Image de couverture de livre

Sirius: Contextual Sparsity with Correction for Efficient LLMs

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Zhou, Yang, Chen, Zhuoming, Xu, Zhaozhuo, Lin, Victoria, Chen, Beidi
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

GSM-Infinite: How Do Your LLMs Behave over Infinitely Increasing Context Length and Reasoning Complexity?
par: Zhou, Yang, et autres
Publié: (2025)

TriForce: Lossless Acceleration of Long Sequence Generation with Hierarchical Speculative Decoding
par: Sun, Hanshi, et autres
Publié: (2024)

Kinetics: Rethinking Test-Time Scaling Laws
par: Sadhukhan, Ranajoy, et autres
Publié: (2025)

SpecExec: Massively Parallel Speculative Decoding for Interactive LLM Inference on Consumer Devices
par: Svirschevski, Ruslan, et autres
Publié: (2024)

Sequoia: Scalable, Robust, and Hardware-aware Speculative Decoding
par: Chen, Zhuoming, et autres
Publié: (2024)

Learn To be Efficient: Build Structured Sparsity in Large Language Models
par: Zheng, Haizhong, et autres
Publié: (2024)

MagicPIG: LSH Sampling for Efficient LLM Generation
par: Chen, Zhuoming, et autres
Publié: (2024)

Do LLMs Know to Respect Copyright Notice?
par: Xu, Jialiang, et autres
Publié: (2024)

KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache
par: Liu, Zirui, et autres
Publié: (2024)

Sensitivity Meets Sparsity: The Impact of Extremely Sparse Parameter Patterns on Theory-of-Mind of Large Language Models
par: Wu, Yuheng, et autres
Publié: (2025)

Prompt-prompted Adaptive Structured Pruning for Efficient LLM Generation
par: Dong, Harry, et autres
Publié: (2024)

MagicDec: Breaking the Latency-Throughput Tradeoff for Long Context Generation with Speculative Decoding
par: Sadhukhan, Ranajoy, et autres
Publié: (2024)

Nearest Neighbor Speculative Decoding for LLM Generation and Attribution
par: Li, Minghan, et autres
Publié: (2024)

WWW.Serve: Interconnecting Global LLM Services through Decentralization
par: Wang, Huanyu, et autres
Publié: (2026)

Efficient Streaming Language Models with Attention Sinks
par: Xiao, Guangxuan, et autres
Publié: (2023)

Detecting Contextual Hallucinations in LLMs with Frequency-Aware Attention
par: Qi, Siya, et autres
Publié: (2026)

Speculative Prefill: Turbocharging TTFT with Lightweight and Training-Free Token Importance Estimation
par: Liu, Jingyu, et autres
Publié: (2025)

Towards Extreme Pruning of LLMs with Plug-and-Play Mixed Sparsity
par: Xu, Chi, et autres
Publié: (2025)

Pangu Pro MoE: Mixture of Grouped Experts for Efficient Sparsity
par: Tang, Yehui, et autres
Publié: (2025)

CATS: Contextually-Aware Thresholding for Sparsity in Large Language Models
par: Lee, Donghyun, et autres
Publié: (2024)

Self-Correction Makes LLMs Better Parsers
par: Zhang, Ziyan, et autres
Publié: (2025)

FSA: An Alternative Efficient Implementation of Native Sparse Attention Kernel
par: Yan, Ran, et autres
Publié: (2025)

Supervised Optimism Correction: Be Confident When LLMs Are Sure
par: Zhang, Junjie, et autres
Publié: (2025)

AIM: Adaptive Inference of Multi-Modal LLMs via Token Merging and Pruning
par: Zhong, Yiwu, et autres
Publié: (2024)

The Diminishing Returns of Early-Exit Decoding in Modern LLMs
par: Wei, Rui, et autres
Publié: (2026)

SFR-RAG: Towards Contextually Faithful LLMs
par: Nguyen, Xuan-Phi, et autres
Publié: (2024)

When Does Sparsity Mitigate the Curse of Depth in LLMs
par: Muhtar, Dilxat, et autres
Publié: (2026)

Enhancing Cross-Tokenizer Knowledge Distillation with Contextual Dynamical Mapping
par: Chen, Yijie, et autres
Publié: (2025)

Instruction Tuning and CoT Prompting for Contextual Medical QA with LLMs
par: Le, Chenqian, et autres
Publié: (2025)

Confidence v.s. Critique: A Decomposition of Self-Correction Capability for LLMs
par: Yang, Zhe, et autres
Publié: (2024)

Long Exposure: Accelerating Parameter-Efficient Fine-Tuning for LLMs under Shadowy Sparsity
par: Wang, Tuowei, et autres
Publié: (2025)

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

LoCoCo: Dropping In Convolutions for Long Context Compression
par: Cai, Ruisi, et autres
Publié: (2024)

SPP: Sparsity-Preserved Parameter-Efficient Fine-Tuning for Large Language Models
par: Lu, Xudong, et autres
Publié: (2024)

Megalodon: Efficient LLM Pretraining and Inference with Unlimited Context Length
par: Ma, Xuezhe, et autres
Publié: (2024)

Token-wise Influential Training Data Retrieval for Large Language Models
par: Lin, Huawei, et autres
Publié: (2024)

Speech LLMs are Contextual Reasoning Transcribers
par: Deng, Keqi, et autres
Publié: (2026)

Can LLMs Correct Themselves? A Benchmark of Self-Correction in LLMs
par: Tie, Guiyao, et autres
Publié: (2025)

ShadowLLM: Predictor-based Contextual Sparsity for Large Language Models
par: Akhauri, Yash, et autres
Publié: (2024)

DEL-ToM: Inference-Time Scaling for Theory-of-Mind Reasoning via Dynamic Epistemic Logic
par: Wu, Yuheng, et autres
Publié: (2025)