PIXEL: Adaptive Steering Via Position-wise Injection with eXact Estimated Levels under Subspace Calibration

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Yu, Manjiang, Li, Hongji, Singh, Priyanka, Li, Xue, Wang, Di, Hu, Lijie
Format:	Preprint
Published:	2025
Subjects:	Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Multi-Adapter Representation Interventions via Energy Calibration
by: Yu, Manjiang, et al.
Published: (2026)

Towards Reasoning-Preserving Unlearning in Multimodal Large Language Models
by: Li, Hongji, et al.
Published: (2025)

Adaptive Token-Weighted Differential Privacy for LLMs: Not All Tokens Require Equal Protection
by: Yu, Manjiang, et al.
Published: (2025)

Not eXactly Byzantine: Efficient and Resilient TEE-Based State Machine Replication
by: Leinweber, Marc, et al.
Published: (2025)

Adaptive Multi-Subspace Representation Steering for Attribute Alignment in Large Language Models
by: Jiang, Xinyan, et al.
Published: (2025)

High Order Reasoning for Time Critical Recommendation in Evidence-based Medicine
by: Yu, Manjiang, et al.
Published: (2024)

FaithSteer-BENCH: A Deployment-Aligned Stress-Testing Benchmark for Inference-Time Steering
by: Ding, Zikang, et al.
Published: (2026)

Global Evolutionary Steering: Refining Activation Steering Control via Cross-Layer Consistency
by: Jiang, Xinyan, et al.
Published: (2026)

Exploring the Personality Traits of LLMs through Latent Features Steering
by: Yang, Shu, et al.
Published: (2024)

Functional Subspace Watermarking for Large Language Models
by: Ding, Zikang, et al.
Published: (2026)

Reservoir Subspace Injection for Online ICA under Top-n Whitening
by: Xiao, Wenjun, et al.
Published: (2026)

DESTEIN: Navigating Detoxification of Language Models via Universal Steering Pairs and Head-wise Activation Fusion
by: Li, Yu, et al.
Published: (2024)

Understanding In-context Learning of Addition via Activation Subspaces
by: Hu, Xinyan, et al.
Published: (2025)

SpecBound: Adaptive Bounded Self-Speculation with Layer-wise Confidence Calibration
by: Wen, Zhuofan, et al.
Published: (2026)

The Constitutional Controller: Doubt-Calibrated Steering of Compliant Agents
by: Kohaut, Simon, et al.
Published: (2025)

Locate-then-edit for Multi-hop Factual Recall under Knowledge Editing
by: Zhang, Zhuoran, et al.
Published: (2024)

Mechanistic Unveiling of Transformer Circuits: Self-Influence as a Key to Model Reasoning
by: Zhang, Lin, et al.
Published: (2025)

Multi-Trait Subspace Steering to Reveal the Dark Side of Human-AI Interaction
by: Chia, Xin Wei, et al.
Published: (2026)

AnchorSteer: Self-Discovered Concept Injection for Structure-Preserving Music Editing
by: Chang, Chih-Heng, et al.
Published: (2026)

Understanding the Dynamics of Demonstration Conflict in In-Context Learning
by: Jiao, Difan, et al.
Published: (2026)

InjectRBP: Steering Large Language Model Reasoning Behavior via Pattern Injection
by: Wu, Xiuping, et al.
Published: (2026)

Block-wise Adaptive Caching for Accelerating Diffusion Policy
by: Ji, Kangye, et al.
Published: (2025)

Mechanistic Steering of LLMs Reveals Layer-wise Feature Vulnerabilities in Adversarial Settings
by: Das, Nilanjana, et al.
Published: (2026)

Towards Inference-time Category-wise Safety Steering for Large Language Models
by: Bhattacharjee, Amrita, et al.
Published: (2024)

Multimodal Classification Network Guided Trajectory Planning for Four-Wheel Independent Steering Autonomous Parking Considering Obstacle Attributes
by: Teng, Jingjia, et al.
Published: (2025)

Chain of Risk: Safety Failures in Large Reasoning Models and Mitigation via Adaptive Multi-Principle Steering
by: Li, Xiaomin, et al.
Published: (2026)

LTMSformer: A Local Trend-Aware Attention and Motion State Encoding Transformer for Multi-Agent Trajectory Prediction
by: Yan, Yixin, et al.
Published: (2025)

SARE: Sample-wise Adaptive Reasoning for Training-free Fine-grained Visual Recognition
by: Yang, Jingxiao, et al.
Published: (2026)

Beyond Scalars: Evaluating and Understanding LLM Reasoning via Geometric Progress and Stability
by: Jiang, Xinyan, et al.
Published: (2026)

MASteer: Multi-Agent Adaptive Steer Strategy for End-to-End LLM Trustworthiness Repair
by: Li, Changqing, et al.
Published: (2025)

Controlling Repetition in Protein Language Models
by: Zhang, Jiahao, et al.
Published: (2026)

Uncertainty Calibration with Energy Based Instance-wise Scaling in the Wild Dataset
by: Kim, Mijoo, et al.
Published: (2024)

Risk Awareness Injection: Calibrating Vision-Language Models for Safety without Compromising Utility
by: Wang, Mengxuan, et al.
Published: (2026)

Intruding with Words: Towards Understanding Graph Injection Attacks at the Text Level
by: Lei, Runlin, et al.
Published: (2024)

rSIM: Incentivizing Reasoning Capabilities of LLMs via Reinforced Strategy Injection
by: Chen, Sijia, et al.
Published: (2025)

Adaptive Budget Allocation for Orthogonal-Subspace Adapter Tuning in LLMs Continual Learning
by: Wan, Zhiyi, et al.
Published: (2025)

Latent Reward Steering: An Adaptive Inference-Time Framework that Implicitly Promotes Cognitive Behaviors in Reasoning LLMs
by: Li, Jiakang, et al.
Published: (2026)

In-Run Data Shapley for Adam Optimizer
by: Ding, Meng, et al.
Published: (2026)

Multi-hop Question Answering under Temporal Knowledge Editing
by: Cheng, Keyuan, et al.
Published: (2024)

Navigating the Black Box: Leveraging LLMs for Effective Text-Level Graph Injection Attacks
by: Lyu, Yuefei, et al.
Published: (2025)