Papers

Rapidly shifting operational scenarios driven by uncertain Distributed Energy Resource (DER) profiles render conventional distribution network optimization methods either computationally expensive or poorly generalizable. This paper introduces GridRAG, a pioneering retrieval-augmented framework that transforms optimization into a “retrieve-and-refine” paradigm. GridRAG first embeds scenario features and optimal solutions into a joint representation space to ensure semantic consistency. Based on the hybrid semantic information, the similar historical scenarios are then retrieved from a pre-constructed database. Then an SDEdit-style diffusion module is integrated to refine retrieved solutions by modeling the conditional distribution over near-feasible manifolds. This process effectively pulls retrieved solutions into near-optimal attraction basins, providing a high-quality warm-start for the final solver. Validated on three optimization tasks across four standard topologies, GridRAG demonstrates superior cross-scenario generalization and a multi-fold speedup in solution time compared to existing learning-based and model-based baselines. Our code is available at https://github.com/YuxuanCEE/GridRAG.

This paper solves the targeting problem focusing on accuracy, computational efficiency, and reliability. The trajectory optimization problem is first recast as a polynomial optimization problem (POP) by leveraging differential algebra to compute high-order Taylor expansions of the nonlinear dynamics and constraints. Moment-sum-of-squares (SOS) optimization is then utilized to solve this POP. A convex formulation based on a second-order expansion of the dynamics is also proposed. For impulsive targeting, the moment-SOS and convex approaches are compared against traditional nonlinear programming (NLP) solvers and map inversion techniques. Results indicate that the moment-SOS approach provides solutions as accurate as traditional NLP, but with the critical advantage of guaranteeing convergence to the global optimum under mild assumptions. Furthermore, the method excels at handling large maneuvers and long propagation times, conditions in which standard linear approximations rapidly degrade. To demonstrate its versatility, the methodology is extended to a continuous low-thrust station keeping (SK) scenario in the Earth-Moon Circular Restricted Three-Body Problem. The algorithm's performance is then evaluated in the presence of significant state errors. The ability to directly handle non-convex constraints and recast complex, nonlinear dynamics into formulations with reliable convergence properties makes the moment-SOS approach suitable for autonomous onboard applications.

Integrated sensing and communication (ISAC) at terahertz (THz) frequencies enables ultra-high-resolution perception while facing a key limitation: highly directional THz beams cannot illuminate extended targets within a single beam. Conventional solutions rely on sequential beam scanning, reducing sensing accuracy and increasing energy consumption. Moreover, in conventional sparse-array, grating lobes are generally treated as undesirable artifacts that should be suppressed to avoid ambiguity and interference. In contrast, this paper adopts a reverse design philosophy by intentionally engineering sparsity-induced grating lobes as controllable auxiliary illumination beams for extended-target sensing. This paper exploits grating lobes and proposes a sparse-connected hybrid beamforming architecture that intentionally engineers and exploits grating lobes to enable single-shot, full-aperture illumination of extended targets while supporting multi-user downlink communication. A switch-controlled sparse RF network preserves the array aperture and generates a dominant main lobe with structured secondary lobes covering the entire target extent. A covariance-driven alternating-minimization framework jointly optimizes digital precoders, quantized phase shifters, and antenna-RF switching. Simulations at 140 GHz demonstrate near fully-digital Cramer-Rao sensing accuracy, competitive communication performance in low-rank THz channels, rapid convergence, and significant hardware and energy savings, establishing structured sparse connectivity as a scalable and energy-efficient solution for extended-target THz ISAC.

Accurate and robust wireless localization is a critical enabler for emerging 5G/6G applications, including autonomous driving, extended reality, and smart manufacturing. Despite its importance, achieving precise localization across diverse environments remains challenging due to the complex nature of wireless signals and their sensitivity to environmental changes. Existing data-driven approaches often suffer from limited generalization capability, requiring extensive labeled data and struggling to adapt to new scenarios. To address these limitations, we propose SigMap, a multimodal foundation model that introduces two key innovations: (1) A cycle-adaptive masking strategy that dynamically adjusts masking patterns based on channel periodicity characteristics to learn robust wireless representations; (2) A novel "map-as-prompt" framework that integrates 3D geographic information through lightweight soft prompts for effective cross-scenario adaptation. Extensive experiments demonstrate that our model achieves state-of-the-art performance across multiple localization tasks while exhibiting strong zero-shot generalization in unseen environments, significantly outperforming both supervised and self-supervised baselines by considerable margins.

