DiPT: Enhancing LLM reasoning through diversified perspective-taking

Existing work on improving language model reasoning typically explores a single solution path, which can be prone to errors. Inspired by perspective-taking in social studies, this paper introduces DiPT, a novel approach that complements current reasoning methods by explicitly incorporating diversified viewpoints. This approach allows the model to gain a deeper understanding of the problem's context and identify the most effective solution path during the inference stage. Additionally, it provides a general data-centric AI recipe for augmenting existing data to improve their quality for fine-tuning. Our empirical results demonstrate that DiPT can be flexibly integrated into existing methods that focus on a single reasoning approach, enhancing their reasoning performance and stability when presented with paraphrased problems. Furthermore, we illustrate improved context understanding by maintaining the model's safe outputs against "jailbreaking" prompts intentionally designed to bypass safeguards built into deployed models. Lastly, we show that fine-tuning with data enriched with diverse perspectives can boost the reasoning capabilities of the model compared to fine-tuning with raw data alone.

Neural Network-Assisted Hybrid Model Based Message Passing for Parametric Holographic MIMO Near Field Channel Estimation

Holographic multiple-input and multiple-output (HMIMO) is a promising technology with the potential to achieve high energy and spectral efficiencies, enhance system capacity and diversity, etc. In this work, we address the challenge of HMIMO near field (NF) channel estimation, which is complicated by the intricate model introduced by the dyadic Green's function. Despite its complexity, the channel model is governed by a limited set of parameters. This makes parametric channel estimation highly attractive, offering substantial performance enhancements and enabling the extraction of valuable sensing parameters, such as user locations, which are particularly beneficial in mobile networks. However, the relationship between these parameters and channel gains is nonlinear and compounded by integration, making the estimation a formidable task. To tackle this problem, we propose a novel neural network (NN) assisted hybrid method. With the assistance of NNs, we first develop a novel hybrid channel model with a significantly simplified expression compared to the original one, thereby enabling parametric channel estimation. Using the readily available training data derived from the original channel model, the NNs in the hybrid channel model can be effectively trained offline. Then, building upon this hybrid channel model, we formulate the parametric channel estimation problem with a probabilistic framework and design a factor graph representation for Bayesian estimation. Leveraging the factor graph representation and unitary approximate message passing (UAMP), we develop an effective message passing-based Bayesian channel estimation algorithm. Extensive simulations demonstrate the superior performance of the proposed method.

Optimization Solution Functions as Deterministic Policies for Offline Reinforcement Learning

Offline reinforcement learning (RL) is a promising approach for many control applications but faces challenges such as limited data coverage and value function overestimation. In this paper, we propose an implicit actor-critic (iAC) framework that employs optimization solution functions as a deterministic policy (actor) and a monotone function over the optimal value of optimization as a critic. By encoding optimality in the actor policy, we show that the learned policies are robust to the suboptimality of the learned actor parameters via the exponentially decaying sensitivity (EDS) property. We obtain performance guarantees for the proposed iAC framework and show its benefits over general function approximation schemes. Finally, we validate the proposed framework on two real-world applications and show a significant improvement over state-of-the-art (SOTA) offline RL methods.

FAS-RIS Communication: Model, Analysis, and Optimization

This correspondence investigates the novel fluid antenna system (FAS) technology, combining with reconfigurable intelligent surface (RIS) for wireless communications, where a base station (BS) communicates with a FAS-enabled user with the assistance of a RIS. To analyze this technology, we derive the outage probability based on the block-diagonal matrix approximation (BDMA) model. With this, we obtain the upper bound, lower bound, and asymptotic approximation of the outage probability to gain more insights. Moreover, we design the phase shift matrix of the RIS in order to minimize the system outage probability. Simulation results confirm the accuracy of our approximations and that the proposed schemes outperform benchmarks significantly.

Full-Duplex ISAC-Enabled D2D Underlaid Cellular Networks: Joint Transceiver Beamforming and Power Allocation

Integrating device-to-device (D2D) communication into cellular networks can significantly reduce the transmission burden on base stations (BSs). Besides, integrated sensing and communication (ISAC) is envisioned as a key feature in future wireless networks. In this work, we consider a full-duplex ISAC- based D2D underlaid system, and propose a joint beamforming and power allocation scheme to improve the performance of the coexisting ISAC and D2D networks. To enhance spectral efficiency, a sum rate maximization problem is formulated for the full-duplex ISAC-based D2D underlaid system, which is non-convex. To solve the non-convex optimization problem, we propose a successive convex approximation (SCA)-based iterative algorithm and prove its convergence. Numerical results are provided to validate the effectiveness of the proposed scheme with the iterative algorithm, demonstrating that the proposed scheme outperforms state-of-the-art ones in both communication and sensing performance.

FAS vs. ARIS: Which Is More Important for FAS-ARIS Communication Systems?

