Related papers: Learn-by-Wire Training Control Governance: Bounded…

The machine learning community has witnessed impressive advancements since large language models (LLMs) first appeared. Yet, their massive memory consumption has become a significant roadblock to large-scale training. For instance, a 7B…

Adaptive gradient methods, such as Adam and LAMB, have demonstrated excellent performance in the training of large language models. Nevertheless, the need for adaptivity requires maintaining second-moment estimates of the per-parameter…

We study the problem of learning-augmented predictive linear quadratic control. Our goal is to design a controller that balances \textit{"consistency"}, which measures the competitive ratio when predictions are accurate, and…

Large language model (LLM) has recently been considered a promising technique for many fields. This work explores LLM-based wireless network optimization via in-context learning. To showcase the potential of LLM technologies, we consider…

We present a constructive approach to bounded $\ell_2$-gain adaptive control with noisy measurements for linear time-invariant scalar systems with uncertain parameters belonging to a finite set. The gain bound refers to the closed-loop…

Large language model (LLM) agents on multi-step tasks suffer reasoning degradation, looping, drift, stuck states, at rates up to 30% on hard tasks. Current solutions include hard step limits (abrupt) or LLM-as-judge monitoring (10-15%…

Robotics Wire Arc Additive Manufacturing (WAAM) is governed by complex and nonlinear process dynamics coupling thermal field to the build geometry. The process may be regarded as a multi-input/multi-output dynamical system with welding…

Large language models (LLMs) have achieved strong performance in language-centric tasks. However, in agentic settings, LLMs often struggle to anticipate action consequences and adapt to environment dynamics, highlighting the need for…

Large Language Models (LLMs) exhibit impressive capabilities but also present risks such as biased content generation and privacy issues. One of the current alignment techniques includes principle-driven integration, but it faces challenges…

Motivated by the growing use of artificial intelligence (AI) tools in control design, this paper analyses the intersection between results from gradient methods for the model-free linear quadratic regulator (LQR), and linear feedforward…

It is widely believed that stochastic gradient descent (SGD) performs significantly worse than adaptive optimizers such as Adam in pre-training Large Language Models (LLMs). Yet the underlying reason for this gap remains unclear. In this…

The applications of large language models (LLMs) have been widely spread across all domains. However, the basic abilities such as the controllability of LLMs are still limited. To address this, we propose "Self-controller", a novel agentic…

To manage and optimize constantly evolving wireless networks, existing machine learning (ML)- based studies operate as black-box models, leading to increased computational costs during training and a lack of transparency in decision-making,…

LLM deployment in critical domains is currently impeded by persistent hallucinations--generating plausible but factually incorrect assertions. While scaling laws drove significant improvements in general capabilities, theoretical frameworks…

The deployment of autonomous robots in safety-critical applications requires safety guarantees. Provably safe reinforcement learning is an active field of research that aims to provide such guarantees using safeguards. These safeguards…

We introduce Llama Guard, an LLM-based input-output safeguard model geared towards Human-AI conversation use cases. Our model incorporates a safety risk taxonomy, a valuable tool for categorizing a specific set of safety risks found in LLM…

In many reinforcement learning (RL) applications, we want policies that reach desired states and then keep the controlled system within an acceptable region around the desired states over an indefinite period of time. This latter objective…

Short-video platforms now host vast multimodal ads whose deceptive visuals, speech and subtitles demand finer-grained, policy-driven moderation than community safety filters. We present BLM-Guard, a content-audit framework for commercial…

The ability to learn and execute optimal control policies safely is critical to realization of complex autonomy, especially where task restarts are not available and/or the systems are safety-critical. Safety requirements are often…

Is the standard weight decay in AdamW truly optimal? Although AdamW decouples weight decay from adaptive gradient scaling, a fundamental conflict remains: the Radial Tug-of-War. In deep learning, gradients tend to increase parameter norms…