With the rapid development of integrated sensing and communication (ISAC) as a key enabler for future wireless networks, ensuring the security of both communication and sensing functions has become increasingly important. Current secure ISAC studies focus restrictively either on the communication or the sensing security, but not both. To bridge this gap, this paper investigates security for both, i.e., dual-security, in indoor orthogonal frequency division multiplexing (OFDM) based ISAC systems. Specifically, we consider a scenario in which a sensing user (SU) is authorized for sensing but may eavesdrop on communication data, while a communication user (CU) is authorized for communication but may perform unauthorized sensing. We chose this scenario as the pathological case where an authorized eavesdropper has more information and is more effective than an unauthorized one. To address this case, we propose the use of temporal artificial noise (AN) to prevent malicious CU sensing by enlarging its time-domain sensing error, and simultaneously degrade SU data eavesdropping by reducing its frequency-domain signal-to-interference-plus-noise ratio (SINR) with standard OFDM receiver processing. Meanwhile, our proposed scheme guarantees the sensing performance of the SU and the communication performance of the CU. We present numerical results that demonstrate AN can effectively provide dual protection for sensing and communication in OFDM-ISAC systems while guaranteeing the performance of legitimate users.

A voice actor's voice is their asset, and AI cloning directly threatens it. The natural defense flags the enrolled actor whose embedding similarity to a suspect recording crosses a threshold. We show it fails where it is most needed: trained voices crowd the embedding space, and each actor performs many styles. On 1,168 Japanese voice actors (56,568 segments, ~63 h), a misidentification floor survives calibration, score normalization, and discriminative re-ranking (linear and nonlinear, including PLDA): the residual is a limit of the embedding geometry, not of the back-ends we evaluate. The best ensemble still leaves ~2.6% closed-set misidentification, several-fold above matched controls; session-disjoint, re-ranking lowers the floor only to 13.0%. The same crowding drives false attribution: on a generic English encoder, roughly half the clones of non-enrolled people falsely accuse an enrolled actor, while – by a separate real-vs-synthetic shift – 32% of Seed-VC clones of enrolled targets are missed at the same threshold; one operating point couples the two, and none escapes both. A domain-matched, voice-actor-trained encoder mitigates substantially (a four-fold gender gap vanishes; wrongful misattribution falls to 1.5-10%), but does not remove the floor. Controls (codec, channel, vocoder, content) support reading the miss rate as a real-versus-synthetic covariate shift, not missing speaker information. Fixed-threshold clone attribution is thus unreliable here, and on a generic encoder unfair. Robust attribution must extend spoofing-aware speaker verification to open-set 1:N (anti-spoofing gate, domain-matched encoder, per-speaker calibration, abstain option), and even then supports detection, not autonomous enforcement.

Urban Air Mobility (UAM) with electric Vertical TakeOff and Landing (eVTOL) vehicles can help address ground traffic congestion. The design of an eVTOL trajectory that is safe and reduces travel time is key for UAM adoption. Existing works on trajectory design either may not adequately incorporate dense obstacles in urban environments, complex eVTOL flight dynamics, or one or more flight phases. Not considering these factors can result in low-quality, or worse infeasible, trajectories. We develop a hybrid framework that can integrate building obstacles data, wind data, eVTOL flight dynamics, and other real-world operational constraints to estimate a four-dimensional eVTOL flight trajectory in ascent, cruise, and descent that aims to minimize travel time. Our framework first fills the obstacle-free regions with intersecting convex polygons, then identifies potentially low-travel time candidate sequences of these polygons using a Graph of Convex Sets-based path planner, and then uses an Optimal Control Program to give the final trajectory that passes through the polygons in a sequence identified before. We evaluate our framework on routes within New York City. Our framework can design trajectories respecting the above constraints in the presence of as many as 250 building obstacles. We show that not including the above constraints can underestimate the flight time by as much as 20%.

