Image de couverture de livre

CTR-Sink: Attention Sink for Language Models in Click-Through Rate Prediction

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Li, Zixuan, Geng, Binzong, Xiong, Jing, He, Yong, Hu, Yuxuan, Chen, Jian, Chen, Dingwei, Chang, Xiyu, Zhang, Liang, Mo, Linjian, Li, Chengming, Yuan, Chuan, Sun, Zhenan
Format:	Preprint
Publié:	2025
Sujets:	Computation and Language
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Breaking the Length Barrier: LLM-Enhanced CTR Prediction in Long Textual User Behaviors
par: Geng, Binzong, et autres
Publié: (2024)

LoopCTR: Unlocking the Loop Scaling Power for Click-Through Rate Prediction
par: Tang, Jiakai, et autres
Publié: (2026)

Attention Sinks and Outliers in Attention Residuals
par: Luo, Haozheng, et autres
Publié: (2026)

Attention Sinks Induce Gradient Sinks: Massive Activations as Gradient Regulators in Transformers
par: Chen, Yihong, et autres
Publié: (2026)

SinkTrack: Attention Sink based Context Anchoring for Large Language Models
par: Liu, Xu, et autres
Publié: (2026)

The Spike, the Sparse and the Sink: Anatomy of Massive Activations and Attention Sinks
par: Sun, Shangwen, et autres
Publié: (2026)

Attention Sink Forges Native MoE in Attention Layers: Sink-Aware Training to Address Head Collapse
par: Fu, Zizhuo, et autres
Publié: (2026)

Efficient Streaming Language Models with Attention Sinks
par: Xiao, Guangxuan, et autres
Publié: (2023)

DGenCTR: Towards a Universal Generative Paradigm for Click-Through Rate Prediction via Discrete Diffusion
par: Zhang, Moyu, et autres
Publié: (2025)

Attention Sink in Transformers: A Survey on Utilization, Interpretation, and Mitigation
par: Su, Zunhai, et autres
Publié: (2026)

Efficient Vocal Source Separation Through Windowed Sink Attention
par: Benetatos, Christodoulos, et autres
Publié: (2025)

Garbage Attention in Large Language Models: BOS Sink Heads and Sink-aware Pruning
par: Sok, Jaewon, et autres
Publié: (2026)

DySink: Dynamic Frame Sinks for Autoregressive Long Video Generation
par: Ye, Bo, et autres
Publié: (2026)

ClickPrompt: CTR Models are Strong Prompt Generators for Adapting Language Models to CTR Prediction
par: Lin, Jianghao, et autres
Publié: (2023)

Attention Sinks in Diffusion Language Models
par: Rulli, Maximo Eduardo, et autres
Publié: (2025)

ASAP: Attention Sink Anchored Pruning
par: Lee, Jaehyuk, et autres
Publié: (2026)

On the Existence and Behavior of Secondary Attention Sinks
par: Wong, Jeffrey T. H., et autres
Publié: (2025)

When Sinks Help or Hurt: Unified Framework for Attention Sink in Large Vision-Language Models
par: Choi, Jiho, et autres
Publié: (2026)

How Attention Sinks Emerge in Large Language Models: An Interpretability Perspective
par: Peng, Runyu, et autres
Publié: (2026)

Surgery: Mitigating Harmful Fine-Tuning for Large Language Models via Attention Sink
par: Liu, Guozhi, et autres
Publié: (2026)

Spectral Filters, Dark Signals, and Attention Sinks
par: Cancedda, Nicola
Publié: (2024)

Sink or Swim
par: Larsen, Karen
Publié: (2004)

Forgetting to Forget: Attention Sink as A Gateway for Backdooring LLM Unlearning
par: Shang, Bingqi, et autres
Publié: (2025)

Quadratic Interest Network for Multimodal Click-Through Rate Prediction
par: Li, Honghao, et autres
Publié: (2025)

Global Nitrogen Deposition Promotes Carbon Sink Formation in Terrestrial Ecosystems
par: Lei Li, et autres
Publié: (2026)

To Sink or Not to Sink: Visual Information Pathways in Large Vision-Language Models
par: Luo, Jiayun, et autres
Publié: (2025)

Attention Sinks in Diffusion Transformers: A Causal Analysis
par: Wu, Fangzheng, et autres
Publié: (2026)

Softpick: No Attention Sink, No Massive Activations with Rectified Softmax
par: Zuhri, Zayd M. K., et autres
Publié: (2025)

SLASH the Sink: Sharpening Structural Attention Inside LLMs
par: Liu, Yiming, et autres
Publié: (2026)

Stochastic Parroting in Temporal Attention -- Regulating the Diagonal Sink
par: Hankemeier, Victoria, et autres
Publié: (2026)

SinkRouter: Sink-Aware Routing for Efficient Long-Context Decoding in Large Language and Multimodal Models
par: Liu, Junnan, et autres
Publié: (2026)

Addressing Exacerbated Attention Sink for Source-Free Cross-Domain Few-Shot Learning
par: Yi, Shuai, et autres
Publié: (2026)

The Structural Origin of Attention Sink: Variance Discrepancy, Super Neurons, and Dimension Disparity
par: Li, Siquan, et autres
Publié: (2026)

EST: Towards Efficient Scaling Laws in Click-Through Rate Prediction via Unified Modeling
par: Liu, Mingyang, et autres
Publié: (2026)

When Attention Sink Emerges in Language Models: An Empirical View
par: Gu, Xiangming, et autres
Publié: (2024)

On the Nature of Attention Sink that Shapes Decoding Strategy in Omni-LLMs
par: Yoo, Suho, et autres
Publié: (2026)

Artifacts and Attention Sinks: Structured Approximations for Efficient Vision Transformers
par: Lu, Andrew, et autres
Publié: (2025)

Attention Sinks: A 'Catch, Tag, Release' Mechanism for Embeddings
par: Zhang, Stephen, et autres
Publié: (2025)

Optimizing Feature Set for Click-Through Rate Prediction
par: Lyu, Fuyuan, et autres
Publié: (2023)

Multi-Epoch learning with Data Augmentation for Deep Click-Through Rate Prediction
par: Fan, Zhongxiang, et autres
Publié: (2024)