相关论文: Improving Aviation Safety Analysis: Automated HFAC…

Large Language Models (LLMs) are increasingly applied in healthcare, yet ensuring their ethical integrity and safety compliance remains a major barrier to clinical deployment. This work introduces a multi-agent refinement framework designed…

Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as a promising paradigm for post-training reasoning models. However, group-based methods such as Group Relative Policy Optimization (GRPO) face a critical dilemma in…

Reinforcement learning from human feedback (RLHF) typically assumes a static or non-strategic reward model (RM). In iterative deployment, however, the policy generates the data on which the RM is retrained, creating a feedback loop.…

Building speech deepfake detection models that are generalizable to unseen attacks remains a challenging problem. Although the field has shifted toward a pre-training and fine-tuning paradigm using speech foundation models, most approaches…

Multi-Agent Systems (MAS) excel at accomplishing complex objectives through the collaborative efforts of individual agents. Among the methodologies employed in MAS, Multi-Agent Reinforcement Learning (MARL) stands out as one of the most…

Reinforcement Learning from Human Feedback (RLHF) plays a crucial role in aligning large language models (LLMs) with human values and preferences. However, the quality and stability of the trained reward model largely determine the final…

Large language model (LLM) alignment via reinforcement learning from human preferences (RLHF) suffers from unstable policy updates, ambiguous gradient directions, poor interpretability, and high gradient variance in mainstream pairwise…

While Multimodal Large Language Models (MLLMs) demonstrate remarkable capabilities across diverse domains, their application to specialized anomaly detection (AD) remains constrained by domain adaptation challenges. Existing Group Relative…

DevOps is a necessity in many industries, including the development of Autonomous Vehicles. In those settings, there are iterative activities that reduce the speed of SafetyOps cycles. One of these activities is "Hazard Analysis & Risk…

Short-term prediction (nowcasting) of low-visibility and precipitation events is critical for aviation safety and operational efficiency. Current operational approaches rely on computationally intensive numerical weather prediction guidance…

Hyperparameter optimization (HPO) plays a critical role in improving model performance. Transformer-based HPO methods have shown great potential; however, existing approaches rely heavily on large-scale historical optimization trajectories…

Policy optimization for large language models often suffers from sparse reward signals in multi-step reasoning tasks. Critic-free methods like GRPO assign a single normalized outcome reward to all tokens, providing limited guidance for…

Large Language Models increasingly power critical infrastructure from healthcare to finance, yet their vulnerability to adversarial manipulation threatens system integrity and user safety. Despite growing deployment, no comprehensive…

Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as a promising approach to improve the reasoning abilities of Large Language Models (LLMs). Among RLVR algorithms, Group Relative Policy Optimization (GRPO) and its variants…

Group-Relative Policy Optimization (GRPO) has emerged as an efficient paradigm for aligning Large Language Models (LLMs), yet its efficacy is primarily confined to domains with verifiable ground truths. Extending GRPO to open-domain…

As Large Language Models (LLMs) have become integral to both research and daily operations, rigorous evaluation is crucial. This assessment is important not only for individual tasks but also for understanding their societal impact and…

We introduce Adversarial Policy Optimization (AdvPO), a novel solution to the pervasive issue of reward over-optimization in Reinforcement Learning from Human Feedback (RLHF) for Large Language Models (LLMs). Over-optimization occurs when a…

With the rapid advancement of large language models (LLMs), their robustness against adversarial manipulations, particularly jailbreak backdoor attacks, has become critically important. Existing approaches to embedding jailbreak…

This paper proposes a GRPO-based approach to enhance the performance of large language model (LLM)-based text-to-speech (TTS) models by deriving rewards from an off-the-shelf automatic speech recognition (ASR) model. Compared to previous…

Effectively managing Air Traffic Control Officer (ATCO) workload is crucial in maintaining operational safety. Group supervisors use tools that estimate upcoming traffic load to aid decision-making. However, industry-standard models can…