Grid-forming (GFM) energy storage system (ESS) is a key enabler for stabilizing future power systems with high penetration of converter-based resources (CBRs). To get a better overview of the state-of-the-art and challenges for implementing and deploying GFM-ESS, a global survey has been initiated by Cigre Working Group B4.101 - industrial implementation and application of grid forming energy storage systems. Feedback was collected from universities, transmission system operators (TSOs), power plant developers, original equipment manufacturers (OEMs), research institutes, as well as consultants. It is interesting to note that while many common understandings have been established in practice, certain gaps persist among different stakeholders. This article intends to bridge this gap by presenting a summary of the survey, including the questionnaire, responses from various stakeholders, and in-depth analysis of the survey results. The key challenges faced by different stakeholders in deploying GFM-ESS are identified, shedding light on future research in this direction.

In this paper, we aim to automate the adjustment of air handling unit (AHU) setpoints within heating, ventilation, and air conditioning (HVAC) systems to maintain indoor temperatures at user-specified levels. A key challenge lies in obtaining sufficient high-quality sensor data from real buildings. To address this, we explore transfer learning and leverage simulation software to generate training data. We propose an adaptive model-based transfer learning approach for dynamic HVAC control, where the agent directly controls the source domain under conditions identical to the target domain. This eliminates the need for extensive target-specific knowledge to define data generation schedules and reduces the risk of collecting irrelevant samples, while also providing greater flexibility during learning. At the control level, we enhance performance through physics rule embedding, which ensures physical consistency, and long-term-aware setpoint selection strategy, which mitigates abrupt setpoint changes. Finally, to accelerate and stabilize deployment in new buildings, we enable knowledge transfer directly between similar real-world buildings, reducing the need to construct virtual source domains repeatedly.

Developing autonomous hydraulic excavators is constrained by limited access to physical machines and the high cost of real-world experimentation. This paper proposes a simulation-to-real framework for learning a system-level digital surrogate using Long Short-Term Memory (LSTM) networks. Instead of modeling internal dynamics, the excavator is treated as an input-output operator, and the surrogate is trained to reproduce its closed-loop behavior under identical control inputs. The approach is first validated in a MuJoCo simulation environment and then transferred to a real excavator. To address measurement inconsistencies in real-world data, a consistency-aware state estimation method based on adaptive Kalman filtering is introduced. Experimental results demonstrate that the learned surrogate achieves high fidelity in both angular velocity and long-horizon trajectory reproduction under closed-loop autoregressive evaluation. These results confirm that the proposed model can serve as a drop-in surrogate for both simulation and physical systems, enabling scalable and efficient development of excavation automation algorithms.

This paper investigates an energy-efficient active stacked intelligent metasurfaces (ASIM)-assisted downlink transmission framework, where a multi-antenna base station (BS) serves multiple users through a multi-layer metasurface architecture. Unlike conventional passive intelligent surfaces, the considered ASIM employs active amplification and multiple transmissive layers to enhance electromagnetic wave manipulation. We aim to maximize the system energy efficiency (EE) by jointly optimizing the BS beamforming and ASIM configurations under user quality-of-service and amplification constraints. The resulting problem is highly coupled and non-convex due to the cascaded near-field channel and multi-layer metasurface structure. To address this challenge, we first transform the original problem through Dinkelbach, Lagrangian dual, and quadratic transformations. An alternative optimization framework is then developed, where the BS beamforming subproblem is solved via successive convex approximation (SCA), while the ASIM configuration is optimized using Bayesian optimization based on a Gaussian process surrogate model. Numerical results demonstrate that the proposed scheme significantly improves the achievable EE compared to conventional passive SIM and heuristic benchmark methods. Furthermore, the impacts of amplification capability, number of metasurface layers, and inter-layer spacing on system performance are investigated, providing useful design insights for future active metasurface-assisted wireless networks.

