Imagen de Portada

Attention Projection Mixing with Exogenous Anchors

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autor principal:	Su, Jonathan
Formato:	Preprint
Publicado:	2026
Materias:	Computation and Language
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Echoes as Anchors: Probabilistic Costs and Attention Refocusing in LLM Reasoning
por: Hao, Zhuoyuan, et al.
Publicado: (2026)

Attention Illuminates LLM Reasoning: The Preplan-and-Anchor Rhythm Enables Fine-Grained Policy Optimization
por: Li, Yang, et al.
Publicado: (2025)

AnchorOPT: Towards Optimizing Dynamic Anchors for Adaptive Prompt Learning
por: Li, Zheng, et al.
Publicado: (2025)

Inference-Friendly Models With MixAttention
por: Rajput, Shashank, et al.
Publicado: (2024)

AdvAnchor: Enhancing Diffusion Model Unlearning with Adversarial Anchors
por: Zhao, Mengnan, et al.
Publicado: (2024)

Mediocrity is the key for LLM as a Judge Anchor Selection
por: Don-Yehiya, Shachar, et al.
Publicado: (2026)

Instruction Anchor: Dissecting the Mechanistic Dynamics of Modality Arbitration
por: Zhang, Yu, et al.
Publicado: (2026)

Anchor Points: Benchmarking Models with Much Fewer Examples
por: Vivek, Rajan, et al.
Publicado: (2023)

GUI-AIMA: Aligning Intrinsic Multimodal Attention with a Context Anchor for GUI Grounding
por: Zhou, Shijie, et al.
Publicado: (2025)

APTQ: Attention-aware Post-Training Mixed-Precision Quantization for Large Language Models
por: Guan, Ziyi, et al.
Publicado: (2024)

Measuring Affinity between Attention-Head Weight Subspaces via the Projection Kernel
por: Yamagiwa, Hiroaki, et al.
Publicado: (2026)

Anchor-based Large Language Models
por: Pang, Jianhui, et al.
Publicado: (2024)

Casual as an Anchor: Resolving Supervision Misalignment in Formality Transfer Dataset
por: Yu, Hyojeong, et al.
Publicado: (2026)

FinAnchor: Aligned Multi-Model Representations for Financial Prediction
por: He, Zirui, et al.
Publicado: (2026)

SAC-Opt: Semantic Anchors for Iterative Correction in Optimization Modeling
por: Zhang, Yansen, et al.
Publicado: (2025)

KVSink: Understanding and Enhancing the Preservation of Attention Sinks in KV Cache Quantization for LLMs
por: Su, Zunhai, et al.
Publicado: (2025)

Semantic Motion Anchors: Bridging Motion and Meaning in Co-Speech Gestures
por: Suresh, Varsha, et al.
Publicado: (2026)

Autoencoding-Free Context Compression for LLMs via Contextual Semantic Anchors
por: Liu, Xin, et al.
Publicado: (2025)

Answer-Centric or Reasoning-Driven? Uncovering the Latent Memory Anchor in LLMs
por: Wu, Yang, et al.
Publicado: (2025)

Reinforcement Learning with Rubric Anchors
por: Huang, Zenan, et al.
Publicado: (2025)

WebAnchor: Anchoring Agent Planning to Stabilize Long-Horizon Web Reasoning
por: Yu, Xinmiao, et al.
Publicado: (2026)

Gradient-Controlled Decoding: A Safety Guardrail for LLMs with Dual-Anchor Steering
por: Chiniya, Purva, et al.
Publicado: (2026)

Chinese Word Boundary Recovery through Character Alignment Projection
por: Wang, Lusha, et al.
Publicado: (2026)

Adaptive Preference Optimization with Uncertainty-aware Utility Anchor
por: Wang, Xiaobo, et al.
Publicado: (2025)

Rethinking Attention Output Projection: Structured Hadamard Transforms for Efficient Transformers
por: Aggarwal, Shubham, et al.
Publicado: (2026)

AnchorMem: Anchored Facts with Associative Contexts for Building Memory in Large Language Models
por: Shen, Zhanyu, et al.
Publicado: (2026)

ClueAnchor: Clue-Anchored Knowledge Reasoning Exploration and Optimization for Retrieval-Augmented Generation
por: Chen, Hao, et al.
Publicado: (2025)

Align-GRAG: Anchor and Rationale Guided Dual Alignment for Graph Retrieval-Augmented Generation
por: Xu, Derong, et al.
Publicado: (2025)

Aura: Universal Multi-dimensional Exogenous Integration for Aviation Time Series
por: Lin, Jiafeng, et al.
Publicado: (2026)

Griffin: Mixing Gated Linear Recurrences with Local Attention for Efficient Language Models
por: De, Soham, et al.
Publicado: (2024)

Tree Attention: Topology-aware Decoding for Long-Context Attention on GPU clusters
por: Shyam, Vasudev, et al.
Publicado: (2024)

Breaking Block Boundaries: Anchor-based History-stable Decoding for Diffusion Large Language Models
por: Zou, Shun, et al.
Publicado: (2026)

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

When Confidence Misleads: Suffix Anchoring and Anchor-Proximity Confidence Modulation for Diffusion Language Models
por: Park, Jungwon, et al.
Publicado: (2026)

Understanding Post-hoc Explainers: The Case of Anchors
por: Lopardo, Gianluigi, et al.
Publicado: (2023)

Anchor function: a type of benchmark functions for studying language models
por: Zhang, Zhongwang, et al.
Publicado: (2024)

AnchorAL: Computationally Efficient Active Learning for Large and Imbalanced Datasets
por: Lesci, Pietro, et al.
Publicado: (2024)

Information Entropy Invariance: Enhancing Length Extrapolation in Attention Mechanisms
por: Li, Kewei, et al.
Publicado: (2025)

ConvMix: A Mixed-Criteria Data Augmentation Framework for Conversational Dense Retrieval
por: Mo, Fengran, et al.
Publicado: (2025)

From Demographics to Survey Anchors: Evaluating LLM Agents for Modeling Retirement Attitudes
por: Garzón, Rubén, et al.
Publicado: (2026)