Image de couverture de livre

Any-Depth Alignment: Unlocking Innate Safety Alignment of LLMs to Any-Depth

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Zhang, Jiawei, Estornell, Andrew, Baek, David D., Li, Bo, Xu, Xiaojun
Format:	Preprint
Publié:	2025
Sujets:	Machine Learning Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Reasoned Safety Alignment: Ensuring Jailbreak Defense via Answer-Then-Check
par: Cao, Chentao, et autres
Publié: (2025)

Symbolic Representation for Any-to-Any Generative Tasks
par: Chen, Jiaqi, et autres
Publié: (2025)

MixEval-X: Any-to-Any Evaluations from Real-World Data Mixtures
par: Ni, Jinjie, et autres
Publié: (2024)

Self-Evaluation Unlocks Any-Step Text-to-Image Generation
par: Yu, Xin, et autres
Publié: (2025)

AR-Omni: A Unified Autoregressive Model for Any-to-Any Generation
par: Cheng, Dongjie, et autres
Publié: (2026)

NExT-GPT: Any-to-Any Multimodal LLM
par: Wu, Shengqiong, et autres
Publié: (2023)

Multimodal Crystal Flow: Any-to-Any Modality Generation for Unified Crystal Modeling
par: Seong, Kiyoung, et autres
Publié: (2026)

AnyFit: Controllable Virtual Try-on for Any Combination of Attire Across Any Scenario
par: Li, Yuhan, et autres
Publié: (2024)

Why Deep Jacobian Spectra Separate: Depth-Induced Scaling and Singular-Vector Alignment
par: Haas, Nathanaël, et autres
Publié: (2026)

Any-Way Meta Learning
par: Lee, Junhoo, et autres
Publié: (2024)

Forgetting Any Data at Any Time: A Theoretically Certified Unlearning Framework for Vertical Federated Learning
par: Wang, Linian, et autres
Publié: (2025)

ChatScene: Knowledge-Enabled Safety-Critical Scenario Generation for Autonomous Vehicles
par: Zhang, Jiawei, et autres
Publié: (2024)

Unifying Sequences, Structures, and Descriptions for Any-to-Any Protein Generation with the Large Multimodal Model HelixProtX
par: Chen, Zhiyuan, et autres
Publié: (2024)

AnyBCQ: Hardware Efficient Flexible Binary-Coded Quantization for Multi-Precision LLMs
par: Park, Gunho, et autres
Publié: (2025)

4M-21: An Any-to-Any Vision Model for Tens of Tasks and Modalities
par: Bachmann, Roman, et autres
Publié: (2024)

How to Train a Leader: Hierarchical Reasoning in Multi-Agent LLMs
par: Estornell, Andrew, et autres
Publié: (2025)

Curriculum Learning for Safety Alignment
par: Kumar, Sandeep, et autres
Publié: (2026)

Depth-Breadth Synergy in RLVR: Unlocking LLM Reasoning Gains with Adaptive Exploration
par: Yang, Zhicheng, et autres
Publié: (2025)

Picky LLMs and Unreliable RMs: An Empirical Study on Safety Alignment after Instruction Tuning
par: Li, Guanlin, et autres
Publié: (2025)

Depth Any Camera: Zero-Shot Metric Depth Estimation from Any Camera
par: Guo, Yuliang, et autres
Publié: (2025)

Time Matters: Scaling Laws for Any Budget
par: Inbar, Itay, et autres
Publié: (2024)

AnyGraph: Graph Foundation Model in the Wild
par: Xia, Lianghao, et autres
Publié: (2024)

Distribution-Based Feature Attribution for Explaining the Predictions of Any Classifier
par: Li, Xinpeng, et autres
Publié: (2025)

Depth Anything at Any Condition
par: Sun, Boyuan, et autres
Publié: (2025)

A2D: Any-Order, Any-Step Safety Alignment for Diffusion Language Models
par: Jeung, Wonje, et autres
Publié: (2025)

Safe Transformer: An Explicit Safety Bit For Interpretable And Controllable Alignment
par: Feng, Jingyuan, et autres
Publié: (2026)

The Blessing and Curse of Dimensionality in Safety Alignment
par: Teo, Rachel S. Y., et autres
Publié: (2025)

SoSBench: Benchmarking Safety Alignment on Six Scientific Domains
par: Jiang, Fengqing, et autres
Publié: (2025)

Alignment and Safety in Large Language Models: Safety Mechanisms, Training Paradigms, and Emerging Challenges
par: Lu, Haoran, et autres
Publié: (2025)

Efficiency vs. Alignment: Investigating Safety and Fairness Risks in Parameter-Efficient Fine-Tuning of LLMs
par: Taraghi, Mina, et autres
Publié: (2025)

Safe Pruning LoRA: Robust Distance-Guided Pruning for Safety Alignment in Adaptation of LLMs
par: Ao, Shuang, et autres
Publié: (2025)

NeuronTune: Fine-Grained Neuron Modulation for Balanced Safety-Utility Alignment in LLMs
par: Pan, Birong, et autres
Publié: (2025)

BSO: Safety Alignment Is Density Ratio Matching
par: Nguyen, Tien-Phat, et autres
Publié: (2026)

CAP: Controllable Alignment Prompting for Unlearning in LLMs
par: Wang, Zhaokun, et autres
Publié: (2026)

Course-Correction: Safety Alignment Using Synthetic Preferences
par: Xu, Rongwu, et autres
Publié: (2024)

Multi-Value Alignment for LLMs via Value Decorrelation and Extrapolation
par: Xu, Hefei, et autres
Publié: (2025)

PSPO*: An Effective Process-supervised Policy Optimization for Reasoning Alignment
par: Li, Jiawei, et autres
Publié: (2024)

AmoebaLLM: Constructing Any-Shape Large Language Models for Efficient and Instant Deployment
par: Fu, Yonggan, et autres
Publié: (2024)

Test-Time Safety Alignment
par: Saglam, Baturay, et autres
Publié: (2026)

Meta-Aligner: Bidirectional Preference-Policy Optimization for Multi-Objective LLMs Alignment
par: Xu, Wenzhe, et autres
Publié: (2026)