This paper investigates the energy-efficiency (EE) maximization problem for a multiuser wireless network equipped with six-dimensional movable antennas (6DMAs), where the three-dimensional (3D) positions and orientations of the antennas are jointly optimized to fully exploit the additional spatial degrees of freedom offered by dynamic channel reconfiguration. However, the practical operation of 6DMAs incurs non-negligible mechanical energy consumption. Moreover, orientation-dependent phase variations, together with the strong coupling among antenna positions, rotation angles, transmit beamforming, and time allocation, render the resulting problem highly non-convex and analytically challenging. To address this issue, we develop a block coordinate descent (BCD) optimization framework that integrates Dinkelbach's transformation with the majorization-minimization (MM) approach to efficiently obtain a high quality suboptimal solution with guaranteed convergence. Simulation results unveil that the proposed design achieves significant EE improvements over conventional benchmarks, thereby highlighting the critical importance of accounting for practical mechanical energy costs in 6DMA enabled systems. Furthermore, our results reveal a fundamental trade-off between throughput enhancement and mechanical overhead: although larger antenna reconfigurations can improve channel conditions, their EE gains gradually diminish due to the increased mechanical energy consumption.

A fluid element (FE)-aided stacked intelligent metasurface (FSIM) for multiple-input single-output (MISO) communication system is investigated, where a multi-antenna base station (BS) serves multiple single-antenna users through FSIM. Unlike conventional SIM with fixed meta-atom deployment, the architecture allows the meta-atoms in each layer to move within a predefined fluidic region to further increase the spatial diversity. By jointly optimizing the two-dimensional meta-atom positions, BS transmit beamforming, and FSIM phase-shifts, the cascaded BS-FSIM-user channels can be flexibly reconfigured to enhance the desired signals and suppress multiuser interference. The proposed sum-rate maximization problem is highly non-convex and nonlinear due to the coupled solutions of element position, beamforming, and phase-shift. To address this challenge, an alternating optimization (AO) algorithm is developed to iteratively update these variables. The beamforming and FSIM phase-shift subproblems are transformed into semi-definite programming problems and solved by using successive convex approximation (SCA), first-order Taylor approximation, and penalty-based rank-one relaxation, whilst the FE position subproblem is handled through a projected gradient-based update. Simulation results reveal that a compact FSIM with a small inter-layer thickness is preferable, as increasing the thickness weakens inter-layer coupling and degrades the achievable sum rate. Results also demonstrate that the proposed FSIM significantly outperforms conventional SIMs with fixed positions, patch-based structures, partial fluidity, restricted fluid regions, and existing flexible intelligent metasurfaces. Furthermore, the proposed AO-based algorithm achieves superior rate performance compared to sub-schemes, metaheuristic methods, and conventional beamforming benchmarks.

Audio mixing style encompasses the artistic and technical decisions a mix engineer makes, including level balancing, spatialization, and the choice, ordering, and parameterization of audio effects (FX) on each stem. FX chains are a key determinant of this style, yet existing approaches to modeling them remain limited. Some operate on stereo mixtures without explicit per-stem FX chain modeling, others fix the number or type of effects per track, and many require differentiable effect implementations or scarce multitrack datasets. We present StemFX, a framework that learns mixing style representations by autoregressively predicting variable-length FX chains on source-separated stems. A Transformer decoder predicts tokenized FX chains autoregressively, while a band-split multi-band CNN encoder with FiLM conditioning captures per-stem spectral structure. To enable large-scale paired training, we extract pseudo-stems from about 105K songs via source separation and augment them using MultiAFx, a toolkit unifying 85 audio effects from 7 Python libraries. Evaluated on mixing style retrieval, StemFX outperforms all baseline models across all tested chain lengths. On paired mixing style transfer, StemFX achieves the best spectral fidelity and the highest listener preference, over 4000 times faster than iterative optimization.

