Cover Image

A2D: Any-Order, Any-Step Safety Alignment for Diffusion Language Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Jeung, Wonje, Yoon, Sangyeon, Cho, Yoonjun, Jeon, Dongjae, Shin, Sangwoo, Hong, Hyesoo, No, Albert
Format:	Preprint
Published:	2025
Subjects:	Computation and Language Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Few-Shot Truly Benign DPO Attack for Jailbreaking LLMs
by: Yoon, Sangyeon, et al.
Published: (2026)

VLMs Trace Without Tracking: Diagnosing Failures in Visual Path Following
by: Hong, Hyesoo, et al.
Published: (2026)

Rethinking Benign Relearning: Syntax as the Hidden Driver of Unlearning Failures
by: Yoon, Sangyeon, et al.
Published: (2026)

SAFEPATH: Preventing Harmful Reasoning in Chain-of-Thought via Early Alignment
by: Jeung, Wonje, et al.
Published: (2025)

BenchPreS: A Benchmark for Context-Aware Personalized Preference Selectivity of Persistent-Memory LLMs
by: Yoon, Sangyeon, et al.
Published: (2026)

R-TOFU: Unlearning in Large Reasoning Models
by: Yoon, Sangyeon, et al.
Published: (2025)

SEPS: A Separability Measure for Robust Unlearning in LLMs
by: Jeung, Wonje, et al.
Published: (2025)

Rainbow Padding: Mitigating Early Termination in Instruction-Tuned Diffusion LLMs
by: Kim, Bumjun, et al.
Published: (2025)

Assigning Distinct Roles to Quantized and Low-Rank Matrices Toward Optimal Weight Decomposition
by: Cho, Yoonjun, et al.
Published: (2025)

DUSK: Do Not Unlearn Shared Knowledge
by: Jeung, Wonje, et al.
Published: (2025)

An Information Theoretic Evaluation Metric For Strong Unlearning
by: Jeon, Dongjae, et al.
Published: (2024)

Preserve-Then-Quantize: Balancing Rank Budgets for Quantization Error Reconstruction in LLMs
by: Cho, Yoonjun, et al.
Published: (2026)

Large Language Models Still Exhibit Bias in Long Text
by: Jeung, Wonje, et al.
Published: (2024)

Adversarial Sample-Based Approach for Tighter Privacy Auditing in Final Model-Only Scenarios
by: Yoon, Sangyeon, et al.
Published: (2024)

A Theoretical Analysis of Why Masked Diffusion Models Mitigate the Reversal Curse
by: Jeon, Moongyu, et al.
Published: (2026)

DSG-KD: Knowledge Distillation from Domain-Specific to General Language Models
by: Cho, Sangyeon, et al.
Published: (2024)

Multi-Level Knowledge Distillation and Dynamic Self-Supervised Learning for Continual Learning
by: Kim, Taeheon, et al.
Published: (2025)

One Adapts to Any: Meta Reward Modeling for Personalized LLM Alignment
by: Cai, Hongru, et al.
Published: (2026)

ConCSE: Unified Contrastive Learning and Augmentation for Code-Switched Embeddings
by: Jeon, Jangyeong, et al.
Published: (2024)

ReasonAny: Incorporating Reasoning Capability to Any Model via Simple and Effective Model Merging
by: Yang, Junyao, et al.
Published: (2026)

Any-Depth Alignment: Unlocking Innate Safety Alignment of LLMs to Any-Depth
by: Zhang, Jiawei, et al.
Published: (2025)

NExT-GPT: Any-to-Any Multimodal LLM
by: Wu, Shengqiong, et al.
Published: (2023)

AR-Omni: A Unified Autoregressive Model for Any-to-Any Generation
by: Cheng, Dongjie, et al.
Published: (2026)

The Emergence of Abstract Thought in Large Language Models Beyond Any Language
by: Chen, Yuxin, et al.
Published: (2025)

MUG-Eval: A Proxy Evaluation Framework for Multilingual Generation Capabilities in Any Language
by: Song, Seyoung, et al.
Published: (2025)

BioBridge: Unified Bio-Embedding with Bridging Modality in Code-Switched EMR
by: Jeon, Jangyeong, et al.
Published: (2024)

AnyFlow: Any-Step Video Diffusion Model with On-Policy Flow Map Distillation
by: Gu, Yuchao, et al.
Published: (2026)

Information-Theoretic Discrete Diffusion
by: Jeon, Moongyu, et al.
Published: (2025)

Unaligning Everything: Or Aligning Any Text to Any Image in Multimodal Models
by: Salman, Shaeke, et al.
Published: (2024)

Understanding and Mitigating Memorization in Generative Models via Sharpness of Probability Landscapes
by: Jeon, Dongjae, et al.
Published: (2024)

AnyMatch -- Efficient Zero-Shot Entity Matching with a Small Language Model
by: Zhang, Zeyu, et al.
Published: (2024)

NExT-OMNI: Towards Any-to-Any Omnimodal Foundation Models with Discrete Flow Matching
by: Luo, Run, et al.
Published: (2025)

Non-linear Interventions on Large Language Models
by: Kim, Sangwoo
Published: (2026)

Navigation with VLM framework: Towards Going to Any Language
by: Yin, Zecheng, et al.
Published: (2024)

Any2Point: Empowering Any-modality Large Models for Efficient 3D Understanding
by: Tang, Yiwen, et al.
Published: (2024)

STEPER: Step-wise Knowledge Distillation for Enhancing Reasoning Ability in Multi-Step Retrieval-Augmented Language Models
by: Lee, Kyumin, et al.
Published: (2025)

MoBiQuant: Mixture-of-Bits Quantization for Token-Adaptive Any-Precision LLM
by: Wang, Dongwei, et al.
Published: (2026)

SLM as Guardian: Pioneering AI Safety with Small Language Models
by: Kwon, Ohjoon, et al.
Published: (2024)

Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution
by: Wang, Peng, et al.
Published: (2024)

Unforgotten Safety: Preserving Safety Alignment of Large Language Models with Continual Learning
by: Alssum, Lama, et al.
Published: (2025)