Beyond Uniform Query Distribution: Key-Driven Grouped Query Attention
Fuente:
arXiv
Guardado en:
| Autores principales: | Khan, Zohaib, Khaquan, Muhammad, Tafveez, Omer, Samiwala, Burhanuddin, Raza, Agha Ali |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
Ejemplares similares
GQKVA: Efficient Pre-training of Transformers by Grouping Queries, Keys, and Values
por: Javadi, Farnoosh, et al.
Publicado: (2023)
por: Javadi, Farnoosh, et al.
Publicado: (2023)
LDA-AQU: Adaptive Query-guided Upsampling via Local Deformable Attention
por: Du, Zewen, et al.
Publicado: (2024)
por: Du, Zewen, et al.
Publicado: (2024)
Masked Multi-Query Slot Attention for Unsupervised Object Discovery
por: Pramanik, Rishav, et al.
Publicado: (2024)
por: Pramanik, Rishav, et al.
Publicado: (2024)
KOPPA: Improving Prompt-based Continual Learning with Key-Query Orthogonal Projection and Prototype-based One-Versus-All
por: Tran, Quyen, et al.
Publicado: (2023)
por: Tran, Quyen, et al.
Publicado: (2023)
Video-Based MPAA Rating Prediction: An Attention-Driven Hybrid Architecture Using Contrastive Learning
por: Neogi, Dipta, et al.
Publicado: (2025)
por: Neogi, Dipta, et al.
Publicado: (2025)
QuARI: Query Adaptive Retrieval Improvement
por: Xing, Eric, et al.
Publicado: (2025)
por: Xing, Eric, et al.
Publicado: (2025)
Attention Based Simple Primitives for Open World Compositional Zero-Shot Learning
por: Munir, Ans, et al.
Publicado: (2024)
por: Munir, Ans, et al.
Publicado: (2024)
An Enhanced Large Language Model For Cross Modal Query Understanding System Using DL-KeyBERT Based CAZSSCL-MPGPT
por: Singh, Shreya
Publicado: (2025)
por: Singh, Shreya
Publicado: (2025)
Graph Query Networks for Object Detection with Automotive Radar
por: Saini, Loveneet, et al.
Publicado: (2025)
por: Saini, Loveneet, et al.
Publicado: (2025)
AttentionDrop: A Novel Regularization Method for Transformer Models
por: Baig, Mirza Samad Ahmed, et al.
Publicado: (2025)
por: Baig, Mirza Samad Ahmed, et al.
Publicado: (2025)
Multimodal Object Query Initialization for 3D Object Detection
por: van Geerenstein, Mathijs R., et al.
Publicado: (2023)
por: van Geerenstein, Mathijs R., et al.
Publicado: (2023)
Enhancing Cost Efficiency in Active Learning with Candidate Set Query
por: Gwon, Yeho, et al.
Publicado: (2025)
por: Gwon, Yeho, et al.
Publicado: (2025)
Countdown-Code: A Testbed for Studying The Emergence and Generalization of Reward Hacking in RLVR
por: Khalifa, Muhammad, et al.
Publicado: (2026)
por: Khalifa, Muhammad, et al.
Publicado: (2026)
SketchQL Demonstration: Zero-shot Video Moment Querying with Sketches
por: Wu, Renzhi, et al.
Publicado: (2024)
por: Wu, Renzhi, et al.
Publicado: (2024)
Noise-Tolerant Few-Shot Unsupervised Adapter for Vision-Language Models
por: Ali, Eman, et al.
Publicado: (2023)
por: Ali, Eman, et al.
Publicado: (2023)
PQDT: Pseudo-Query Dual Transformer for Robust Point Cloud Restoration
por: Wu, Haoqing, et al.
Publicado: (2026)
por: Wu, Haoqing, et al.
Publicado: (2026)
Hausdorff Distance Matching with Adaptive Query Denoising for Rotated Detection Transformer
por: Lee, Hakjin, et al.
Publicado: (2023)
por: Lee, Hakjin, et al.
Publicado: (2023)
Structure Disruption: Subverting Malicious Diffusion-Based Inpainting via Self-Attention Query Perturbation
por: He, Yuhao, et al.
Publicado: (2025)
por: He, Yuhao, et al.
Publicado: (2025)
Recommender Engine Driven Client Selection in Federated Brain Tumor Segmentation
por: Khan, Muhammad Irfan, et al.
Publicado: (2024)
por: Khan, Muhammad Irfan, et al.
Publicado: (2024)
LifelongMemory: Leveraging LLMs for Answering Queries in Long-form Egocentric Videos
por: Wang, Ying, et al.
Publicado: (2023)
por: Wang, Ying, et al.
Publicado: (2023)
Matryoshka Query Transformer for Large Vision-Language Models
por: Hu, Wenbo, et al.
Publicado: (2024)
por: Hu, Wenbo, et al.
Publicado: (2024)
RAVEN: Query-Guided Representation Alignment for Question Answering over Audio, Video, Embedded Sensors, and Natural Language
por: Biswas, Subrata, et al.
Publicado: (2025)
por: Biswas, Subrata, et al.