Multi-spectral video segmentation is essential for robust scene understanding in unmanned aerial vehicle (UAV) applications such as city planning, land use monitoring, traffic monitoring, and crowd estimation. While the fusion of RGB and thermal modalities offers complementary information for perception under varying lighting and visibility conditions, two fundamental challenges remain: (1) the modal fusion dilemma, arising from significant discrepancies between RGB and thermal features that obscure complementary cues, and (2) temporal variation, induced by rapid motion and viewpoint changes on UAV platforms, which leads to appearance inconsistency and misalignment across frames. To address these issues, this study proposed MSTF-Net, a modality-robust scale-adaptive fusion framework for multi-spectral video segmentation that effectively models cross-modal fusion and temporal consistency. The Modality Spatial Complementary Suppression and Enhancement (MSCSE) module generates unified instance queries via cross-modal attention and suppresses modality-specific noise using residual-guided discrepancy filtering and consistency constraints. To model temporal dynamics, the Multi-scale Temporal Cross-modality Semantic Consistency (MTCSC) module adaptively adjusts the temporal receptive field based on frame distance, capturing both coarse global context and fine local structure across time. Extensive ablation experiments on public RGB-T datasets demonstrate that MSTF-Net achieves state-of-the-art segmentation performance, especially under challenging conditions such as small targets, occlusion, and modality degradation. Specifically, reached 56.42% mIoU on the MVSeg dataset and 51.80% mIoU on the CART dataset, respectively.

Graph signal sampling and reconstruction are commonly formulated in the graph Fourier transform (GFT) domain. However, the reconstruction performance may be limited when practical graph signals are not sufficiently concentrated in the GFT spectrum. To address this issue, this paper proposes a graph signal sampling and reconstruction framework based on the graph fractional Fourier transform (GFRFT) domain. The fractional order is introduced as an adjustable spectral domain parameter, and the optimal order is selected to provide a more suitable representation domain for a given graph signal and sampling model. Under a unified sampling reconstruction formulation, subspace, smoothness, and stochastic priors are incorporated, and both unconstrained and predefined reconstruction mechanisms are considered, leading to several fractional domain sampling and reconstruction methods. Furthermore, the theoretical analysis shows that the optimal GFRFT domain can provide a more suitable low-dimensional spectral representation by improving energy concentration and reducing projection residual. The effects of residual leakage and noise amplification are further considered to explain how this representation advantage is translated into reconstruction error reduction. Experimental results show that, GFRFT domain sampling and reconstruction generally achieve better recovery performance than GFT domain methods.

High-resolution energy data is increasingly central to Industry 4.0, where electrical signals such as three-phase voltage and current carry rich information about machine condition, tool wear, and process dynamics. Capturing this information in practice remains difficult: commercial power analysis are largely proprietary, offer limited or no access to high-sampling rate data for transient analysis, restrict access to raw waveform data, and offer no customization, while general-purpose open hardware lacks the front-end accuracy, isolation, and robustness required for industrial measurement. This paper presents Autonomous Energy Monitoring System (AEMS), an open-source, low-cost, and modular platform supported by a host, edge-gateway, and optional cloud software stack that enables autonomous, long-duration acquisition independent of a continuously connected host and thereby closes this gap by combining research-grade fidelity with industrial deployability. The system acquires three-phase voltage and current through an isolated front-end and a 24-bit, simultaneously sampling analog-to-digital converter, managed by a dual-core architecture that separates deterministic acquisition and on-board logging from host communication and control. Industrial interfaces (Ethernet, RS-485/Modbus, and BLE) together with hardware-level synchronization enable scalable, time-aligned acquisition across multiple machines, supported by a complete host, edge-gateway, and optional cloud software stack. We validate the platform on a three-axis CNC machining center, where it resolves spindle, feed-drive, rapid-traverse, and material-removal energy states and detects feed-rate changes as small as 50 mm/min. By releasing the full hardware and firmware openly, this work aims to democratize access to high-fidelity energy monitoring for both researchers and small and medium-sized manufacturers.

