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

Autonomous off-road driving is challenging as risky actions taken by the robot may lead to catastrophic damage. As such, developing controllers in simulation is often desirable as it provides a safer and more economical alternative.…

Reinforcement learning (RL) has emerged as an effective post-training paradigm for enhancing the reasoning capabilities of multimodal large language model (MLLM). However, current RL pipelines often suffer from training inefficiencies…

Reinforcement Learning (RL) has recently emerged as a powerful technique for improving image and video generation in Diffusion and Flow Matching models, specifically for enhancing output quality and alignment with prompts. A critical step…

Learning by interaction is the key to skill acquisition for most living organisms, which is formally called Reinforcement Learning (RL). RL is efficient in finding optimal policies for endowing complex systems with sophisticated behavior.…

Refusal behavior in large language models (LLMs) enables them to decline responding to harmful, unethical, or inappropriate prompts, ensuring alignment with ethical standards. This paper investigates refusal behavior across six LLMs from…

Diffusion models (DMs) have recently demonstrated remarkable generation capability. However, their training generally requires huge computational resources and large-scale datasets. To solve these, recent studies empower DMs with the…

Decision-making stands as a pivotal component in the realm of autonomous vehicles (AVs), playing a crucial role in navigating the intricacies of autonomous driving. Amidst the evolving landscape of data-driven methodologies, enhancing…

Despite the growing success of diffusion models in continuous-valued domains (e.g., images), similar efforts for discrete domains such as text have yet to match the performance of autoregressive language models. In this work, we present…

Recent developments in offline reinforcement learning have uncovered the immense potential of diffusion modeling, which excels at representing heterogeneous behavior policies. However, sampling from diffusion policies is considerably slow…

Transformer LMs show emergent reasoning that resists mechanistic understanding. We offer a statistical physics framework for continuous-time chain-of-thought reasoning dynamics. We model sentence-level hidden state trajectories as a…

Ensuring robust safety measures across a wide range of scenarios is crucial for user-facing systems. While Large Language Models (LLMs) can generate valuable data for safety measures, they often exhibit distributional biases, focusing on…

While mobile devices provide ever more compute power, improvements in DRAM bandwidth are much slower. This is unfortunate for large language model (LLM) token generation, which is heavily memory-bound. Previous work has proposed to leverage…

Effectively controlling systems governed by Partial Differential Equations (PDEs) is crucial in several fields of Applied Sciences and Engineering. These systems usually yield significant challenges to conventional control schemes due to…

As the next generation of mobile systems evolves, artificial intelligence (AI) is expected to deeply integrate with wireless communications for resource management in variable environments. In particular, deep reinforcement learning (DRL)…

This paper proposes a novel inverse reinforcement learning framework using a diffusion-based adaptive lookahead planner (IRL-DAL) for autonomous vehicles. Training begins with imitation from an expert finite state machine (FSM) controller…

Machine Unlearning is essential for large generative models (VAEs, DDPMs) to comply with the right to be forgotten and prevent undesired content generation without costly retraining. Existing approaches, such as Static-lambda SISS for…

In this letter, we investigate a dynamic reconfigurable distributed antenna and reflection surface (RDARS)-driven secure communication system, where the working mode of the RDARS can be flexibly configured. We aim to maximize the secrecy…

Deep reinforcement learning (DRL) has proven extremely useful in a large variety of application domains. However, even successful DRL-based software can exhibit highly undesirable behavior. This is due to DRL training being based on…

Large language models (LLMs) offer strong capabilities but raise cost and privacy concerns, whereas small language models (SLMs) facilitate efficient and private local inference yet suffer from limited capacity. To synergize the…

Discrete diffusion models have demonstrated great promise in modeling various sequence data, ranging from human language to biological sequences. Inspired by the success of RL in language models, there is growing interest in further…