Copertina

SQ-format: A Unified Sparse-Quantized Hardware-friendly Data Format for LLMs

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Huang, Ruixuan, Zeng, Hao, Huang, Hantao, Shi, Jinyuan, Yu, Minghui, Yen, Ian En-Hsu, Wang, Shuai
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Computation and Language
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

APTQ: Attention-aware Post-Training Mixed-Precision Quantization for Large Language Models
di: Guan, Ziyi, et al.
Pubblicazione: (2024)

MagicDec: Breaking the Latency-Throughput Tradeoff for Long Context Generation with Speculative Decoding
di: Sadhukhan, Ranajoy, et al.
Pubblicazione: (2024)

Endor: Hardware-Friendly Sparse Format for Offloaded LLM Inference
di: Joo, Donghyeon, et al.
Pubblicazione: (2024)

Enhancing Function-Calling Capabilities in LLMs: Strategies for Prompt Formats, Data Integration, and Multilingual Translation
di: Chen, Yi-Chang, et al.
Pubblicazione: (2024)

Persona-SQ: A Personalized Suggested Question Generation Framework For Real-world Documents
di: Lin, Zihao, et al.
Pubblicazione: (2024)

DeSQ: Decomposition-based SPARQL Query Generation
di: Diallo, Papa Abdou Karim Karou, et al.
Pubblicazione: (2026)

MobileQuant: Mobile-friendly Quantization for On-device Language Models
di: Tan, Fuwen, et al.
Pubblicazione: (2024)

Atomic-SNLI: Fine-Grained Natural Language Inference through Atomic Fact Decomposition
di: Huang, Minghui
Pubblicazione: (2026)

DecMetrics: Structured Claim Decomposition Scoring for Factually Consistent LLM Outputs
di: Huang, Minghui
Pubblicazione: (2025)

GuidedBench: Measuring and Mitigating the Evaluation Discrepancies of In-the-wild LLM Jailbreak Methods
di: Huang, Ruixuan, et al.
Pubblicazione: (2025)

LLMs Are Biased Towards Output Formats! Systematically Evaluating and Mitigating Output Format Bias of LLMs
di: Long, Do Xuan, et al.
Pubblicazione: (2024)

The Sparse Frontier: Sparse Attention Trade-offs in Transformer LLMs
di: Nawrot, Piotr, et al.
Pubblicazione: (2025)

Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention
di: Yuan, Jingyang, et al.
Pubblicazione: (2025)

SynCPKL: Harnessing LLMs to Generate Synthetic Data for Commonsense Persona Knowledge Linking
di: Lin, Kuan-Yen
Pubblicazione: (2024)

For-Value: Efficient Forward-Only Data Valuation for finetuning LLMs and VLMs
di: Deng, Wenlong, et al.
Pubblicazione: (2025)

Training Data Efficiency in Multimodal Process Reward Models
di: Li, Jinyuan, et al.
Pubblicazione: (2026)

SASFT: Sparse Autoencoder-guided Supervised Finetuning to Mitigate Unexpected Code-Switching in LLMs
di: Deng, Boyi, et al.
Pubblicazione: (2025)

Sparse Brains are Also Adaptive Brains: Cognitive-Load-Aware Dynamic Activation for LLMs
di: Yang, Yiheng, et al.
Pubblicazione: (2025)

On LLMs-Driven Synthetic Data Generation, Curation, and Evaluation: A Survey
di: Long, Lin, et al.
Pubblicazione: (2024)

Fundamental Limitations on Subquadratic Alternatives to Transformers
di: Alman, Josh, et al.
Pubblicazione: (2024)

AGoQ: Activation and Gradient Quantization for Memory-Efficient Distributed Training of LLMs
di: Lin, Wenxiang, et al.
Pubblicazione: (2026)

Low-Bit Quantization Favors Undertrained LLMs: Scaling Laws for Quantized LLMs with 100T Training Tokens
di: Ouyang, Xu, et al.
Pubblicazione: (2024)

Format-Adapter: Improving Reasoning Capability of LLMs by Adapting Suitable Format
di: Wang, Dingzirui, et al.
Pubblicazione: (2025)

From Oracle to Noisy Context: Mitigating Contextual Exposure Bias in Speech-LLMs
di: Guo, Xiaoyong, et al.
Pubblicazione: (2026)

Are they lovers or friends? Evaluating LLMs' Social Reasoning in English and Korean Dialogues
di: Kim, Eunsu, et al.
Pubblicazione: (2025)

SALS: Sparse Attention in Latent Space for KV cache Compression
di: Mu, Junlin, et al.
Pubblicazione: (2025)

Evaluating LLMs for Hardware Design and Test
di: Blocklove, Jason, et al.
Pubblicazione: (2024)

SqueezeLLM: Dense-and-Sparse Quantization
di: Kim, Sehoon, et al.
Pubblicazione: (2023)

Uncovering Safety Risks of Large Language Models through Concept Activation Vector
di: Xu, Zhihao, et al.
Pubblicazione: (2024)

Attention Consistency for LLMs Explanation
di: Lan, Tian, et al.
Pubblicazione: (2025)

MathEDU: Feedback Generation on Problem-Solving Processes for Mathematical Learning Support
di: Hsu, Wei-Ling, et al.
Pubblicazione: (2025)

Sparse-dLLM: Accelerating Diffusion LLMs with Dynamic Cache Eviction
di: Song, Yuerong, et al.
Pubblicazione: (2025)

Tuning LLMs with Contrastive Alignment Instructions for Machine Translation in Unseen, Low-resource Languages
di: Mao, Zhuoyuan, et al.
Pubblicazione: (2024)

LightMamba: Efficient Mamba Acceleration on FPGA with Quantization and Hardware Co-design
di: Wei, Renjie, et al.
Pubblicazione: (2025)

UniSparse: An Intermediate Language for General Sparse Format Customization
di: Liu, Jie, et al.
Pubblicazione: (2024)

ProxSparse: Regularized Learning of Semi-Structured Sparsity Masks for Pretrained LLMs
di: Liu, Hongyi, et al.
Pubblicazione: (2025)

SQ-LLaVA: Self-Questioning for Large Vision-Language Assistant
di: Sun, Guohao, et al.
Pubblicazione: (2024)

Foot-In-The-Door: A Multi-turn Jailbreak for LLMs
di: Weng, Zixuan, et al.
Pubblicazione: (2025)

QeRL: Beyond Efficiency -- Quantization-enhanced Reinforcement Learning for LLMs
di: Huang, Wei, et al.
Pubblicazione: (2025)

Sparse-BitNet: 1.58-bit LLMs are Naturally Friendly to Semi-Structured Sparsity
di: Zhang, Di, et al.
Pubblicazione: (2026)