Communication-limited robots in mission-critical scenarios such as disaster inspection and search-and-rescue must make reliable onboard decisions without access to remote operators or high-capacity reasoning services. Episodic memory reuse is an attractive low-cost fallback, but retrieval similarity does not guarantee execution validity, i.e., a retrieved action may match the current context yet be unsafe due to changed topology, insufficient battery margin, or unreliable prior outcomes. We call such high-similarity but execution-invalid episodes memory traps. This creates a safety-efficiency design space where similarity only reuse minimizes fallback cost but can be unsafe, while always invoking local reasoning improves safety at high computational and energy cost. This paper presents MemoGuard, a lightweight adaptive runtime that validates episodic memories against topology, resource, and outcome contracts before reuse, invoking fallback only when validation fails. In a graph-based corridor-inspection simulator, MemoGuard reduces battery safety violations by 76.6% over similarity-only top-1 reuse while reducing fallback calls by 21.4% over always reasoning. On an NVIDIA Jetson AGX Xavier with local llama3.2:3b fallback reasoning, this corresponds to 3.67 s and 36.97 J of avoided fallback-reasoning overhead per trial. We open-source MemoGuard at https://github.com/hetheiin/memoguard.

Persistent aerial surveillance using multi-unmanned aerial systems (UASs) requires decentralized coordination, continuous team reconfiguration, and provable mission correctness despite limited onboard energy and communication constraints. This paper develops a distributed framework for continuous aerial surveillance under bounded Linear Temporal Logic (LTL) mission specifications. The proposed approach partitions the UAS team into stationary anchors and mobile workers operating under cyclic replacement modes, and constructs a deep neural network (DNN)-inspired communication topology that enables fully decentralized coordination through local interactions. A hierarchical bounded LTL specification formally captures mode-to-mode reference consistency, cyclic team rotation, finite-time reachability, trajectory tracking, and prescribed surveillance coverage. By proving the finite-time convergence of the worker-agent coordination dynamics, the paper guarantees the finite-time satisfaction of the mission specification. To maximize sensing effectiveness, an information-theoretic optimization framework synthesizes the reference configuration of newly deployed worker agents by minimizing the Kullback–Leibler divergence between the surveillance-node distribution and the induced coverage density. The resulting reference configuration uniquely determines a deterministic, mode-dependent communication topology, eliminating online communication-graph optimization while preserving the formal mission guarantees. Finally, a decentralized quadrotor controller realizes the distributed references using only local communication. Numerical simulations demonstrate cyclic team reconfiguration, decentralized communication-topology synthesis, finite-time formation convergence, and certified persistent surveillance coverage.

We propose an integrated sensing and communications (ISAC) framework that supports chirp signal transmission in CP-OFDM-based multiple access communication systems, enabling efficient coexistence of communication and sensing capabilities. Our framework employs the discrete Fourier transform phase rotated and permuted frequency division multiple access (DFT-p-FDMA) waveform to transmit chirp signals using a portion of the frequency resources, while ensuring interference-free concurrent CP-OFDM data transmissions on other bands. We analyze the effective channel behavior under the DFT-p-FDMA waveform, characterizing how delays and Doppler shifts impact radar target echoes. We also show how processing multiple received symbols improves Doppler resolution in practical scenarios. Our framework allows flexible adjustment of range-Doppler resolution through optimized time-frequency resource allocation, offering a versatile solution for ISAC applications. Simulation results validate the framework's performance in delay and Doppler estimation, highlighting its potential to support ISAC in next-generation wireless networks.

Battery energy storage systems (BESSs) are widely used in smart grids. However, power consumed by inner impedance and the capacity degradation of each battery unit become particularly severe, which has resulted in an increase in operating costs. The general economic dispatch (ED) algorithm based on marginal cost (MC) consensus is usually a proportional (P) controller, which encounters the defects of slow convergence speed and low control accuracy. In order to solve the distributed ED problem of the isolated BESS network with excellent dynamic and steady-state performance, we attempt to design a proportional integral (PI) controller with a reset mechanism (PI+R) to asymptotically promote MC consensus and total power mismatch towards 0 in this paper. To be frank, the integral term in the PI controller is reset to 0 at an appropriate time when the proportional term undergoes a zero crossing, which accelerates convergence, improves control accuracy, and avoids overshoot. The eigenvalues of the system under a PI+R controller is well analyzed, ensuring the regularity of the system and enabling the reset mechanism. To ensure supply and demand balance within the isolated BESSs, a centralized reset mechanism is introduced, so that the controller is distributed in a flow set and centralized in a jump set. To cope with Zeno behavior and input delay, a dwell time that the system resides in a flow set is given. Based on this, the system with input delays can be reduced to a time-delay free system. Considering the capacity limitation of the battery, a modified MC scheme with PI+R controller is designed. The correctness of the designed scheme is verified through relevant simulations.

