Image de couverture de livre

XL3M: A Training-free Framework for LLM Length Extension Based on Segment-wise Inference

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Wang, Shengnan, Bai, Youhui, Zhang, Lin, Zhou, Pingyi, Zhao, Shixiong, Zhang, Gong, Wang, Sen, Chen, Renhai, Xu, Hua, Sun, Hongwei
Format:	Preprint
Publié:	2024
Sujets:	Computation and Language Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Efficient Long-Context LLM Inference via KV Cache Clustering
par: Hu, Jie, et autres
Publié: (2025)

BigMac: A Communication-Efficient Mixture-of-Experts Model Structure for Fast Training and Inference
par: Jin, Zewen, et autres
Publié: (2025)

HATA: Trainable and Hardware-Efficient Hash-Aware Top-k Attention for Scalable Large Model Inference
par: Gong, Ping, et autres
Publié: (2025)

LiteCache: A Query Similarity-Driven, GPU-Centric KVCache Subsystem for Efficient LLM Inference
par: Yi, Jiawei, et autres
Publié: (2025)

HyLRA: Hybrid Layer Reuse Attention for Efficient Long-Context Inference
par: Ai, Xuan, et autres
Publié: (2026)

Accelerating Long-Tail Generation in Synchronous RLHF Training via Adaptive Tensor Parallelism
par: Zhao, Long, et autres
Publié: (2026)

AdaCluster: Adaptive Query-Key Clustering for Sparse Attention in Video Generation
par: Tan, Haoyue, et autres
Publié: (2026)

E^2-LLM: Efficient and Extreme Length Extension of Large Language Models
par: Liu, Jiaheng, et autres
Publié: (2024)

Lagom: Unleashing the Power of Communication and Computation Overlapping for Distributed LLM Training
par: Xu, Guanbin, et autres
Publié: (2026)

Train Short, Inference Long: Training-free Horizon Extension for Autoregressive Video Generation
par: Li, Jia, et autres
Publié: (2026)

iSeg: An Iterative Refinement-based Framework for Training-free Segmentation
par: Sun, Lin, et autres
Publié: (2024)

Making MoE-based LLM Inference Resilient with Tarragon
par: Zhang, Songyu, et autres
Publié: (2026)

MDP3: A Training-free Approach for List-wise Frame Selection in Video-LLMs
par: Sun, Hui, et autres
Publié: (2025)

Is Less More? Exploring Token Condensation as Training-free Test-time Adaptation
par: Wang, Zixin, et autres
Publié: (2024)

SARE: Sample-wise Adaptive Reasoning for Training-free Fine-grained Visual Recognition
par: Yang, Jingxiao, et autres
Publié: (2026)

WindowKV: Task-Adaptive Group-Wise KV Cache Window Selection for Efficient LLM Inference
par: Zuo, Youhui, et autres
Publié: (2025)

Uncertainty-Aware Bayes' Rule and Its Applications
par: Wang, Shixiong
Publié: (2023)

Correlation-Aware Select and Merge Attention for Efficient Fine-Tuning and Context Length Extension
par: Wang, Ning, et autres
Publié: (2024)

A Mathematical Theory of Top-$k$ Sparse Attention via Total Variation Distance
par: Tzachristas, Georgios, et autres
Publié: (2025)

Segmentation-guided Layer-wise Image Vectorization with Gradient Fills
par: Zhou, Hengyu, et autres
Publié: (2024)

Fourier Position Embedding: Enhancing Attention's Periodic Extension for Length Generalization
par: Hua, Ermo, et autres
Publié: (2024)

PoSE: Efficient Context Window Extension of LLMs via Positional Skip-wise Training
par: Zhu, Dawei, et autres
Publié: (2023)

Scene-wise Adaptive Network for Dynamic Cold-start Scenes Optimization in CTR Prediction
par: Li, Wenhao, et autres
Publié: (2024)

Training-free Geometric Image Editing on Diffusion Models
par: Zhu, Hanshen, et autres
Publié: (2025)

Bioinspired Directional Hydrogel‐Based High‐Performance Flexible Sensor for Multiple Jumping Pattern Detection in Athletic Training
par: Hanqi Wang, et autres
Publié: (2025)

SSMRadNet : A Sample-wise State-Space Framework for Efficient and Ultra-Light Radar Segmentation and Object Detection
par: Sen, Anuab, et autres
Publié: (2025)

HeadInfer: Memory-Efficient LLM Inference by Head-wise Offloading
par: Luo, Cheng, et autres
Publié: (2025)

SlimPack: Fine-Grained Asymmetric Packing for Balanced and Efficient Variable-Length LLM Training
par: Liu, Yuliang, et autres
Publié: (2025)

NEFT: A Unified Transformer Framework for Efficient Near-Field CSI Feedback in XL-MIMO Systems
par: Mao, Tianqi, et autres
Publié: (2025)

3D-TAFS: A Training-free Framework for 3D Affordance Segmentation
par: Chu, Meng, et autres
Publié: (2024)

Distributional Robustness Bounds Generalization Errors
par: Wang, Shixiong, et autres
Publié: (2022)

Using Cu‐Based Metal–Organic Framework as a Comprehensive and Powerful Antioxidant Nanozyme for Efficient Osteoarthritis Treatment
par: Bo Yu, et autres
Publié: (2024)

Tensor-Structured Bayesian Channel Prediction for Upper Mid-Band XL-MIMO Systems
par: Hou, Hongwei, et autres
Publié: (2025)

Towards Feedback-to-Plan Decisions for Self-Evolving LLM Agents in CUDA Kernel Generation
par: Chong, Yee Hin, et autres
Publié: (2026)

Mixture of Attention Spans: Optimizing LLM Inference Efficiency with Heterogeneous Sliding-Window Lengths
par: Fu, Tianyu, et autres
Publié: (2024)

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

VecAttention: Vector-wise Sparse Attention for Accelerating Long Context Inference
par: Liu, Anmin, et autres
Publié: (2026)

Near-Field Multiuser Beam Training for XL-MIMO: An End-to-End Interference-Aware Approach with Pilot Limitations
par: Li, Xinyang, et autres
Publié: (2026)

Tarot-SAM3: Training-free SAM3 for Any Referring Expression Segmentation
par: Zhang, Weiming, et autres
Publié: (2026)

PAT: Pixel-wise Adaptive Training for Long-tailed Segmentation
par: Do, Khoi, et autres
Publié: (2024)