Toward Anthropomorphic Dialogue: A Closed-Loop Framework for Human-Like Chat Generation, Evaluation, and Preference Alignment

Human-like private chat requires more than fluent response generation: a system must preserve persona, relationship, memory, bounded knowledge, medium-specific timing, and a coherent multi-turn arc. We present AnthroDial, a closed-loop framework that formulates anthropomorphic dialogue as a joint problem of system architecture, executable evaluation, and diagnostic alignment. It combines (1) a role-conditioned scheduled dialogue runtime with persona and scenario cards, long-term memory, virtual time, and single-draft message decisions; (2) an executable benchmark with an L0 validity gate, five per-turn dimensions, and five dialogue-level dimensions; and (3) a post-training pipeline that filters 16,436 scheduled-decision examples for SFT and applies GRPO with a cognitive-diagnostic, ZPD-aware reward. The reward maintains Kalman-filtered capability estimates for each behavioral dimension, upweights dimensions with larger capability deficits, and uses rollout scores as task-level ZPD matches to focus optimization on learnable weak skills. On a benchmark with 55 personas, 50 scenarios, 50 persona-scenario bindings, and 100 role-conditioned cases per model, we evaluate 16 systems spanning frontier baselines, open models, thinking/no-think variants, and SFT/RL ablations. The strongest non-trained baseline reaches 32.00% strict ACC, while Qwen3.6-27B-SFT+RL reaches 39.00% strict ACC and a 98.5 overall score. In the 9B no-think setting, SFT and RL improve strict ACC from 0.00% to 13.00% and 18.37%. These results show that anthropomorphic dialogue benefits when generation, evaluation, and reward shaping share the same behavioral dimensions.

FedUP: One-Shot Federated Unlearning via Centroid-Guided Plug-in Filters

Federated unlearning (FU) is critical for complying with legal mandates like the right to be forgotten in decentralized systems, yet current methods face a persistent dilemma between non-target knowledge loss and high request latency. To resolve these issues, we propose FedUP, a one-shot federated unlearning framework utilizing lightweight pluggable filters that act as a "knowledge funnel" to screen out target data while preserving original model performance. By freezing original model parameters and training filters at the server side using differentially private (DP)-protected class centroid samples, FedUP bypasses the need for multi-round client-server communication and complex retraining, reducing unlearning latency from minutes to mere seconds. Additionally, the framework's pluggable architecture ensures inherent reversibility, enabling the seamless restoration of forgotten knowledge by simply removing the filters. Extensive experiments on diverse image and text tasks demonstrate that FedUP effectively reduces non-target knowledge loss and achieves superior unlearning precision and efficiency across various scenarios. Code is available at: https://github.com/suows/FedUP-code.

LER-YOLO: Reliability-Aware Expert Routing for Misaligned RGB-Infrared UAV Detection

Detecting small unmanned aerial vehicles from RGB-infrared remote-sensing pairs remains challenging due to tiny target scale, cluttered backgrounds, and spatial misalignment between heterogeneous sensors. Existing bimodal detectors often align or fuse features without assessing the reliability of local cross-sensor correspondence, allowing mismatch artifacts to propagate into the detection head. To address this issue, we propose LER-YOLO, a reliability-aware sparse mixture-of-experts framework for misaligned RGB-infrared UAV detection. LER-YOLO first introduces an Uncertainty-Aware Target Alignment module that resamples visible features toward the infrared reference and estimates a spatial reliability map. This reliability prior is then used by a Reliability-Guided Sparse MoE Fusion module to adaptively select k experts from RGB-dominant, infrared-dominant, and interactive fusion experts, enabling trustworthy cross-modal interaction while suppressing unreliable fusion. Experiments on the public MBU benchmark under a YOLOv5s-family protocol show that LER-YOLO achieves 89.7+/-0.2% AP50 over three independent seeds, with a best result of 89.9%. Extensive ablations, parameter-matched comparisons, synthetic-shift evaluations, and complexity analysis demonstrate that the gains mainly come from reliability-guided expert routing rather than increased model capacity.

