Image de couverture de livre

SpecAttn: Speculating Sparse Attention

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteur principal:	Shah, Harsh
Format:	Preprint
Publié:	2025
Sujets:	Computation and Language Machine Learning Systems and Control
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

SpecKV: Adaptive Speculative Decoding with Compression-Aware Gamma Selection
par: Shukla, Shikhar
Publié: (2026)

ProxyAttn: Guided Sparse Attention via Representative Heads
par: Wang, Yixuan, et autres
Publié: (2025)

ParallelSpec: Parallel Drafter for Efficient Speculative Decoding
par: Xiao, Zilin, et autres
Publié: (2024)

STS: Efficient Sparse Attention with Speculative Token Sparsity
par: Xu, Ceyu, et autres
Publié: (2026)

State Space Models as Foundation Models: A Control Theoretic Overview
par: Alonso, Carmen Amo, et autres
Publié: (2024)

SysCaps: Language Interfaces for Simulation Surrogates of Complex Systems
par: Emami, Patrick, et autres
Publié: (2024)

HiSpec: Hierarchical Speculative Decoding for LLMs
par: Kumar, Avinash, et autres
Publié: (2025)

AttnCache: Accelerating Self-Attention Inference for LLM Prefill via Attention Cache
par: Song, Dinghong, et autres
Publié: (2025)

SlimSpec: Low-Rank Draft LM-Head for Accelerated Speculative Decoding
par: Plaksin, Anton, et autres
Publié: (2026)

DistillSpec: Improving Speculative Decoding via Knowledge Distillation
par: Zhou, Yongchao, et autres
Publié: (2023)

Sparse Attention-driven Quality Prediction for Production Process Optimization in Digital Twins
par: Yin, Yanlei, et autres
Publié: (2024)

ML-SpecQD: Multi-Level Speculative Decoding with Quantized Drafts
par: Georganas, Evangelos, et autres
Publié: (2025)

SpecExit: Accelerating Large Reasoning Model via Speculative Exit
par: Yang, Rubing, et autres
Publié: (2025)

SpecDec++: Boosting Speculative Decoding via Adaptive Candidate Lengths
par: Huang, Kaixuan, et autres
Publié: (2024)

ACING: Actor-Critic for Instruction Learning in Black-Box LLMs
par: Kharrat, Salma, et autres
Publié: (2024)

ControlAgent: Automating Control System Design via Novel Integration of LLM Agents and Domain Expertise
par: Guo, Xingang, et autres
Publié: (2024)

LogicGuard: Improving Embodied LLM agents through Temporal Logic based Critics
par: Gokhale, Anand, et autres
Publié: (2025)

Fine-tuning Smaller Language Models for Question Answering over Financial Documents
par: Phogat, Karmvir Singh, et autres
Publié: (2024)

Are More LLM Calls All You Need? Towards Scaling Laws of Compound Inference Systems
par: Chen, Lingjiao, et autres
Publié: (2024)

Language Models as Efficient Reward Function Searchers for Custom-Environment Multi-Objective Reinforcement
par: Xie, Guanwen, et autres
Publié: (2024)

PreFT: Prefill-only finetuning for efficient inference
par: Lanpouthakoun, Andrew, et autres
Publié: (2026)

Most Likely Sequence Generation for $n$-Grams, Transformers, HMMs, and Markov Chains, by Using Rollout Algorithms
par: Li, Yuchao, et autres
Publié: (2024)

Fake-Mamba: Real-Time Speech Deepfake Detection Using Bidirectional Mamba as Self-Attention's Alternative
par: Xuan, Xi, et autres
Publié: (2025)

Context, Reasoning, and Hierarchy: A Cost-Performance Study of Compound LLM Agent Design in an Adversarial POMDP
par: Bogdanov, Igor, et autres
Publié: (2026)

FORGE: Self-Evolving Agent Memory With No Weight Updates via Population Broadcast
par: Bogdanov, Igor, et autres
Publié: (2026)

LongSpec: Long-Context Lossless Speculative Decoding with Efficient Drafting and Verification
par: Yang, Penghui, et autres
Publié: (2025)

SpecBound: Adaptive Bounded Self-Speculation with Layer-wise Confidence Calibration
par: Wen, Zhuofan, et autres
Publié: (2026)

DynaSpec: Context-aware Dynamic Speculative Sampling for Large-Vocabulary Language Models
par: Zhang, Jinbin, et autres
Publié: (2025)

SpecForge: A Flexible and Efficient Open-Source Training Framework for Speculative Decoding
par: Li, Shenggui, et autres
Publié: (2026)

BASS: Batched Attention-optimized Speculative Sampling
par: Qian, Haifeng, et autres
Publié: (2024)

Spatial Language Likelihood Grounding Network for Bayesian Fusion of Human-Robot Observations
par: Sitdhipol, Supawich, et autres
Publié: (2025)

Multi-Bin Batching for Increasing LLM Inference Throughput
par: Guldogan, Ozgur, et autres
Publié: (2024)

On the Relation of State Space Models and Hidden Markov Models
par: Ghojogh, Aydin, et autres
Publié: (2026)

A Survey on Large Language Model-empowered Autonomous Driving
par: Zhu, Yuxuan, et autres
Publié: (2024)

SpecTr: Fast Speculative Decoding via Optimal Transport
par: Sun, Ziteng, et autres
Publié: (2023)

FR-Spec: Accelerating Large-Vocabulary Language Models via Frequency-Ranked Speculative Sampling
par: Zhao, Weilin, et autres
Publié: (2025)

AttnLRP: Attention-Aware Layer-Wise Relevance Propagation for Transformers
par: Achtibat, Reduan, et autres
Publié: (2024)

$\partial$CBDs: Differentiable Causal Block Diagrams
par: Beckers, Thomas, et autres
Publié: (2026)

Mixture of Attentions For Speculative Decoding
par: Zimmer, Matthieu, et autres
Publié: (2024)

Temporal Logic Imitation: Learning Plan-Satisficing Motion Policies from Demonstrations
par: Wang, Yanwei, et autres
Publié: (2022)