Complex narrative contexts often challenge language models' ability to follow instructions, and existing benchmarks fail to capture these difficulties.To address this, we propose Concise-SAE, a training-free framework that improves instruction following by identifying and editing instruction-relevant neurons using only natural language instructions, without requiring labelled data.To thoroughly evaluate our method, we introduce FREEIN-STRUCT, a diverse and realistic benchmark of 1,212 examples that highlights the challenges of instruction following in narrative-rich settings.While initially motivated by complex narratives, Concise-SAE demonstrates stateof-the-art instruction adherence across varied tasks without compromising generation quality.

Fact-checking, the task of reasoning about a claim’s truthfulness based on evidence, has become increasingly crucial with the rapid spread of misinformation. In real-world scenarios, fact-checking often involves checking complex claims necessitating multi-step reasoning, thus imposing a high requirement for a model’s autonomous ability. LLM-based fact-checking performs multi-step reasoning through generating natural language rationales. However, it is susceptible to error propagation problems, which means any error occurring inside rationales will result in an incorrect label. To this end, we propose an iterative rationalization finetuning approach to address this issue, enhancing the LLM’s ability by finetuning it with high-quality rationales. Specifically, we guide the generation of high-quality rationales using golden labels and, inversely, utilize these to finetune the LLM itself, thus constructing a self-improvement cycle. We demonstrate the effectiveness of the proposed method on HoVer and FEVEROUS-S benchmarks, where it achieves state-of-the-art performance, particularly in multi-step reasoning scenarios.

This article introduces an integrated guidance and control method for morphing flight vehicles, addressing model uncertainties and external disturbances through a robust deep reinforcement learning framework built on sliding-mode control (SMC). The method development begins with the establishment of a longitudinal guidance and control model and a detailed introduction to the necessary theoretical foundations. The proposed approach incorporates robust observation strategies enabled by a novel fixed-time SMC design. The agent’s actions, rewards, neural network structure, and training process are meticulously crafted to tackle practical guidance and control challenges effectively. Trained offline to achieve seamless integration of position and attitude control, the agent generates end-to-end control commands in real time during online operation. Extensive testing, including robustness evaluations, generalization assessments, and comparative performance analyses, demonstrates the superiority and reliability of the proposed method.

This paper presents a multirotor control architecture, where Model Predictive Path Integral Control (MPPI) and ℒ1adaptive control are combined to achieve both fast model predictive trajectory planning and robust trajectory tracking. MPPI provides a framework to solve nonlinear MPC with complex cost functions in real-time. However, it often lacks robustness, especially when the simulated dynamics are different from the true dynamics. We show that the ℒ1adaptive controller robustifies the architecture, allowing the overall system to behave similar to the nominal system simulated with MPPI. The architecture is validated in a simulated multirotor racing environment.

Control on solid oxide fuel cells (SOFC) is challenging due to its nonlinearity, time-varying uncertainties, tight operating constraints and modeling difficulties. The L 1 adaptive output feedback controller for systems of unknown relative degree is introduced for the SOFC output voltage control in this paper. It allows for fast and robust adaptation, and provides improved transient performance. Its advantages of not enforcing a strictly positive real condition along with the low-pass filtered control signal bring it the potential to be applied in wide industrial processes. In the study of the SOFC control, a dynamic SOFC model is first built; then a L 1 adaptive output feedback controller is designed only using the nominal working conditions of the SOFC model. Through setting the operating constraints at proper locations, the closed-loop stability is maintained in the presence of hard constraints by the symmetric structure of the L 1 adaptive control loop. A simulation comparison is made in the SOFC constant voltage control process between the L 1 adaptive controller and a linear disturbance model predictive controller (DMPC) for their almost equal complexity in designs. The result shows the advantage of the L 1 adaptive controller in disturbance rejections for its faster transient response.

This paper presents a fully functional and highly portable mini Unmanned Aerial Vehicle (UAV) system, HAWK, for conducting aerial localization. HAWK is a programmable mini helicopter Draganflyer X6 armed with a wireless sniffer Nokia N900. We developed custom PI-Control laws to implement a robust waypoint algorithm for the mini helicopter to fly a planned route. A Moore space filling curve is designed as a flight route for HAWK to survey a specific area. A set of theorems were derived to calculate the minimum Moore curve level for sensing all targets in the area with minimum flight distance. With such a flight strategy, we can confine the location of a target of interest to a small hot area. We can recursively apply the Moore curve-based flight route to the hot area for a fine-grained localization of a target of interest. We have conducted extensive experiments to validate the feasibility of HAWK and our theory. A demo of HAWK in autonomous fly is available at http://www.youtube.com/watch?v=ju86xnHbEq0.

This paper presents a fully functional and highly portable mini Unmanned Aerial Vehicle (UAV) system, HAWK, for conducting aerial localization. HAWK is a programmable mini helicopter - Draganflyer X6 - armed with a wireless sniffer - Nokia N900. We developed custom PI-Control laws to implement a robust waypoint algorithm for the mini helicopter to fly a planned route. A Moore space filling curve is designed as a flight route for HAWK to survey a specific area. A set of theorems were derived to calculate the minimum Moore curve level for sensing all targets in the area with minimum flight distance. With such a flight strategy, we can confine the location of a target of interest to a small hot area. We can recursively apply the Moore curve based flight route to the hot area for a fine-grained localization of a target of interest. Therefore, HAWK does not rely on a positioning infrastructure for localization. We have conducted extensive experiments to validate the feasibility of HAWK and our theory. A demo of HAWK in autonomous fly is available at http://www.youtube.com/watch?v=ju86xnHbEq0.

This paper presents a full state feedback adaptive dynamic inversion method for uncertain systems that depend nonlinearly upon the control input. Using a specialized set of basis functions that respect the monotonic property of the system nonlinearities with respect to control input, a state predictor is defined for derivation of the adaptive laws. The adaptive dynamic inversion controller is defined as a solution of a fast dynamical equation, which achieves time-scale separation between the state predictor and the controller dynamics. Lyapunov-based adaptive laws ensure that the predictor tracks the state of the nonlinear system with bounded errors. As a result, the system state tracks the desired reference model with bounded errors. Benefits of the proposed design method are demonstrated using Van der Pol dynamics with nonlinear control input.

In this paper, we present a novel neural network (NN) adaptive control architecture with guaranteed transient performance. With this new architecture, both input and output signals of an uncertain nonlinear system follow a desired linear system during the transient phase, in addition to stable tracking. This new architecture uses a low-pass filter in the feedback loop, which consequently enables to enforce the desired transient performance by increasing the adaptation gain. For the guaranteed transient performance of both input and output signals of the uncertain nonlinear system, the L1 gain of a cascaded system, comprised of the low-pass filter and the closed-loop desired reference model, is required to be less than the inverse of the Lipschitz constant of the unknown nonlinearities in the system. The tools from this paper can be used to develop a theoretically justified verification and validation framework for NN adaptive controllers. Simulation results illustrate the theoretical findings.