Publicado: (2025)
A Deep Learning Pipeline for Epilepsy Genomic Analysis Using GPT-2 XL and NVIDIA H100
por: Latif, Muhammad Omer, et al.
Publicado: (2025)
por: Latif, Muhammad Omer, et al.
Publicado: (2025)
Accelerating Targeted Hard-Label Adversarial Attacks in Low-Query Black-Box Settings
por: Swaminathan, Arjhun, et al.
Publicado: (2025)
por: Swaminathan, Arjhun, et al.
Publicado: (2025)
Plasticity vs. Rigidity: The Impact of Low-Rank Adapters on Reasoning on a Micro-Budget
por: Khan, Zohaib, et al.
Publicado: (2026)
por: Khan, Zohaib, et al.
Publicado: (2026)
A Tumor Aware DenseNet Swin Hybrid Learning with Boosted and Hierarchical Feature Spaces for Large-Scale Brain MRI Classification
por: Shah, Muhammad Ali, et al.
Publicado: (2026)
por: Shah, Muhammad Ali, et al.
Publicado: (2026)
VQPP: Video Query Performance Prediction Benchmark
por: Lutu, Adrian Catalin, et al.
Publicado: (2026)
por: Lutu, Adrian Catalin, et al.
Publicado: (2026)
Opportunistic Target Selection: Early Directional Commitment for Query-Efficient Black-Box Adversarial Attacks
por: Tariolle, Florent, et al.
Publicado: (2026)
por: Tariolle, Florent, et al.
Publicado: (2026)
Towards High-Fidelity Gaussian Splatting with Queried-Convolution Neural Networks
por: Kumar, Abhinav, et al.
Publicado: (2025)
por: Kumar, Abhinav, et al.
Publicado: (2025)
How Deep is Your Art: An Experimental Study on the Limits of Artistic Understanding in a Single-Task, Single-Modality Neural Network
por: Zahedi, Mahan Agha, et al.
Publicado: (2022)
por: Zahedi, Mahan Agha, et al.
Publicado: (2022)
Attention-Guided Dual-Stream Learning for Group Engagement Recognition: Fusing Transformer-Encoded Motion Dynamics with Scene Context via Adaptive Gating
por: Chowdhury, Saniah Kayenat, et al.
Publicado: (2026)
por: Chowdhury, Saniah Kayenat, et al.
Publicado: (2026)
Annotation-Free Reinforcement Learning Query Rewriting via Verifiable Search Reward
por: Cha, Sungguk, et al.
Publicado: (2025)
por: Cha, Sungguk, et al.
Publicado: (2025)
PARCEL: Pool-Anchored Resampling with Conditioned Elastic Queries for Efficient Vision-Language Understanding
por: Kuzucu, Selim, et al.
Publicado: (2026)
por: Kuzucu, Selim, et al.
Publicado: (2026)
Gated-Attention Feature-Fusion Based Framework for Poverty Prediction
por: Ramzan, Muhammad Umer, et al.
Publicado: (2024)
por: Ramzan, Muhammad Umer, et al.
Publicado: (2024)
UDM-GRPO: Stable and Efficient Group Relative Policy Optimization for Uniform Discrete Diffusion Models
por: Wang, Jiaqi, et al.
Publicado: (2026)
por: Wang, Jiaqi, et al.
Publicado: (2026)
Learning Semantic Segmentation with Query Points Supervision on Aerial Images
por: Rivier, Santiago, et al.
Publicado: (2023)
por: Rivier, Santiago, et al.
Publicado: (2023)
Scratching Visual Transformer's Back with Uniform Attention
por: Hyeon-Woo, Nam, et al.
Publicado: (2022)
por: Hyeon-Woo, Nam, et al.
Publicado: (2022)
Reproducing DragDiffusion: Interactive Point-Based Editing with Diffusion Models
por: Subhan, Ali, et al.
Publicado: (2026)
por: Subhan, Ali, et al.
Publicado: (2026)
Latent Geometric Chords for Query-Efficient Decision-Based Adversarial Attacks
por: Khine, Ei Hmue, et al.
Publicado: (2026)
por: Khine, Ei Hmue, et al.
Publicado: (2026)
Align Your Query: Representation Alignment for Multimodality Medical Object Detection
por: Seo, Ara, et al.
Publicado: (2025)
por: Seo, Ara, et al.
Publicado: (2025)
Ejemplares similares
-
GQKVA: Efficient Pre-training of Transformers by Grouping Queries, Keys, and Values
por: Javadi, Farnoosh, et al.
Publicado: (2023) -
LDA-AQU: Adaptive Query-guided Upsampling via Local Deformable Attention
por: Du, Zewen, et al.
Publicado: (2024) -
Masked Multi-Query Slot Attention for Unsupervised Object Discovery
por: Pramanik, Rishav, et al.
Publicado: (2024) -
KOPPA: Improving Prompt-based Continual Learning with Key-Query Orthogonal Projection and Prototype-based One-Versus-All
por: Tran, Quyen, et al.
Publicado: (2023) -
Video-Based MPAA Rating Prediction: An Attention-Driven Hybrid Architecture Using Contrastive Learning
por: Neogi, Dipta, et al.
Publicado: (2025)