相关论文: ReLAPSe: Reinforcement-Learning-trained Adversaria…

The development of autonomous agents for complex, long-horizon tasks is a central goal in AI. However, dominant training paradigms face a critical limitation: reinforcement learning (RL) methods that optimize solely for final task success…

Reinforcement learning (RL) for large language model reasoning is frequently hindered by signal loss, a phenomenon where standard uniform sampling with small group sizes fails to uncover informative learning signals for difficult prompts.…

Recent advances in text-to-video (T2V) diffusion models have significantly enhanced the quality of generated videos. However, their capability to produce explicit or harmful content introduces new challenges related to misuse and potential…

Concept erasure techniques for text-to-video (T2V) diffusion models report substantial suppression of sensitive content, yet current evaluation is limited to checking whether the target concept is absent from generated frames, treating…

Reinforcement learning (RL) has achieved remarkable success in fields like robotics and autonomous driving, but adversarial attacks designed to mislead RL systems remain challenging. Existing approaches often rely on modifying the…

Federated Learning is a promising paradigm for privacy-preserving collaborative model training. In practice, it is essential not only to continuously train the model to acquire new knowledge but also to guarantee old knowledge the right to…

This work tackles an intriguing and fundamental open challenge in representation learning: Given a well-trained deep learning model, can it be reprogrammed to enhance its robustness against adversarial or noisy input perturbations without…

Modern neural models trained on textual data rely on pre-trained representations that emerge without direct supervision. As these representations are increasingly being used in real-world applications, the inability to \emph{control} their…

Deep learning based image classification models are shown vulnerable to adversarial attacks by injecting deliberately crafted noises to clean images. To defend against adversarial attacks in a training-free and attack-agnostic manner, this…

Intelligent agents must pursue their goals in complex environments with partial information and often limited computational capacity. Reinforcement learning methods have achieved great success by creating agents that optimize engineered…

Despite the remarkable generation capabilities of diffusion models, recent studies have shown that they can memorize and create harmful content when given specific text prompts. Although fine-tuning approaches have been developed to…

As large language models (LLMs) are increasingly deployed across various applications, privacy and copyright concerns have heightened the need for more effective LLM unlearning techniques. Many existing unlearning methods aim to suppress…

Insensitivity to semantically-preserving variations of prompts (paraphrases) is crucial for reliable behavior and real-world deployment of large language models. However, language models exhibit significant performance degradation when…

Diffusion models are a class of flexible generative models trained with an approximation to the log-likelihood objective. However, most use cases of diffusion models are not concerned with likelihoods, but instead with downstream objectives…

Large Reasoning Models possess remarkable capabilities for self-correction in general domain; however, they frequently struggle to recover from unsafe reasoning trajectories under adversarial attacks. Existing alignment methods attempt to…

Reinforcement learning algorithms in multi-agent systems deliver highly resilient and adaptable solutions for common problems in telecommunications,aerospace, and industrial robotics. However, achieving an optimal global goal remains a…

With the rapid advancement of remote sensing technology, super-resolution image reconstruction is of great research and practical significance. Existing deep learning methods have made progress but still face limitations in handling complex…

Transfer learning from pretrained language models recently became the dominant approach for solving many NLP tasks. A common approach to transfer learning for multiple tasks that maximize parameter sharing trains one or more task-specific…

We propose a novel computational strategy for de novo design of molecules with desired properties termed ReLeaSE (Reinforcement Learning for Structural Evolution). Based on deep and reinforcement learning approaches, ReLeaSE integrates two…

Unlearning seeks to remove specific knowledge from large language models (LLMs), but its effectiveness remains contested. On one side, "forgotten" knowledge can often be recovered through interventions such as light fine-tuning; on the…