We study price-based distributed scheduling of flexible demand in an energy community, where a coordinator broadcasts electricity prices and individual households schedule their consumption. Household demand includes deferrable and non-deferrable loads, such as electric vehicle charging with completion deadlines and thermostatically controlled loads. The coordinator transacts with a distribution utility on behalf of community members under the regulated Net Energy Metering tariff. We formulate distributed demand scheduling as a bilevel stochastic dynamic program. The upper level optimizes the coordinator's pricing policy to minimize the community's energy costs subject to operating, revenue adequacy, and individual rationality constraints. The lower level involves stochastic dynamic programs that maximize households' consumption benefits subject to the availability of renewable generation. The computational cost of such a distributed stochastic dynamic program is prohibitive in general. By uncovering the structure of optimal centralized scheduling, we derive Threshold Pricing Rule (TPR) – a simple community pricing policy with linear computational costs for the upper- and lower-level optimizations. Being independent of parameters of the underlying stochastic dynamic program, TPR is robust against modeling uncertainties and is shown to guarantee revenue adequacy for the community and individual rationality for community members. As the community size grows, TPR is shown to be asymptotically optimal.

Where should the question go in a vision-language model (VLM) prompt: before the image or after it? Intuition says before: knowing what is asked should tell the model where to look. Yet across visual question answering benchmarks, question-first prompting consistently underperforms the image-first ordering recommended for frontier VLMs, a phenomenon we term the question-first paradox. We trace this paradox to a conflict between two stages of VLM computation. Logit-lens and attention probes show that question-first prompting steers perception, shifting image patch representations toward question-relevant concepts. But downstream, stranded behind hundreds of image tokens, the question is barely attended by the answer token, which instead commits to image-driven, often wrong answers. Causal attention knockout confirms that the answer reads the question only when it follows the image. This diagnosis yields a training-free fix: question echoing, restating the question on both sides of the image so one copy steers perception while the other is available at answer time. A similar division of labor appears in a fifty-year-old finding on human 'adjunct questions', where repeating a question before and after a passage improves comprehension. Echoing the image as well brings further gains by restoring the whole-image view otherwise lost by a causal decoder. The paradox holds across five open VLMs, costing up to 17.5 group-accuracy points. Echoed prompts recover most of the gap and, on NaturalBench and Winoground, surpass the best single-pass ordering by up to 19 group-accuracy points on Winoground, with no training, fine-tuning, or architecture change. The paradox reveals a tension between steering what a model sees and preserving access to what it was asked; echoing resolves this through prompt design. Project Page: https://rakshanda-cmu.github.io/ask-twice-look-twice/

Conventional pinching antenna (PA)-assisted integrated sensing and communication (ISAC) architectures typically assume static receiver locations or predetermined receive waveguides, thereby underutilizing the inherent spatial degrees of freedom. This paper proposes a novel mode-selectable PA-assisted ISAC framework to maximize the post-combining sensing signal-to-noise ratio while satisfying multi-user quality-of-service constraints by jointly optimizing the waveguide mode selection, transmit beamforming, and transmit/receive PA positions. To tackle the resulting mixed-integer nonconvex optimization problem, we develop a low-complexity block-coordinate descent algorithm that leverages a penalty-based majorization-minimization method to achieve high-quality suboptimal solutions. Numerical results demonstrate that the proposed design significantly outperforms both traditional PA and fixed-antenna benchmarks by synergistically harnessing spatial adaptability and modal reconfigurability. In particular, the mode-selectable design enables the coordinated optimization of transmit/receive operations and sensing-communication resource allocation, thereby maintaining sensing robustness under stringent communication requirements.

