Cover Image

Probe and Skip: Self-Predictive Token Skipping for Efficient Long-Context LLM Inference

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wu, Zimeng, Wang, Donghao, Jin, Chaozhe, Chen, Jiaxin, Wang, Yunhong
Format:	Preprint
Published:	2026
Subjects:	Computation and Language Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

DASH: Input-Aware Dynamic Layer Skipping for Efficient LLM Inference with Markov Decision Policies
by: Yang, Ning, et al.
Published: (2025)

FFN-SkipLLM: A Hidden Gem for Autoregressive Decoding with Adaptive Feed Forward Skipping
by: Jaiswal, Ajay, et al.
Published: (2024)

AdaSkip: Adaptive Sublayer Skipping for Accelerating Long-Context LLM Inference
by: He, Zhuomin, et al.
Published: (2025)

PoSE: Efficient Context Window Extension of LLMs via Positional Skip-wise Training
by: Zhu, Dawei, et al.
Published: (2023)

LayerSkip: Enabling Early Exit Inference and Self-Speculative Decoding
by: Elhoushi, Mostafa, et al.
Published: (2024)

Skip-Connected Policy Optimization for Implicit Advantage
by: Teng, Fengwei, et al.
Published: (2026)

SkipSR: Faster Super Resolution with Token Skipping
by: Choudhury, Rohan, et al.
Published: (2025)

Skipformer: A Skip-and-Recover Strategy for Efficient Speech Recognition
by: Zhu, Wenjing, et al.
Published: (2024)

Learning to Skip the Middle Layers of Transformers
by: Lawson, Tim, et al.
Published: (2025)

LazyLLM: Dynamic Token Pruning for Efficient Long Context LLM Inference
by: Fu, Qichen, et al.
Published: (2024)

ConfLayers: Adaptive Confidence-based Layer Skipping for Self-Speculative Decoding
by: Amer, Walaa, et al.
Published: (2026)

Skip-It? Theoretical Conditions for Layer Skipping in Vision-Language Models
by: Hartman, Max, et al.
Published: (2025)

Token Sparse Attention: Efficient Long-Context Inference with Interleaved Token Selection
by: Jo, Dongwon, et al.
Published: (2026)

TokenSelect: Efficient Long-Context Inference and Length Extrapolation for LLMs via Dynamic Token-Level KV Cache Selection
by: Wu, Wei, et al.
Published: (2024)

Post-Trained MoE Can Skip Half Experts via Self-Distillation
by: Lv, Xingtai, et al.
Published: (2026)

On SkipGram Word Embedding Models with Negative Sampling: Unified Framework and Impact of Noise Distributions
by: Liu, Dezhi, et al.
Published: (2020)

Federated Learning with Layer Skipping: Efficient Training of Large Language Models for Healthcare NLP
by: Zhang, Lihong, et al.
Published: (2025)

CLaSp: In-Context Layer Skip for Self-Speculative Decoding
by: Chen, Longze, et al.
Published: (2025)

Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference
by: Tang, Jiaming, et al.
Published: (2024)

Not All Experts are Equal: Efficient Expert Pruning and Skipping for Mixture-of-Experts Large Language Models
by: Lu, Xudong, et al.
Published: (2024)

SkipViT: Speeding Up Vision Transformers with a Token-Level Skip Connection
by: Ataiefard, Foozhan, et al.
Published: (2024)

XKV: Personalized KV Cache Memory Reduction for Long-Context LLM Inference
by: Li, Weizhuo, et al.
Published: (2024)

LLMs Know What to Drop: Self-Attention Guided KV Cache Eviction for Efficient Long-Context Inference
by: Wang, Guangtao, et al.
Published: (2025)

RetrievalAttention: Accelerating Long-Context LLM Inference via Vector Retrieval
by: Liu, Di, et al.
Published: (2024)

TTKV: Temporal-Tiered KV Cache for Long-Context LLM Inference
by: Dzikanyanga, Gradwell, et al.
Published: (2026)

LLMSteer: Improving Long-Context LLM Inference by Steering Attention on Reused Contexts
by: Gu, Zhuohan, et al.
Published: (2024)

Megalodon: Efficient LLM Pretraining and Inference with Unlimited Context Length
by: Ma, Xuezhe, et al.
Published: (2024)

Ltri-LLM: Streaming Long Context Inference for LLMs with Training-Free Dynamic Triangular Attention Pattern
by: Tang, Hongyin, et al.
Published: (2024)

DynSplit-KV: Dynamic Semantic Splitting for KVCache Compression in Efficient Long-Context LLM Inference
by: Ye, Jiancai, et al.
Published: (2026)

Position-Agnostic Pre-Projection for Transformer Attention: Nonlinear Feature Construction and Content Skip Before Q/K/V
by: Shinde, Chirag
Published: (2026)

SkipPredict: When to Invest in Predictions for Scheduling
by: Shahout, Rana, et al.
Published: (2024)

DELTA: Dynamic Layer-Aware Token Attention for Efficient Long-Context Reasoning
by: Zarch, Hossein Entezari, et al.
Published: (2025)

LLM Maybe LongLM: Self-Extend LLM Context Window Without Tuning
by: Jin, Hongye, et al.
Published: (2024)

ShadowKV: KV Cache in Shadows for High-Throughput Long-Context LLM Inference
by: Sun, Hanshi, et al.
Published: (2024)

Collaborative Multi-Mode Pruning for Vision-Language Models
by: Wu, Zimeng, et al.
Published: (2026)

Efficient Temporal Tokenization for Mobility Prediction with Large Language Models
by: He, Haoyu, et al.
Published: (2025)

PQCache: Product Quantization-based KVCache for Long Context LLM Inference
by: Zhang, Hailin, et al.
Published: (2024)

Hopscotch: Discovering and Skipping Redundancies in Language Models
by: Eyceoz, Mustafa, et al.
Published: (2025)

TokenSkip: Controllable Chain-of-Thought Compression in LLMs
by: Xia, Heming, et al.
Published: (2025)

Always Skip Attention
by: Ji, Yiping, et al.
Published: (2025)