Rethink Efficiency Side of Neural Combinatorial Solver: An Offline and Self-Play Paradigm

We propose ECO, a versatile learning paradigm that enables efficient offline self-play for Neural Combinatorial Optimization (NCO). ECO addresses key limitations in the field through: 1) Paradigm Shift: Moving beyond inefficient online paradigms, we introduce a two-phase offline paradigm consisting of supervised warm-up and iterative Direct Preference Optimization (DPO); 2) Architecture Shift: We deliberately design a Mamba-based architecture to further enhance the efficiency in the offline paradigm; and 3) Progressive Bootstrapping: To stabilize training, we employ a heuristic-based bootstrapping mechanism that ensures continuous policy improvement during training. Comparison results on TSP and CVRP highlight that ECO performs competitively with up-to-date baselines, with significant advantage on the efficiency side in terms of memory utilization and training throughput. We provide further in-depth analysis on the efficiency, throughput and memory usage of ECO. Ablation studies show rationale behind our designs.

Fluid Antenna Systems under Channel Uncertainty and Hardware Impairments: Trends, Challenges, and Future Research Directions

Fluid antenna systems (FAS) have recently emerged as a promising paradigm for achieving spatially reconfigurable, compact, and energy-efficient wireless communications in beyond fifth-generation (B5G) and sixth-generation (6G) networks. By dynamically repositioning a liquid-based radiating element within a confined physical structure, FAS can exploit spatial diversity without relying on multiple fixed antenna elements. This spatial mobility provides a new degree of freedom for mitigating channel fading and interference, while maintaining low hardware complexity and power consumption. However, the performance of FAS in realistic deployments is strongly affected by channel uncertainty, hardware nonidealities, and mechanical constraints, all of which can substantially deviate from idealized analytical assumptions. This paper presents a comprehensive survey of the operation and design of FAS under such practical considerations. Key aspects include the characterization of spatio-temporal channel uncertainty, analysis of hardware and mechanical impairments such as RF nonlinearity, port coupling, and fluid response delay, as well as the exploration of robust design and learning-based control strategies to enhance system reliability. Finally, open research directions are identified, aiming to guide future developments toward robust, adaptive, and cross-domain FAS design for next-generation wireless networks.

Symphony: A Decentralized Multi-Agent Framework for Scalable Collective Intelligence

Most existing Large Language Model (LLM)-based agent frameworks rely on centralized orchestration, incurring high deployment costs, rigid communication topologies, and limited adaptability. To address these challenges, we introduce Symphony, a decentralized multi-agent system which enables lightweight LLMs on consumer-grade GPUs to coordinate. Symphony introduces three key mechanisms: (1) a decentralized ledger that records capabilities, (2) a Beacon-selection protocol for dynamic task allocation, and (3) weighted result voting based on CoTs. This design forms a privacy-saving, scalable, and fault-tolerant orchestration with low overhead. Empirically, Symphony outperforms existing baselines on reasoning benchmarks, achieving substantial accuracy gains and demonstrating robustness across models of varying capacities.

Task-Specific Zero-shot Quantization-Aware Training for Object Detection

Quantization is a key technique to reduce network size and computational complexity by representing the network parameters with a lower precision. Traditional quantization methods rely on access to original training data, which is often restricted due to privacy concerns or security challenges. Zero-shot Quantization (ZSQ) addresses this by using synthetic data generated from pre-trained models, eliminating the need for real training data. Recently, ZSQ has been extended to object detection. However, existing methods use unlabeled task-agnostic synthetic images that lack the specific information required for object detection, leading to suboptimal performance. In this paper, we propose a novel task-specific ZSQ framework for object detection networks, which consists of two main stages. First, we introduce a bounding box and category sampling strategy to synthesize a task-specific calibration set from the pre-trained network, reconstructing object locations, sizes, and category distributions without any prior knowledge. Second, we integrate task-specific training into the knowledge distillation process to restore the performance of quantized detection networks. Extensive experiments conducted on the MS-COCO and Pascal VOC datasets demonstrate the efficiency and state-of-the-art performance of our method. Our code is publicly available at: https://github.com/DFQ-Dojo/dfq-toolkit .

