Related papers: Step-Wise Refusal Dynamics in Autoregressive and D…

Remote sensing image segmentation faces persistent challenges in distinguishing morphologically similar categories and adapting to diverse scene variations. While existing methods rely on implicit representation learning paradigms, they…

Diffusion Language Models (DLMs) have recently demonstrated remarkable capabilities in natural language processing tasks. However, the potential of Retrieval-Augmented Generation (RAG), which shows great successes for enhancing large…

With the growing adoption of Large Language Models (LLMs) in critical areas, ensuring their security against jailbreaking attacks is paramount. While traditional defenses primarily rely on refusing malicious prompts, recent logit-level…

The electromagnetic inverse problem has long been a research hotspot. This study aims to reverse radar view angles in synthetic aperture radar (SAR) images given a target model. Nonetheless, the scarcity of SAR data, combined with the…

Reinforcement learning from expert demonstrations has long remained a challenging research problem, and existing state-of-the-art methods using behavioral cloning plus further RL training often suffer from poor generalization, low sample…

Deep reinforcement learning (DRL) is a promising approach for developing legged locomotion skills. However, the iterative design process that is inevitable in practice is poorly supported by the default methodology. It is difficult to…

Diffusion Language Models (DLMs) promise parallel generation and bidirectional context, yet they underperform autoregressive (AR) models in both likelihood modeling and generated text quality. We identify that this performance gap arises…

The emergence of Large Language Models (LLMs) has driven rapid progress in multi-modal learning, particularly in the development of Large Vision-Language Models (LVLMs). However, existing LVLM training paradigms place excessive reliance on…

Fine-tuning safety-aligned language models for downstream tasks often leads to substantial degradation of refusal behavior, making models vulnerable to adversarial misuse. While prior work has shown that safety-relevant features are encoded…

Spoken Language Understanding (SLU), a core component of the task-oriented dialogue system, expects a shorter inference latency due to the impatience of humans. Non-autoregressive SLU models clearly increase the inference speed but suffer…

Training deep reinforcement learning (DRL) locomotion policies often require massive amounts of data to converge to the desired behaviour. In this regard, simulators provide a cheap and abundant source. For successful sim-to-real transfer,…

In this study, we propose a method Distributionally Robust Safe Screening (DRSS), for identifying unnecessary samples and features within a DR covariate shift setting. This method effectively combines DR learning, a paradigm aimed at…

While inference-time thinking allows Large Language Models (LLMs) to address complex problems, the extended thinking process can be unreliable or inconsistent because of the model's probabilistic nature, especially near its knowledge…

In decentralized Multi-Agent Reinforcement Learning (MARL), steganographic collusion -- where agents develop private protocols to evade monitoring -- presents a critical AI safety threat. Existing defenses, limited to behavioral or reward…

Despite extensive efforts in safety alignment, large language models (LLMs) remain vulnerable to jailbreak attacks. Activation steering offers a training-free defense method but relies on fixed steering coefficients, resulting in suboptimal…

Unmanned Aerial Vehicles (UAVs) are increasingly adopted in modern communication networks. However, challenges in decision-making and digital modeling continue to impede their rapid advancement. Reinforcement Learning (RL) algorithms face…

Latent dynamical models are commonly used to learn the distribution of a latent dynamical process that represents a sequence of noisy data samples. However, producing samples from such models with high fidelity is challenging due to the…

It is challenging to use reinforcement learning (RL) in cyber-physical systems due to the lack of safety guarantees during learning. Although there have been various proposals to reduce undesired behaviors during learning, most of these…

Safety alignment is often conceptualized as a monolithic process wherein harmfulness detection automatically triggers refusal. However, the persistence of jailbreak attacks suggests a fundamental mechanistic decoupling. We propose the…

Diffusion Language Models (DLMs) have recently achieved strong results in text generation. However, their multi-step sampling leads to slow inference, limiting practical use. To address this, we extend Inverse Distillation, a technique…