Related papers: AURA: Affordance-Understanding and Risk-aware Alig…

Process Reward Models (PRMs) have shown promise in enhancing the mathematical reasoning capabilities of Large Language Models (LLMs) through Test-Time Scaling (TTS). However, their integration into multimodal reasoning remains largely…

Personalized alignment is crucial for enabling Large Language Models (LLMs) to engage effectively in user-centric interactions. However, current methods face a dual challenge: they fail to infer users' deep implicit preferences (including…

Instruction fine-tuning of large language models (LLMs) is a powerful method for improving task-specific performance, but it can inadvertently lead to a phenomenon where models generate harmful responses when faced with malicious prompts.…

Recent advancements in large language models (LLMs) have accelerated progress toward artificial general intelligence, yet their potential to generate harmful content poses critical safety challenges. Existing alignment methods often…

Safely aligning large language models (LLMs) often demands extensive human-labeled preference data, a process that's both costly and time-consuming. While synthetic data offers a promising alternative, current methods frequently rely on…

Fine-tuning Large Language Models (LLMs) for downstream tasks often compromises safety alignment, even when using parameter-efficient methods like LoRA. In this work, we uncover a notable property: fine-tuned models preserve the geometric…

Despite the remarkable proficiency of \textit{Large Reasoning Models} (LRMs) in handling complex reasoning tasks, their reliability in safety-critical scenarios remains uncertain. Existing evaluations primarily assess response-level safety,…

Although Large Language Models (LLMs) exhibit advanced reasoning ability, conventional alignment remains largely dominated by outcome reward models (ORMs) that judge only final answers. Process Reward Models(PRMs) address this gap by…

Reward models (RMs) are essential for aligning large language models (LLM) with human expectations. However, existing RMs struggle to capture the stochastic and uncertain nature of human preferences and fail to assess the reliability of…

Large Language Models (LLMs) have achieved tremendous success in various tasks, yet concerns about their safety and security have emerged. In particular, they pose risks of generating harmful content and are vulnerable to jailbreaking…

Process Reward Models (PRMs) have emerged as a promising approach to enhance the reasoning capabilities of large language models (LLMs) by guiding their step-by-step reasoning toward a final answer. However, existing PRMs either treat each…

Autonomous highway driving demands a critical balance between proactive, efficiency-seeking behavior and robust safety guarantees. This paper proposes Language Action-guided Reinforcement Learning (LA-RL) with Safety Guarantees, a novel…

Reasoning about failures is crucial for building reliable and trustworthy robotic systems. Prior approaches either treat failure reasoning as a closed-set classification problem or assume access to ample human annotations. Failures in the…

Reliable reward models (RMs) are critical for ensuring the safe alignment of large language models (LLMs). However, current RM evaluation methods focus solely on preference perception accuracies in given specific scenarios, obscuring the…

With the rapid development of Large Language Models (LLMs), aligning these models with human preferences and values is critical to ensuring ethical and safe applications. However, existing alignment techniques such as RLHF or DPO often…

Large language models (LLMs) exhibit strong reasoning capabilities when guided by high-quality demonstrations, yet such data is often distributed across organizations that cannot centralize it due to regulatory, proprietary, or…

Large Language Models (LLMs) demonstrate transformative potential, yet their reasoning remains inconsistent and unreliable. Reinforcement learning (RL)-based fine-tuning is a key mechanism for improvement, but its effectiveness is…

Multimodal language models (MLMs) still face challenges in fundamental visual perception tasks where specialized models excel. Tasks requiring reasoning about 3D structures benefit from depth estimation, and reasoning about 2D object…

Aligning large language models (LLMs) to diverse human preferences is fundamentally challenging since criteria can often conflict with each other. Inference-time alignment methods have recently gained popularity as they allow LLMs to be…

Process Reward Models (PRMs) are rapidly becoming the backbone of LLM reasoning pipelines, yet we demonstrate that state-of-the-art PRMs are systematically exploitable under adversarial optimization pressure. To address this, we introduce a…