Resource Allocation for Pinching-Antenna Systems: State-of-the-Art, Key Techniques and Open Issues

Pinching antennas have emerged as a promising technology for reconfiguring wireless propagation environments, particularly in high-frequency communication systems operating in the millimeter-wave and terahertz bands. By enabling dynamic activation at arbitrary positions along a dielectric waveguide, pinching antennas offer unprecedented channel reconfigurability and the ability to provide line-of-sight (LoS) links in scenarios with severe LoS blockages. The performance of pinching-antenna systems is highly dependent on the optimized placement of the pinching antennas, which must be jointly considered with traditional resource allocation (RA) variables -- including transmission power, time slots, and subcarriers. The resulting joint RA problems are typically non-convex with complex variable coupling, necessitating sophisticated optimization techniques. This article provides a comprehensive survey of existing RA algorithms designed for pinching-antenna systems, supported by numerical case studies that demonstrate their potential performance gains. Key challenges and open research problems are also identified to guide future developments in this emerging field.

Energy-Efficient Design for Downlink Pinching-Antenna Systems with QoS Guarantee

Pinching antennas have recently garnered significant attention due to their ability to dynamically reconfigure wireless propagation environments. Despite notable advancements in this area, the exploration of energy efficiency (EE) maximization in pinching-antenna systems remains relatively underdeveloped. In this paper, we address the EE maximization problem in a downlink time-division multiple access (TDMA)-based multi-user system employing one waveguide and multiple pinching antennas, where each user is subject to a minimum rate constraint to ensure quality-of-service. The formulated optimization problem jointly considers transmit power and time allocations as well as the positioning of pinching antennas, resulting in a non-convex problem. To tackle this challenge, we first obtain the optimal positions of the pinching antennas. Based on this, we establish a feasibility condition for the system. Subsequently, the joint power and time allocation problem is decomposed into two subproblems, which are solved iteratively until convergence. Specifically, the power allocation subproblem is addressed through an iterative approach, where a semi-analytical solution is obtained in each iteration. Likewise, a semi-analytical solution is derived for the time allocation subproblem. Numerical simulations demonstrate that the proposed pinching-antenna-based strategy significantly outperforms both conventional fixed-antenna systems and other benchmark pinching-antenna schemes in terms of EE.

Energy-Efficient Resource Allocation for NOMA-Assisted Uplink Pinching-Antenna Systems

The pinching-antenna architecture has emerged as a promising solution for reconfiguring wireless propagation environments and enhancing system performance. While prior research has primarily focused on sum-rate maximization or transmit power minimization of pinching-antenna systems, the critical aspect of energy efficiency (EE) has received limited attention. Given the increasing importance of EE in future wireless communication networks, this work investigates EE optimization in a non-orthogonal multiple access (NOMA)-assisted multi-user pinching-antenna uplink system. The problem entails the joint optimization of the users' transmit power and the pinching-antenna position. The resulting optimization problem is non-convex due to tightly coupled variables. To tackle this, we employ an alternating optimization framework to decompose the original problem into two subproblems: one focusing on power allocation and the other on antenna positioning. A low-complexity optimal solution is derived for the power allocation subproblem, while the pinching-antenna positioning subproblem is addressed using a particle swarm optimization algorithm to obtain a high-quality near-optimal solution. Simulation results demonstrate that the proposed scheme significantly outperforms both conventional-antenna configurations and orthogonal multiple access-based pinching-antenna systems in terms of EE.