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Metel, Michael R., Lu, Peng, Chen, Boxing, Rezagholizadeh, Mehdi, Kobyzev, Ivan
Formato:	Preprint
Publicado:	2024
Materias:	Computation and Language
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Batch-Max: Higher LLM Throughput using Larger Batch Sizes and KV Cache Compression
por: Metel, Michael R., et al.
Publicado: (2024)

ReGLA: Refining Gated Linear Attention
por: Lu, Peng, et al.
Publicado: (2025)

OTTAWA: Optimal TransporT Adaptive Word Aligner for Hallucination and Omission Translation Errors Detection
por: Huang, Chenyang, et al.
Publicado: (2024)

Resonance RoPE: Improving Context Length Generalization of Large Language Models
por: Wang, Suyuchen, et al.
Publicado: (2024)

LABO: Towards Learning Optimal Label Regularization via Bi-level Optimization
por: Lu, Peng, et al.
Publicado: (2023)

S2D: Sorted Speculative Decoding For More Efficient Deployment of Nested Large Language Models
por: Kavehzadeh, Parsa, et al.
Publicado: (2024)

Integral Transformer: Denoising Attention, Not Too Much Not Too Little
por: Kobyzev, Ivan, et al.
Publicado: (2025)

BOSCH: Black-Box Binary Optimization for Short-Context Attention-Head Selection in LLMs
por: Ghaddar, Abbas, et al.
Publicado: (2026)

On the importance of Data Scale in Pretraining Arabic Language Models
por: Ghaddar, Abbas, et al.
Publicado: (2024)

PEARL: Parallel Speculative Decoding with Adaptive Draft Length
por: Liu, Tianyu, et al.
Publicado: (2024)

Learning to Draft: Adaptive Speculative Decoding with Reinforcement Learning
por: Zhang, Jiebin, et al.
Publicado: (2026)

Thinking Long, but Short: Stable Sequential Test-Time Scaling for Large Reasoning Models
por: Metel, Michael R., et al.
Publicado: (2026)

OPT-Tree: Speculative Decoding with Adaptive Draft Tree Structure
por: Wang, Jikai, et al.
Publicado: (2024)

AdaEAGLE: Optimizing Speculative Decoding via Explicit Modeling of Adaptive Draft Structures
por: Zhang, Situo, et al.
Publicado: (2024)

Draft & Verify: Lossless Large Language Model Acceleration via Self-Speculative Decoding
por: Zhang, Jun, et al.
Publicado: (2023)

SWIFT: On-the-Fly Self-Speculative Decoding for LLM Inference Acceleration
por: Xia, Heming, et al.
Publicado: (2024)

Do Robot Snakes Dream like Electric Sheep? Investigating the Effects of Architectural Inductive Biases on Hallucination
por: Huang, Jerry, et al.
Publicado: (2024)

Cost-Aware Diffusion Draft Trees for Speculative Decoding
por: Zhang, Shuai, et al.
Publicado: (2026)

Accelerating Speculative Decoding with Block Diffusion Draft Trees
por: Ringel, Liran, et al.
Publicado: (2026)

OmniDraft: A Cross-vocabulary, Online Adaptive Drafter for On-device Speculative Decoding
por: Ramakrishnan, Ramchalam Kinattinkara, et al.
Publicado: (2025)

TABED: Test-Time Adaptive Ensemble Drafting for Robust Speculative Decoding in LVLMs
por: Lee, Minjae, et al.
Publicado: (2026)

Bridging Draft Policy Misalignment: Group Tree Optimization for Speculative Decoding
por: Hu, Shijing, et al.
Publicado: (2025)

SpecHub: Provable Acceleration to Multi-Draft Speculative Decoding
por: Sun, Ryan, et al.
Publicado: (2024)

CHARP: Conversation History AwaReness Probing for Knowledge-grounded Dialogue Systems
por: Ghaddar, Abbas, et al.
Publicado: (2024)

Sorted LLaMA: Unlocking the Potential of Intermediate Layers of Large Language Models for Dynamic Inference
por: Kavehzadeh, Parsa, et al.
Publicado: (2023)

SpecBlock: Block-Iterative Speculative Decoding with Dynamic Tree Drafting
por: Shi, Weijie, et al.
Publicado: (2026)

Make Every Draft Count: Hidden State based Speculative Decoding
por: Chen, Yuetao, et al.
Publicado: (2026)

Draft Model Knows When to Stop: Self-Verification Speculative Decoding for Long-Form Generation
por: Zhang, Ziyin, et al.
Publicado: (2024)

DuoDecoding: Hardware-aware Heterogeneous Speculative Decoding with Dynamic Multi-Sequence Drafting
por: Lv, Kai, et al.
Publicado: (2025)

DREAM: Drafting with Refined Target Features and Entropy-Adaptive Cross-Attention Fusion for Multimodal Speculative Decoding
por: Hu, Yunhai, et al.
Publicado: (2025)

Ouroboros: Generating Longer Drafts Phrase by Phrase for Faster Speculative Decoding
por: Zhao, Weilin, et al.
Publicado: (2024)

Domino: Decoupling Causal Modeling from Autoregressive Drafting in Speculative Decoding
por: Huang, Jianuo, et al.
Publicado: (2026)

DFlare: Scaling Up Draft Capacity for Block Diffusion Speculative Decoding
por: Zhang, Jiebin, et al.
Publicado: (2026)

TETRIS: Optimal Draft Token Selection for Batch Speculative Decoding
por: Wu, Zhaoxuan, et al.
Publicado: (2025)

Draft-OPD: On-Policy Distillation for Speculative Draft Models
por: Lei, Haodi, et al.
Publicado: (2026)

SpecTr-GBV: Multi-Draft Block Verification Accelerating Speculative Decoding
por: Lin, Yijun, et al.
Publicado: (2026)

KOALA: Enhancing Speculative Decoding for LLM via Multi-Layer Draft Heads with Adversarial Learning
por: Zhang, Kaiqi, et al.
Publicado: (2024)

POSS: Position Specialist Generates Better Draft for Speculative Decoding
por: Huang, Langlin, et al.
Publicado: (2025)

MineDraft: A Framework for Batch Parallel Speculative Decoding
por: Tang, Zhenwei, et al.
Publicado: (2026)

FlexDraft: Flexible Speculative Decoding via Attention Tuning and Bonus-Guided Calibration
por: Zhang, Yaojie, et al.
Publicado: (2026)