Copertina

Autoencoding-Free Context Compression for LLMs via Contextual Semantic Anchors

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Liu, Xin, Zhao, Runsong, Huang, Pengcheng, Liu, Xinyu, Xiao, Junyi, Xiao, Chunyang, Xiao, Tong, Gao, Shengxiang, Yu, Zhengtao, Zhu, Jingbo
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

Position IDs Matter: An Enhanced Position Layout for Efficient Context Compression in Large Language Models
di: Zhao, Runsong, et al.
Pubblicazione: (2024)

MemoSight: Unifying Context Compression and Multi Token Prediction for Reasoning Acceleration
di: Liu, Xinyu, et al.
Pubblicazione: (2026)

Forgetting Curve: A Reliable Method for Evaluating Memorization Capability for Long-context Models
di: Liu, Xinyu, et al.
Pubblicazione: (2024)

MTP-S2UT: Enhancing Speech-to-Speech Translation Quality with Multi-token Prediction
di: Wang, Jianjin, et al.
Pubblicazione: (2025)

PoC: Performance-oriented Context Compression for Large Language Models via Performance Prediction
di: Zhao, Runsong, et al.
Pubblicazione: (2026)

Translate-and-Revise: Boosting Large Language Models for Constrained Translation
di: Huang, Pengcheng, et al.
Pubblicazione: (2024)

ChartAnchor: Chart Grounding with Structural-Semantic Fidelity
di: Li, Xinhang, et al.
Pubblicazione: (2025)

Multilingual Generative Retrieval via Cross-lingual Semantic Compression
di: Huang, Yuxin, et al.
Pubblicazione: (2025)

APR: Penalizing Structural Redundancy in Large Reasoning Models via Anchor-based Process Rewards
di: Chang, Kaiyan, et al.
Pubblicazione: (2026)

CoMeT: Collaborative Memory Transformer for Efficient Long Context Modeling
di: Zhao, Runsong, et al.
Pubblicazione: (2026)

EfficientGraph-RAG: Structured Retrieval-State Management for Cross-Task Retrieval-Augmented Generation
di: Niu, Miaohe, et al.
Pubblicazione: (2026)

M-CIF: Multi-Scale Alignment For CIF-Based Non-Autoregressive ASR
di: Mao, Ruixiang, et al.
Pubblicazione: (2025)

Structural Anchor Pruning: Training-Free Multi-Vector Compression for Visual Document Retrieval
di: Liu, Zhuchenyang, et al.
Pubblicazione: (2026)

Foundations of Large Language Models
di: Xiao, Tong, et al.
Pubblicazione: (2025)

FLEXI: Benchmarking Full-duplex Human-LLM Speech Interaction
di: Ge, Yuan, et al.
Pubblicazione: (2025)

RLAIF-SPA: Structured AI Feedback for Semantic-Prosodic Alignment in Speech Synthesis
di: Yang, Qing, et al.
Pubblicazione: (2025)

SECodec: Structural Entropy-based Compressive Speech Representation Codec for Speech Language Models
di: Wang, Linqin, et al.
Pubblicazione: (2024)

Robust UAV Jittering and Task Scheduling in Mobile Edge Computing with Data Compression
di: Li, Bin, et al.
Pubblicazione: (2024)

InfLLM: Training-Free Long-Context Extrapolation for LLMs with an Efficient Context Memory
di: Xiao, Chaojun, et al.
Pubblicazione: (2024)

Latent-Compressed Variational Autoencoder for Video Diffusion Models
di: Guan, Jiarui, et al.
Pubblicazione: (2026)

Read As Human: Compressing Context via Parallelizable Close Reading and Skimming
di: Tang, Jiwei, et al.
Pubblicazione: (2026)

Multilingual Knowledge Graph Completion via Efficient Multilingual Knowledge Sharing
di: Mao, Cunli, et al.
Pubblicazione: (2025)

IIET: Efficient Numerical Transformer via Implicit Iterative Euler Method
di: Liu, Xinyu, et al.
Pubblicazione: (2025)

Leveraging Unit Language Guidance to Advance Speech Modeling in Textless Speech-to-Speech Translation
di: Zhang, Yuhao, et al.
Pubblicazione: (2025)

Glyph: Scaling Context Windows via Visual-Text Compression
di: Cheng, Jiale, et al.
Pubblicazione: (2025)

Process In-Context Learning: Enhancing Mathematical Reasoning via Dynamic Demonstration Insertion
di: Gao, Ang, et al.
Pubblicazione: (2026)

Multilingual Knowledge Graph Completion from Pretrained Language Models with Knowledge Constraints
di: Song, Ran, et al.
Pubblicazione: (2024)

Semantic Anchors in In-Context Learning: Why Small LLMs Cannot Flip Their Labels
di: Kumar, Anantha Padmanaban Krishna
Pubblicazione: (2025)

SARM: LLM-Augmented Semantic Anchor for End-to-End Live-Streaming Ranking
di: Yang, Ruochen, et al.
Pubblicazione: (2026)

EIT: Enhanced Interactive Transformer
di: Zheng, Tong, et al.
Pubblicazione: (2022)

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

MRGSEM-Sum: An Unsupervised Multi-document Summarization Framework based on Multi-Relational Graphs and Structural Entropy Minimization
di: Zhang, Yongbing, et al.
Pubblicazione: (2025)

A Mixed-Language Multi-Document News Summarization Dataset and a Graphs-Based Extract-Generate Model
di: Gao, Shengxiang, et al.
Pubblicazione: (2024)

Elastic-dLLM: Position Preserving Context Compression and Augmentation of Diffusion LLMs
di: Wu, Junyi, et al.
Pubblicazione: (2026)

Embedding Compression via Spherical Coordinates
di: Xiao, Han
Pubblicazione: (2026)

Does the Opening of High‐Speed Rail Give Rise to the Birth of Enterprises in Peripheral Areas: Evidence From County‐Level Cities in China?
di: Xiao Li, et al.
Pubblicazione: (2025)

Compressing Lengthy Context With UltraGist
di: Zhang, Peitian, et al.
Pubblicazione: (2024)

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

RITFIS: Robust input testing framework for LLMs-based intelligent software
di: Xiao, Mingxuan, et al.
Pubblicazione: (2024)

Mean Masked Autoencoder with Flow-Mixing for Encrypted Traffic Classification
di: Liu, Xiao, et al.
Pubblicazione: (2026)