Imagen de Portada

ATACompressor: Adaptive Task-Aware Compression for Efficient Long-Context Processing in LLMs

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Li, Xuancheng, Li, Haitao, Zhou, Yujia, Ai, Qingyao, Liu, Yiqun
Formato:	Preprint
Publicado:	2026
Materias:	Computation and Language Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Beyond Experience Retrieval: Learning to Generate Utility-Optimized Structured Experience for Frozen LLMs
por: Li, Xuancheng, et al.
Publicado: (2026)

Decoupling Reasoning and Knowledge Injection for In-Context Knowledge Editing
por: Wang, Changyue, et al.
Publicado: (2025)

MulFeRL: Enhancing Reinforcement Learning with Verbal Feedback in a Multi-turn Loop
por: Li, Xuancheng, et al.
Publicado: (2026)

Evaluation Ethics of LLMs in Legal Domain
por: Zhang, Ruizhe, et al.
Publicado: (2024)

How do Humans Process AI-generated Hallucination Contents: a Neuroimaging Study
por: Zhu, Shuqi, et al.
Publicado: (2026)

Are Long-LLMs A Necessity For Long-Context Tasks?
por: Qian, Hongjin, et al.
Publicado: (2024)

Unsupervised Real-Time Hallucination Detection based on the Internal States of Large Language Models
por: Su, Weihang, et al.
Publicado: (2024)

Improve Large Language Model Systems with User Logs
por: Wang, Changyue, et al.
Publicado: (2026)

Beyond Scalar Reward Model: Learning Generative Judge from Preference Data
por: Ye, Ziyi, et al.
Publicado: (2024)

Overview of the NTCIR-18 Automatic Evaluation of LLMs (AEOLLM) Task
por: Chen, Junjie, et al.
Publicado: (2025)

Option-ID Based Elimination For Multiple Choice Questions
por: Zhu, Zhenhao, et al.
Publicado: (2025)

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

CalibraEval: Calibrating Prediction Distribution to Mitigate Selection Bias in LLMs-as-Judges
por: Li, Haitao, et al.
Publicado: (2024)

Adapting LLMs for Efficient Context Processing through Soft Prompt Compression
por: Wang, Cangqing, et al.
Publicado: (2024)

Enhancing Judgment Document Generation via Agentic Legal Information Collection and Rubric-Guided Optimization
por: Su, Weihang, et al.
Publicado: (2026)

Analytical Search
por: Tu, Yiteng, et al.
Publicado: (2026)

What Scales in Cross-Entropy Scaling Law?
por: Yan, Junxi, et al.
Publicado: (2025)

Relative-Based Scaling Law for Neural Language Models
por: Yue, Baoqing, et al.
Publicado: (2025)

LiteLong: Resource-Efficient Long-Context Data Synthesis for LLMs
por: Jia, Junlong, et al.
Publicado: (2025)

APCE: Adaptive Progressive Context Expansion for Long Context Processing
por: Lee, Baisub, et al.
Publicado: (2025)

Evaluating Zero-Shot Long-Context LLM Compression
por: Wang, Chenyu, et al.
Publicado: (2024)

LongSafety: Enhance Safety for Long-Context LLMs
por: Huang, Mianqiu, et al.
Publicado: (2024)

Long Context Compression with Activation Beacon
por: Zhang, Peitian, et al.
Publicado: (2024)

Capability-aware Prompt Reformulation Learning for Text-to-Image Generation
por: Zhan, Jingtao, et al.
Publicado: (2024)

LLMs-as-Judges: A Comprehensive Survey on LLM-based Evaluation Methods
por: Li, Haitao, et al.
Publicado: (2024)

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

AdmTree: Compressing Lengthy Context with Adaptive Semantic Trees
por: Li, Yangning, et al.
Publicado: (2025)

SemToken: Semantic-Aware Tokenization for Efficient Long-Context Language Modeling
por: Liu, Dong, et al.
Publicado: (2025)

Chinese Court Simulation with LLM-Based Agent System
por: Zhang, Kaiyuan, et al.
Publicado: (2025)

Decoding Compressed Trust: Scrutinizing the Trustworthiness of Efficient LLMs Under Compression
por: Hong, Junyuan, et al.
Publicado: (2024)

ArcAligner: Adaptive Recursive Aligner for Compressed Context Embeddings in RAG
por: Li, Jianbo, et al.
Publicado: (2026)

LeKUBE: A Legal Knowledge Update BEnchmark
por: Wang, Changyue, et al.
Publicado: (2024)

SWAA: Sliding Window Attention Adaptation for Efficient and Quality Preserving Long Context Processing
por: Yu, Yijiong, et al.
Publicado: (2025)

Decoupled Reasoning with Implicit Fact Tokens (DRIFT): A Dual-Model Framework for Efficient Long-Context Inference
por: Xie, Wenxuan, et al.
Publicado: (2026)

Enhancing RAG Efficiency with Adaptive Context Compression
por: Guo, Shuyu, et al.
Publicado: (2025)

Tactic: Adaptive Sparse Attention with Clustering and Distribution Fitting for Long-Context LLMs
por: Zhu, Kan, et al.
Publicado: (2025)

Query Augmentation by Decoding Semantics from Brain Signals
por: Ye, Ziyi, et al.
Publicado: (2024)

Incentivizing In-depth Reasoning over Long Contexts with Process Advantage Shaping
por: Peng, Miao, et al.
Publicado: (2026)

LycheeCluster: Efficient Long-Context Inference with Structure-Aware Chunking and Hierarchical KV Indexing
por: Li, Dongfang, et al.
Publicado: (2026)

Sentinel: Decoding Context Utilization via Attention Probing for Efficient LLM Context Compression
por: Zhang, Yong, et al.
Publicado: (2025)