In this paper, we investigate the question of which technology, fluid antenna systems (FAS) or active reconfigurable intelligent surfaces (ARIS), plays a more crucial role in FAS-ARIS wireless communication systems. To address this, we develop a comprehensive system model and explore the problem from an optimization perspective. We introduce an alternating optimization (AO) algorithm incorporating majorization-minimization (MM), successive convex approximation (SCA), and sequential rank-one constraint relaxation (SRCR) to tackle the non-convex challenges inherent in these systems. Specifically, for the transmit beamforming of the BS optimization, we propose a closed-form rank-one solution with low-complexity. For the optimization the positions of fluid antennas (FAs) of the BS, the Taylor expansions and MM algorithm are utilized to construct the effective lower bounds and upper bounds of the objective function and constraints, transforming the non-convex optimization problem into a convex one. Furthermore, we use the SCA and SRCR to optimize the reflection coefficient matrix of the ARIS and effectively solve the rank-one constraint. Simulation results reveal that the relative importance of FAS and ARIS varies depending on the scenario: FAS proves more critical in simpler models with fewer reflecting elements or limited transmission paths, while ARIS becomes more significant in complex scenarios with a higher number of reflecting elements or transmission paths. Ultimately, the integration of both FAS and ARIS creates a win-win scenario, resulting in a more robust and efficient communication system. This study underscores the importance of combining FAS with ARIS, as their complementary use provides the most substantial benefits across different communication environments.

DyG-Mamba: Continuous State Space Modeling on Dynamic Graphs

Dynamic graph learning aims to uncover evolutionary laws in real-world systems, enabling accurate social recommendation (link prediction) or early detection of cancer cells (classification). Inspired by the success of state space models, e.g., Mamba, for efficiently capturing long-term dependencies in language modeling, we propose DyG-Mamba, a new continuous state space model (SSM) for dynamic graph learning. Specifically, we first found that using inputs as control signals for SSM is not suitable for continuous-time dynamic network data with irregular sampling intervals, resulting in models being insensitive to time information and lacking generalization properties. Drawing inspiration from the Ebbinghaus forgetting curve, which suggests that memory of past events is strongly correlated with time intervals rather than specific details of the events themselves, we directly utilize irregular time spans as control signals for SSM to achieve significant robustness and generalization. Through exhaustive experiments on 12 datasets for dynamic link prediction and dynamic node classification tasks, we found that DyG-Mamba achieves state-of-the-art performance on most of the datasets, while also demonstrating significantly improved computation and memory efficiency.

A Black Swan Hypothesis in Markov Decision Process via Irrationality

Black swan events are statistically rare occurrences that carry extremely high risks. A typical view of defining black swan events is heavily assumed to originate from an unpredictable time-varying environments; however, the community lacks a comprehensive definition of black swan events. To this end, this paper challenges that the standard view is incomplete and claims that high-risk, statistically rare events can also occur in unchanging environments due to human misperception of their value and likelihood, which we call as spatial black swan event. We first carefully categorize black swan events, focusing on spatial black swan events, and mathematically formalize the definition of black swan events. We hope these definitions can pave the way for the development of algorithms to prevent such events by rationally correcting human perception

Data-Centric Human Preference Optimization with Rationales

Reinforcement learning from human feedback plays a crucial role in aligning language models towards human preferences, traditionally represented through comparisons between pairs or sets of responses within a given context. While many studies have enhanced algorithmic techniques to optimize learning from such data, this work shifts focus to improving preference learning through a data-centric approach. Specifically, we propose enriching existing preference datasets with machine-generated rationales that explain the reasons behind choices. We develop a simple and principled framework to augment current preference learning methods with rationale information. Our comprehensive analysis highlights how rationales enhance learning efficiency. Extensive experiments reveal that rationale-enriched preference learning offers multiple advantages: it improves data efficiency, accelerates convergence to higher-performing models, and reduces verbosity bias and hallucination. Furthermore, this framework is versatile enough to integrate with various preference optimization algorithms. Overall, our findings highlight the potential of re-imagining data design for preference learning, demonstrating that even freely available machine-generated rationales can significantly boost performance across multiple dimensions. The code repository is available at https: //github.com/reds-lab/preference-learning-with-rationales

Fluid Antenna-Assisted Simultaneous Wireless Information and Power Transfer Systems

This paper examines a fluid antenna (FA)-assisted simultaneous wireless information and power transfer (SWIPT) system. Unlike traditional SWIPT systems with fixed-position antennas (FPAs), our FA-assisted system enables dynamic reconfiguration of the radio propagation environment by adjusting the positions of FAs. This capability enhances both energy harvesting and communication performance. The system comprises a base station (BS) equipped with multiple FAs that transmit signals to an energy receiver (ER) and an information receiver (IR), both equipped with a single FA. Our objective is to maximize the communication rate between the BS and the IR while satisfying the harvested power requirement of the ER. This involves jointly optimizing the BS's transmit beamforming and the positions of all FAs. To address this complex convex optimization problem, we employ an alternating optimization (AO) approach, decomposing it into three sub-problems and solving them iteratively using first and second-order Taylor expansions. Simulation results validate the effectiveness of our proposed FA-assisted SWIPT system, demonstrating significant performance improvements over traditional FPA-based systems.