Related papers: Adversary-Aware DPO: Enhancing Safety Alignment in…

Reinforcement Learning (RL) has emerged as a central paradigm for advancing Large Language Models (LLMs), where pre-training and RL post-training share the same log-likelihood formulation. In contrast, recent RL approaches for diffusion…

As large language models (LLMs) become more capable, fine-tuning techniques for aligning with human intent are increasingly important. A key consideration for aligning these models is how to most effectively use human resources, or model…

Adversarial examples derived from deliberately crafted perturbations on visual inputs can easily harm decision process of deep neural networks. To prevent potential threats, various adversarial training-based defense methods have grown…

Reinforcement learning (RL) has shown strong performance in LLM post-training, but real-world deployment often involves noisy or incomplete supervision. In such settings, complex and unreliable supervision signals can destabilize training…

Trajectory prediction is essential for autonomous vehicles (AVs) to plan correct and safe driving behaviors. While many prior works aim to achieve higher prediction accuracy, few study the adversarial robustness of their methods. To bridge…

As powerful Large Language Models (LLMs) are now widely used for numerous practical applications, their safety is of critical importance. While alignment techniques have significantly improved overall safety, LLMs remain vulnerable to…

DPO has become a widely adopted alternative to RLHF for aligning LLMs with human preferences, eliminating the need for a separate reward model or RL loop. Recent theoretical analysis uncovers an asymmetric gradient behavior in DPO: the loss…

Direct Preference Optimization (DPO) has been widely adopted for preference alignment of Large Language Models (LLMs) due to its simplicity and effectiveness. However, DPO is derived as a bandit problem in which the whole response is…

To guarantee safe and robust deployment of large language models (LLMs) at scale, it is critical to accurately assess their adversarial robustness. Existing adversarial attacks typically target harmful responses in single-point greedy…

Improving and understanding the training dynamics and reasoning of Large Language Models (LLMs) has become essential for their deployment in AI-based security tools, such as software vulnerability detection. In this work, we present an…

Vision-Language-Action models (VLAs) have recently demonstrated remarkable progress in embodied environments, enabling robots to perceive, reason, and act through unified multimodal understanding. Despite their impressive capabilities, the…

Large Reasoning Models (LRMs) have demonstrated remarkable capabilities in complex problem-solving through Chain-of-Thought (CoT) reasoning. However, the multi-step nature of CoT introduces new safety challenges that extend beyond…

Large Language Model (LLM) agents can leverage tools such as Google Search to complete complex tasks. However, this tool usage introduces the risk of indirect prompt injections, where malicious instructions hidden in tool outputs can…

Visual preference alignment involves training Large Vision-Language Models (LVLMs) to predict human preferences between visual inputs. This is typically achieved by using labeled datasets of chosen/rejected pairs and employing optimization…

Large visual language models (LVLMs) have demonstrated excellent instruction-following capabilities, yet remain vulnerable to stealthy backdoor attacks when finetuned using contaminated data. Existing backdoor defense techniques are usually…

Aligning Large Language Models (LLMs) is crucial for enhancing their safety and utility. However, existing methods, primarily based on preference datasets, face challenges such as noisy labels, high annotation costs, and privacy concerns.…

As large language models (LLMs) are increasingly applied across various domains, enhancing safety while maintaining the helpfulness of LLMs has become a critical challenge. Recent studies solve this problem through safety-constrained online…

Reinforcement learning (RL) has emerged as an effective approach for enhancing the reasoning capabilities of large language models (LLMs), especially in scenarios where supervised fine-tuning (SFT) falls short due to limited…

Large pre-trained Vision-Language Models (VLMs) such as Contrastive Language-Image Pre-training (CLIP) have been shown to be susceptible to adversarial attacks, raising concerns about their deployment in safety-critical applications like…

The rapid development of large language models (LLMs) has not only provided numerous opportunities but also presented significant challenges. This becomes particularly evident when LLMs inadvertently generate harmful or toxic content,…