Cover Image

VSPO: Vector-Steered Policy Optimization for Behavioral Control

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhang, Xuechen, Huang, Zijian, Yang, Kai, Zhang, Weijia, Chen, Jiasi, Oymak, Samet
Format:	Preprint
Published:	2026
Subjects:	Machine Learning Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Efficient Contextual LLM Cascades through Budget-Constrained Policy Learning
by: Zhang, Xuechen, et al.
Published: (2024)

Selective Attention: Enhancing Transformer through Principled Context Control
by: Zhang, Xuechen, et al.
Published: (2024)

SmartChunk Retrieval: Query-Aware Chunk Compression with Planning for Efficient Document RAG
by: Zhang, Xuechen, et al.
Published: (2025)

Class-attribute Priors: Adapting Optimization to Heterogeneity and Fairness Objective
by: Zhang, Xuechen, et al.
Published: (2024)

On the Power of Convolution Augmented Transformer
by: Li, Mingchen, et al.
Published: (2024)

BREAD: Branched Rollouts from Expert Anchors Bridge SFT & RL for Reasoning
by: Zhang, Xuechen, et al.
Published: (2025)

Making Small Language Models Efficient Reasoners: Intervention, Supervision, Reinforcement
by: Zhang, Xuechen, et al.
Published: (2025)

Transformers as Support Vector Machines
by: Tarzanagh, Davoud Ataee, et al.
Published: (2023)

Attention with Trained Embeddings Provably Selects Important Tokens
by: Wu, Diyuan, et al.
Published: (2025)

Personalized Steering of Large Language Models: Versatile Steering Vectors Through Bi-directional Preference Optimization
by: Cao, Yuanpu, et al.
Published: (2024)

Fine-grained Analysis of In-context Linear Estimation: Data, Architecture, and Beyond
by: Li, Yingcong, et al.
Published: (2024)

Beyond Steering Vector: Flow-based Activation Steering for Inference-Time Intervention
by: Jin, Zehao, et al.
Published: (2026)

From Self-Attention to Markov Models: Unveiling the Dynamics of Generative Transformers
by: Ildiz, M. Emrullah, et al.
Published: (2024)

Predicting Where Steering Vectors Succeed
by: Billa, Jayadev
Published: (2026)

Mechanics of Next Token Prediction with Self-Attention
by: Li, Yingcong, et al.
Published: (2024)

Evolutionary Multi-Task Optimization for LLM-Guided Program Discovery
by: Gozeten, Halil Alperen, et al.
Published: (2026)

Beyond Multiple Choice: Evaluating Steering Vectors for Summarization
by: Braun, Joschka, et al.
Published: (2025)

White-Box Sensitivity Auditing with Steering Vectors
by: Cyberey, Hannah, et al.
Published: (2026)

Gating is Weighting: Understanding Gated Linear Attention through In-context Learning
by: Li, Yingcong, et al.
Published: (2025)

When and How Unlabeled Data Provably Improve In-Context Learning
by: Li, Yingcong, et al.
Published: (2025)

Latent Chain-of-Thought Improves Structured-Data Transformers
by: Dudley, Carson, et al.
Published: (2026)

RetrievalAttention: Accelerating Long-Context LLM Inference via Vector Retrieval
by: Liu, Di, et al.
Published: (2024)

Steer2Adapt: Dynamically Composing Steering Vectors Elicits Efficient Adaptation of LLMs
by: Han, Pengrui, et al.
Published: (2026)

Behavioral Steering in a 35B MoE Language Model via SAE-Decoded Probe Vectors: One Agency Axis, Not Five Traits
by: Yap, Jia Qing
Published: (2026)

GAGPO: Generalized Advantage Grouped Policy Optimization
by: Zhu, Siyuan, et al.
Published: (2026)

Understanding and Steering the Cognitive Behaviors of Reasoning Models at Test-Time
by: Zhang, Zhenyu, et al.
Published: (2025)

In-context Vectors: Making In Context Learning More Effective and Controllable Through Latent Space Steering
by: Liu, Sheng, et al.
Published: (2023)

Improving Steering Vectors by Targeting Sparse Autoencoder Features
by: Chalnev, Sviatoslav, et al.
Published: (2024)

Shifting Perspectives: Steering Vectors for Robust Bias Mitigation in LLMs
by: Siddique, Zara, et al.
Published: (2025)

ROAST: Rollout-based On-distribution Activation Steering Technique
by: Su, Xuanbo, et al.
Published: (2026)

Test-Time Training Provably Improves Transformers as In-context Learners
by: Gozeten, Halil Alperen, et al.
Published: (2025)

Vector Policy Optimization: Training for Diversity Improves Test-Time Search
by: Bahlous-Boldi, Ryan, et al.
Published: (2026)

No Training Wheels: Steering Vectors for Bias Correction at Inference Time
by: Gupta, Aviral, et al.
Published: (2025)

DSO: Direct Steering Optimization for Bias Mitigation
by: Paes, Lucas Monteiro, et al.
Published: (2025)

Beyond Prompt Engineering: Robust Behavior Control in LLMs via Steering Target Atoms
by: Wang, Mengru, et al.
Published: (2025)

Soft Adaptive Policy Optimization
by: Gao, Chang, et al.
Published: (2025)

Agentic Reinforced Policy Optimization
by: Dong, Guanting, et al.
Published: (2025)

Stabilizing Policy Optimization via Logits Convexity
by: Chen, Hongzhan, et al.
Published: (2026)

Enabling Intrinsic Reasoning over Dense Geospatial Embeddings with DFR-Gemma
by: Zhang, Xuechen, et al.
Published: (2026)

HTPO: Towards Exploration-Exploitation Balanced Policy Optimization via Hierarchical Token-level Objective Control
by: Yao, Xincheng, et al.
Published: (2026)