Copertina

AdapShot: Adaptive Many-Shot In-Context Learning with Semantic-Aware KV Cache Reuse

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Ou, Jie, Guo, Jinyu, Guo, Shiyao, Li, Yuang, Wu, Ruiqi, Wang, Zhaokun, Li, Wenyi, Tian, Wenhong
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Adaptive KV Cache Reuse for Fast Long-Context LLM Serving
di: li, Fei, et al.
Pubblicazione: (2026)

Accelerating Adaptive Retrieval Augmented Generation via Instruction-Driven Representation Reduction of Retrieval Overlaps
di: Ou, Jie, et al.
Pubblicazione: (2025)

ALTER: Asymmetric LoRA for Token-Entropy-Guided Unlearning of LLMs
di: Chen, Xunlei, et al.
Pubblicazione: (2026)

CAP: Controllable Alignment Prompting for Unlearning in LLMs
di: Wang, Zhaokun, et al.
Pubblicazione: (2026)

DynamicKV: Task-Aware Adaptive KV Cache Compression for Long Context LLMs
di: Zhou, Xiabin, et al.
Pubblicazione: (2024)

HASH-RAG: Bridging Deep Hashing with Retriever for Efficient, Fine Retrieval and Augmented Generation
di: Guo, Jinyu, et al.
Pubblicazione: (2025)

Noise-Robustness Through Noise: A Framework combining Asymmetric LoRA with Poisoning MoE
di: Wang, Zhaokun, et al.
Pubblicazione: (2025)

MAPLE: Many-Shot Adaptive Pseudo-Labeling for In-Context Learning
di: Chen, Zihan, et al.
Pubblicazione: (2025)

Many-Shot In-Context Learning
di: Agarwal, Rishabh, et al.
Pubblicazione: (2024)

CacheClip: Accelerating RAG with Effective KV Cache Reuse
di: Yang, Bin, et al.
Pubblicazione: (2025)

DASH-KV: Accelerating Long-Context LLM Inference via Asymmetric KV Cache Hashing
di: Guo, Jinyu, et al.
Pubblicazione: (2026)

Towards More Economical Context-Augmented LLM Generation by Reusing Stored KV Cache
di: Li, Hanchen, et al.
Pubblicazione: (2025)

ClusterKV: Manipulating LLM KV Cache in Semantic Space for Recallable Compression
di: Liu, Guangda, et al.
Pubblicazione: (2024)

MomentKV: Closing the Directional Gap in KV Cache Eviction for Long-Context Inference
di: Li, Yu, et al.
Pubblicazione: (2026)

ZSMerge: Zero-Shot KV Cache Compression for Memory-Efficient Long-Context LLMs
di: Liu, Xin, et al.
Pubblicazione: (2025)

Compressing Many-Shots in In-Context Learning
di: Khatri, Devvrit, et al.
Pubblicazione: (2025)

KVmix: Gradient-Based Layer Importance-Aware Mixed-Precision Quantization for KV Cache
di: Li, Fei, et al.
Pubblicazione: (2025)

CSKV: Training-Efficient Channel Shrinking for KV Cache in Long-Context Scenarios
di: Wang, Luning, et al.
Pubblicazione: (2024)

AFANet: Adaptive Frequency-Aware Network for Weakly-Supervised Few-Shot Semantic Segmentation
di: Ma, Jiaqi, et al.
Pubblicazione: (2024)

Lossless Acceleration of Large Language Model via Adaptive N-gram Parallel Decoding
di: Ou, Jie, et al.
Pubblicazione: (2024)

RelayCaching: Accelerating LLM Collaboration via Decoding KV Cache Reuse
di: Geng, Yingsheng, et al.
Pubblicazione: (2026)

On Many-Shot In-Context Learning for Long-Context Evaluation
di: Zou, Kaijian, et al.
Pubblicazione: (2024)

EFIM: Efficient Serving of LLMs for Infilling Tasks with Improved KV Cache Reuse
di: Guo, Tianyu, et al.
Pubblicazione: (2025)

ChunkKV: Semantic-Preserving KV Cache Compression for Efficient Long-Context LLM Inference
di: Liu, Xiang, et al.
Pubblicazione: (2025)

MadaKV: Adaptive Modality-Perception KV Cache Eviction for Efficient Multimodal Long-Context Inference
di: Li, Kunxi, et al.
Pubblicazione: (2025)

Many-Shot In-Context Learning for Molecular Inverse Design
di: Moayedpour, Saeed, et al.
Pubblicazione: (2024)

Selecting Demonstrations for Many-Shot In-Context Learning via Gradient Matching
di: Zhang, Jianfei, et al.
Pubblicazione: (2025)

Enabling Small Models for Zero-Shot Selection and Reuse through Model Label Learning
di: Zhang, Jia, et al.
Pubblicazione: (2024)

SABlock: Semantic-Aware KV Cache Eviction with Adaptive Compression Block Size
di: Chen, Jinhan, et al.
Pubblicazione: (2025)

KV-CAR: KV Cache Compression using Autoencoders and KV Reuse in Large Language Models
di: Roy, Sourjya, et al.
Pubblicazione: (2025)

Neuron: Learning Context-Aware Evolving Representations for Zero-Shot Skeleton Action Recognition
di: Chen, Yang, et al.
Pubblicazione: (2024)

Efficient Many-Shot In-Context Learning with Dynamic Block-Sparse Attention
di: Xiao, Emily, et al.
Pubblicazione: (2025)

Many-Shot In-Context Learning in Multimodal Foundation Models
di: Jiang, Yixing, et al.
Pubblicazione: (2024)

Towards Compute-Optimal Many-Shot In-Context Learning
di: Golchin, Shahriar, et al.
Pubblicazione: (2025)

OjaKV: Context-Aware Online Low-Rank KV Cache Compression
di: Zhu, Yuxuan, et al.
Pubblicazione: (2025)

KV Packet: Recomputation-Free Context-Independent KV Caching for LLMs
di: Chen, Chuangtao, et al.
Pubblicazione: (2026)

Distilling Many-Shot In-Context Learning into a Cheat Sheet
di: Honda, Ukyo, et al.
Pubblicazione: (2025)

Where and What Matters: Sensitivity-Aware Task Vectors for Many-Shot Multimodal In-Context Learning
di: Ma, Ziyu, et al.
Pubblicazione: (2025)

Meta-Semantics Augmented Few-Shot Relational Learning
di: Wu, Han, et al.
Pubblicazione: (2025)

Learning by Neighbor-Aware Semantics, Deciding by Open-form Flows: Towards Robust Zero-Shot Skeleton Action Recognition
di: Chen, Yang, et al.
Pubblicazione: (2025)