Cover Image

PEAR: Position-Embedding-Agnostic Attention Re-weighting Enhances Retrieval-Augmented Generation with Zero Inference Overhead

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Tan, Tao, Qian, Yining, Lv, Ang, Lin, Hongzhan, Wu, Songhao, Wang, Yongbo, Wang, Feng, Wu, Jingtong, Lu, Xin, Yan, Rui
Format:	Preprint
Published:	2024
Subjects:	Computation and Language Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Autonomy-of-Experts Models
by: Lv, Ang, et al.
Published: (2025)

iPEAR: Iterative Pyramid Estimation with Attention and Residuals for Deformable Medical Image Registration
by: Wu, Heming, et al.
Published: (2025)

ZeCO: Zero Communication Overhead Sequence Parallelism for Linear Attention
by: Chou, Yuhong, et al.
Published: (2025)

From Concepts to Components: Concept-Agnostic Attention Module Discovery in Transformers
by: Su, Jingtong, et al.
Published: (2025)

Language-Agnostic Visual Embeddings for Cross-Script Handwriting Retrieval
by: Chen, Fangke, et al.
Published: (2026)

ReZG: Retrieval-Augmented Zero-Shot Counter Narrative Generation for Hate Speech
by: Jiang, Shuyu, et al.
Published: (2023)

Understanding Parametric Knowledge Injection in Retrieval-Augmented Generation
by: Tang, Minghao, et al.
Published: (2025)

Batch-ICL: Effective, Efficient, and Order-Agnostic In-Context Learning
by: Zhang, Kaiyi, et al.
Published: (2024)

Retrieval-Enhanced Mutation Mastery: Augmenting Zero-Shot Prediction of Protein Language Model
by: Tan, Yang, et al.
Published: (2024)

PEAR: Pixel-aligned Expressive humAn mesh Recovery
by: Wu, Jiahao, et al.
Published: (2026)

The Rotary Position Embedding May Cause Dimension Inefficiency in Attention Heads for Long-Distance Retrieval
by: Chiang, Ting-Rui, et al.
Published: (2025)

StepHint: Multi-level Stepwise Hints Enhance Reinforcement Learning to Reason
by: Zhang, Kaiyi, et al.
Published: (2025)

PolarQuant: Leveraging Polar Transformation for Efficient Key Cache Quantization and Decoding Acceleration
by: Wu, Songhao, et al.
Published: (2025)

Activation-Descent Regularization for Input Optimization of ReLU Networks
by: Yu, Hongzhan, et al.
Published: (2024)

S0 Tuning: Zero-Overhead Adaptation of Hybrid Recurrent-Attention Models
by: Young, Jack
Published: (2026)

ReXMoE: Reusing Experts with Minimal Overhead in Mixture-of-Experts
by: Tan, Zheyue, et al.
Published: (2025)

ASTRA: Enhancing Multi-Subject Generation with Retrieval-Augmented Pose Guidance and Disentangled Position Embedding
by: Xia, Tianze, et al.
Published: (2026)

Mixture of In-Context Experts Enhance LLMs' Long Context Awareness
by: Lin, Hongzhan, et al.
Published: (2024)

LLM-Augmented Retrieval: Enhancing Retrieval Models Through Language Models and Doc-Level Embedding
by: Wu, Mingrui, et al.
Published: (2024)

PEAR: Planner-Executor Agent Robustness Benchmark
by: Dong, Shen, et al.
Published: (2025)

PEAR: Equal Area Weather Forecasting on the Sphere
by: Linander, Hampus, et al.
Published: (2025)

CacheFocus: Dynamic Cache Re-Positioning for Efficient Retrieval-Augmented Generation
by: Lee, Kun-Hui, et al.
Published: (2025)

FIER: Fine-Grained and Efficient KV Cache Retrieval for Long-context LLM Inference
by: Wang, Dongwei, et al.
Published: (2025)

ReAttn: Improving Attention-based Re-ranking via Attention Re-weighting
by: Tian, Yuxing, et al.
Published: (2026)

Near-Zero-Overhead Freshness for Recommendation Systems via Inference-Side Model Updates
by: Yu, Wenjun, et al.
Published: (2025)

Searching for Best Practices in Retrieval-Augmented Generation
by: Wang, Xiaohua, et al.
Published: (2024)

Safe Interval Motion Planning for Quadrotors in Dynamic Environments
by: Huang, Songhao, et al.
Published: (2024)

Embedding-Informed Adaptive Retrieval-Augmented Generation of Large Language Models
by: Huang, Chengkai, et al.
Published: (2024)

PEAR: Phase Entropy Aware Reward for Efficient Reasoning
by: Huang, Chen, et al.
Published: (2025)

PEAR: Phrase-Based Hand-Object Interaction Anticipation
by: Zhang, Zichen, et al.
Published: (2024)

PRODUCTION OF PEAR TREES GRAFTED UNDER HYDROPONIC CONDITIONS
by: Aline das Graças de SOUZA
Published: (2011)

Enhancing IMU-Based Online Handwriting Recognition via Contrastive Learning with Zero Inference Overhead
by: Li, Jindong, et al.
Published: (2026)

Detecting Miscitation on the Scholarly Web through LLM-Augmented Text-Rich Graph Learning
by: Wu, Huidong, et al.
Published: (2026)

MotionRAG: Motion Retrieval-Augmented Image-to-Video Generation
by: Zhu, Chenhui, et al.
Published: (2025)

Adaptive Schema-aware Event Extraction with Retrieval-Augmented Generation
by: Liang, Sheng, et al.
Published: (2025)

Checkmate: Zero-Overhead Model Checkpointing via Network Gradient Replication
by: Bhardwaj, Ankit, et al.
Published: (2025)

From 1,000,000 Users to Every User: Scaling Up Personalized Preference for User-level Alignment
by: Li, Jia-Nan, et al.
Published: (2025)

ReMoMask: Retrieval-Augmented Masked Motion Generation
by: Li, Zhengdao, et al.
Published: (2025)

Re-Align: Aligning Vision Language Models via Retrieval-Augmented Direct Preference Optimization
by: Xing, Shuo, et al.
Published: (2025)

ReFIR: Grounding Large Restoration Models with Retrieval Augmentation
by: Guo, Hang, et al.
Published: (2024)