Imagen de Portada

ODESteer: A Unified ODE-Based Steering Framework for LLM Alignment

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Zhao, Hongjue, Sun, Haosen, Kong, Jiangtao, Li, Xiaochang, Wang, Qineng, Jiang, Liwei, Zhu, Qi, Abdelzaher, Tarek, Choi, Yejin, Li, Manling, Shao, Huajie
Formato:	Preprint
Publicado:	2026
Materias:	Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Understanding the Theoretical Foundations of Deep Neural Networks through Differential Equations
por: Zhao, Hongjue, et al.
Publicado: (2026)

NetBench: A Large-Scale and Comprehensive Network Traffic Benchmark Dataset for Foundation Models
por: Qian, Chen, et al.
Publicado: (2024)

WestWorld: A Knowledge-Encoded Scalable Trajectory World Model for Diverse Robotic Systems
por: Wang, Yuchen, et al.
Publicado: (2026)

Word Embeddings Are Steers for Language Models
por: Han, Chi, et al.
Publicado: (2023)

Lens: A Knowledge-Guided Foundation Model for Network Traffic
por: Li, Xiaochang, et al.
Publicado: (2024)

Polarization Detection on Social Networks: dual contrastive objectives for Self-supervision
por: Cui, Hang, et al.
Publicado: (2024)

Unsupervised node clustering via contrastive hard sampling
por: Cui, Hang, et al.
Publicado: (2024)

Virtual Node Generation for Node Classification in Sparsely-Labeled Graphs
por: Cui, Hang, et al.
Publicado: (2024)

Scalable Neural Symbolic Regression using Control Variables
por: Chu, Xieting, et al.
Publicado: (2023)

P3SL: Personalized Privacy-Preserving Split Learning on Heterogeneous Edge Devices
por: Fan, Wei, et al.
Publicado: (2025)

Dywave: Event-Aligned Dynamic Tokenization for Heterogeneous IoT Sensing Signals
por: Kimura, Tomoyoshi, et al.
Publicado: (2026)

Metabolic Reprogramming in Endometrium During Menstrual Cycle and Its Relationship to Infertility
por: Mohammad H. Abdelzaher, et al.
Publicado: (2026)

SENTINEL: A Multi-Level Formal Framework for Safety Evaluation of Foundation Model-based Embodied Agents
por: Zhan, Simon Sinong, et al.
Publicado: (2025)

A Generalizable Physics-Enhanced State Space Model for Long-Term Dynamics Forecasting in Complex Environments
por: Wang, Yuchen, et al.
Publicado: (2025)

DailyDilemmas: Revealing Value Preferences of LLMs with Quandaries of Daily Life
por: Chiu, Yu Ying, et al.
Publicado: (2024)

SPAR: Self-supervised Placement-Aware Representation Learning for Distributed Sensing
por: Chen, Yizhuo, et al.
Publicado: (2025)

Can Language Models Reason about Individualistic Human Values and Preferences?
por: Jiang, Liwei, et al.
Publicado: (2024)

Hybrid Memory Replay: Blending Real and Distilled Data for Class Incremental Learning
por: Kong, Jiangtao, et al.
Publicado: (2024)

EasySteer: A Unified Framework for High-Performance and Extensible LLM Steering
por: Xu, Haolei, et al.
Publicado: (2025)

DocCHA: Towards LLM-Augmented Interactive Online diagnosis System
por: Liu, Xinyi, et al.
Publicado: (2025)

CSRAP: Enhanced Canvas Attention Scheduling for Real-Time Mission Critical Perception
por: Sakib, Md Iftekharul Islam, et al.
Publicado: (2025)

RAGEN: Understanding Self-Evolution in LLM Agents via Multi-Turn Reinforcement Learning
por: Wang, Zihan, et al.
Publicado: (2025)

CAT: Interpretable Concept-based Taylor Additive Models
por: Duong, Viet, et al.
Publicado: (2024)

Learning from Trials and Errors: Reflective Test-Time Planning for Embodied LLMs
por: Hong, Yining, et al.
Publicado: (2026)

Towards Comprehensive Benchmarking Infrastructure for LLMs In Software Engineering
por: Rodriguez-Cardenas, Daniel, et al.
Publicado: (2026)

Theory of Space: Can Foundation Models Construct Spatial Beliefs through Active Exploration?
por: Zhang, Pingyue, et al.
Publicado: (2026)

Enhancing Compositional Generalization via Compositional Feature Alignment
por: Wang, Haoxiang, et al.
Publicado: (2024)

A Unified Framework for the Evaluation of LLM Agentic Capabilities
por: Zhu, Pengyu, et al.
Publicado: (2026)

ESI-Bench: Towards Embodied Spatial Intelligence that Closes the Perception-Action Loop
por: Hong, Yining, et al.
Publicado: (2026)

Targeted Synthesis of Interpenetration‐Free Mesoporous Aromatic Frameworks by Manipulating Catalysts as Templates
por: Zihao Wang, et al.
Publicado: (2024)

FailLite: Failure-Resilient Model Serving for Resource-Constrained Edge Environments
por: Wu, Li, et al.
Publicado: (2025)

VAGEN: Reinforcing World Model Reasoning for Multi-Turn VLM Agents
por: Wang, Kangrui, et al.
Publicado: (2025)

RAGEN-2: Reasoning Collapse in Agentic RL
por: Wang, Zihan, et al.
Publicado: (2026)

JAMDEC: Unsupervised Authorship Obfuscation using Constrained Decoding over Small Language Models
por: Fisher, Jillian, et al.
Publicado: (2024)

Guided Path Sampling: Steering Diffusion Models Back on Track with Principled Path Guidance
por: Li, Haosen, et al.
Publicado: (2025)

Where to Steer: Input-Dependent Layer Selection for Steering Improves LLM Alignment
por: Gadgil, Soham, et al.
Publicado: (2026)

Modular Pluralism: Pluralistic Alignment via Multi-LLM Collaboration
por: Feng, Shangbin, et al.
Publicado: (2024)

Unsupervised Audio-Visual Segmentation with Modality Alignment
por: Bhosale, Swapnil, et al.
Publicado: (2024)

Output‐Feedback Control for a Class of Sampled‐Data ODE‐PDE Systems
por: Tarek Ahmed‐Ali, et al.
Publicado: (2025)

PASS: Private Attributes Protection with Stochastic Data Substitution
por: Chen, Yizhuo, et al.
Publicado: (2025)