Cover Image

Indirect Attention: Turning Context Misalignment into a Feature

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Bahaduri, Bissmella, Talaoubrid, Hicham, Feng, Fangchen, Ming, Zuheng, Mokraoui, Anissa
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Interactive Masked Image Modeling for Multimodal Object Detection in Remote Sensing
by: Vu, Minh-Duc, et al.
Published: (2024)

Multimodal Transformer Using Cross-Channel attention for Object Detection in Remote Sensing Images
by: Bahaduri, Bissmella, et al.
Published: (2023)

Analyzing the Impact of Low-Rank Adaptation for Cross-Domain Few-Shot Object Detection in Aerial Images
by: Talaoubrid, Hicham, et al.
Published: (2025)

Efficient Image Compression Using Advanced State Space Models
by: Arezki, Bouzid, et al.
Published: (2024)

Universal End-to-End Neural Network for Lossy Image Compression
by: Arezki, Bouzid, et al.
Published: (2024)

Convolutional Transformer-Based Image Compression
by: Arezki, Bouzid, et al.
Published: (2024)

Understanding Emergent Misalignment via Feature Superposition Geometry
by: Minegishi, Gouki, et al.
Published: (2026)

Unraveling Indirect In-Context Learning Using Influence Functions
by: Askari, Hadi, et al.
Published: (2025)

TED: Turn Emphasis with Dialogue Feature Attention for Emotion Recognition in Conversation
by: Ono, Junya, et al.
Published: (2025)

Overtrained, Not Misaligned
by: Schreiber, Joel, et al.
Published: (2026)

Body Transformer: Leveraging Robot Embodiment for Policy Learning
by: Sferrazza, Carmelo, et al.
Published: (2024)

Model Organisms for Emergent Misalignment
by: Turner, Edward, et al.
Published: (2025)

Subgroups Matter for Robust Bias Mitigation
by: Alloula, Anissa, et al.
Published: (2025)

Convergent Linear Representations of Emergent Misalignment
by: Soligo, Anna, et al.
Published: (2025)

Misalignment from Treating Means as Ends
by: Marklund, Henrik, et al.
Published: (2025)

Emergence of Minimal Circuits for Indirect Object Identification in Attention-Only Transformers
by: Adhikari, Rabin
Published: (2025)

Scaling Context Requires Rethinking Attention
by: Gelada, Carles, et al.
Published: (2025)

Extending Test-Time Scaling: A 3D Perspective with Context, Batch, and Turn
by: Yu, Chao, et al.
Published: (2025)

LLM Misalignment via Adversarial RLHF Platforms
by: Entezami, Erfan, et al.
Published: (2025)

ACCon: Angle-Compensated Contrastive Regularizer for Deep Regression
by: Zhao, Botao, et al.
Published: (2025)

Persona Features Control Emergent Misalignment
by: Wang, Miles, et al.
Published: (2025)

Scaling Attention via Feature Sparsity
by: Xie, Yan, et al.
Published: (2026)

Representation Invariance and Allocation: When Subgroup Balance Matters
by: Alloula, Anissa, et al.
Published: (2025)

Long-Context Attention Benchmark: From Kernel Efficiency to Distributed Context Parallelism
by: Bu, Tao, et al.
Published: (2025)

In-Training Defenses against Emergent Misalignment in Language Models
by: Kaczér, David, et al.
Published: (2025)

Singular Vectors of Attention Heads Align with Features
by: Franco, Gabriel, et al.
Published: (2026)

Paged Attention Meets FlexAttention: Unlocking Long-Context Efficiency in Deployed Inference
by: Joshi, Thomas, et al.
Published: (2025)

Attention in Constant Time: Vashista Sparse Attention for Long-Context Decoding with Exponential Guarantees
by: Nobaub, Vashista
Published: (2026)

Superiority of Multi-Head Attention in In-Context Linear Regression
by: Cui, Yingqian, et al.
Published: (2024)

Beyond Prior Limits: Addressing Distribution Misalignment in Particle Filtering
by: Shi, Yiwei, et al.
Published: (2025)

Preemptive Detection and Steering of LLM Misalignment via Latent Reachability
by: Karnik, Sathwik, et al.
Published: (2025)

RACE Attention: A Strictly Linear-Time Attention Layer for Training on Outrageously Large Contexts
by: Joshi, Sahil, et al.
Published: (2025)

DH-RAG: A Dynamic Historical Context-Powered Retrieval-Augmented Generation Method for Multi-Turn Dialogue
by: Zhang, Feiyuan, et al.
Published: (2025)

Out-of-Domain Intent Detection Considering Multi-Turn Dialogue Contexts
by: Lang, Hao, et al.
Published: (2023)

Orion-Bix: Bi-Axial Attention for Tabular In-Context Learning
by: Bouadi, Mohamed, et al.
Published: (2025)

Self-Attention Mechanism in Multimodal Context for Banking Transaction Flow
by: Delestre, Cyrile, et al.
Published: (2024)

MKA: Memory-Keyed Attention for Efficient Long-Context Reasoning
by: Liu, Dong, et al.
Published: (2026)

Shared Parameter Subspaces and Cross-Task Linearity in Emergently Misaligned Behavior
by: Arturi, Daniel Aarao Reis, et al.
Published: (2025)

Decomposing Behavioral Phase Transitions in LLMs: Order Parameters for Emergent Misalignment
by: Arnold, Julian, et al.
Published: (2025)

From Narrow Unlearning to Emergent Misalignment: Causes, Consequences, and Containment in LLMs
by: Mushtaq, Erum, et al.
Published: (2025)