Starlink and other low Earth orbit (LEO) satellite broadband systems are producing increasingly diverse measurement data across regions, time periods, and access conditions. These measurements are valuable for throughput prediction, adaptive bitrate (ABR) evaluation, and network experimentation, but converting continuously arriving data into reusable experimental evidence still relies heavily on manually developed analysis code and expert-guided data inspection and failure-case organization. This paper proposes StarCodex, a dynamic coding harness for Starlink measurement analysis and experiment automation. StarCodex detects analysis gaps from the current measurement state, converts them into structured coding tasks, uses Codex to generate or repair executable analysis artifacts, and accepts artifacts through code, data-interface, measurement-semantics, and output validation. Experiments on real Starlink measurements show that StarCodex discovers 49 of 56 uncovered system-risk cases, attains higher average precision than the strongest predefined analysis baseline, and constructs a benchmark with denser and broader system-risk evidence. The generated prediction and replay artifacts further reveal prediction risks and quality-of-experience (QoE)–risk differences among ABR controllers. These results demonstrate the feasibility of using a dynamic coding harness to convert evolving Starlink measurements into validated analysis artifacts for automated experiment workflows.

A mixed-pitch grating coupler which can couple a wide range of wavelengths is preferred in its application in co-packaged optics (CPO). However, the design and optimization of such grating coupler is complex. In this work, we developed software with integrated deep neural network (DNN) model to automatically design the mixed-pitch grating coupler from user-specified peak wavelengths and full-width half-maximum (FWHM) values. We first trained the DNN model with 10,000 rows of grating parameters-power spectrum datasets, where the power spectrum was simulated using finite-difference time domain (FDTD) technique. Upon training, we tested the model using ~1,000 different combinations of peak wavelengths and FWHM values. Among the combinations, 822 attempts have <15% error, while 351 attempts have <5% error when comparing the user-specified and FDTD-verified spectrum. Meanwhile, comparing the user-specified and FDTD-verified peak wavelengths, 844 attempts have peak wavelengths with absolute error (AE) < 2 nm. For FWHMs, 738 attempts have FWHM values with AE < 10 nm. We have also developed a graphical-user interface (GUI) to ease the usage of this software.

Ambivalence and hesitancy (A/H) are subtle behavioural states that can be expressed through both what a person says and how it is spoken. This paper presents an audio–text framework for video-level A/H recognition. Full-video transcripts and speech waveforms are encoded using pre-trained multilingual BERT and wav2vec~2.0, respectively, and projected into a shared representation space. Two stacked bidirectional cross-attention blocks allow linguistic tokens to attend to acoustic frames and acoustic frames to attend to linguistic context without requiring explicit temporal alignment. The resulting sequences are aggregated through masked mean pooling and combined using concatenation, element-wise products, and absolute differences for binary classification. We evaluate the model on the subject-independent split of the Behavioural Ambivalence/Hesitancy (BAH) dataset. The proposed system achieves 72.19% accuracy, 75.00% precision, 81.13% recall, 77.95% A/H F1-score, and 70.16% Macro-F1 on the test set. These results demonstrate the potential of jointly modelling linguistic and acoustic information for automatic A/H recognition.code at:https://github.com/DorriG/ECCV.

Audio-driven digital human generation plays an important role in virtual communication, immersive interaction, and media production. With the development of Neural Radiance Fields (NeRF) and 3D Gaussian Splatting (3DGS), recent talking-head systems have obtained more faithful 3D facial geometry and appearance modeling. A remaining difficulty is that speech features mainly describe temporal acoustic patterns rather than explicit facial layouts. As a result, directly driving 3D facial deformation with audio may produce inaccurate mouth motion, weak expression details, and local artifacts. To address this issue, we propose a facial-keypoint-guided spatial enhancement module. The predicted landmarks provide structural cues for selecting and enriching spatial points around expression-sensitive facial regions. We further introduce a global landmark compensation mechanism, where the full set of keypoints is encoded into a conditioning vector to refine 3DGS attributes. This compensation supplies whole-face structural information to the underlying shape representation. Experiments under self-driven and cross-driven settings show that the proposed method improves visual quality, facial realism, and lip synchronization.

Audio-Visual Navigation (AVN) requires an agent to localize and navigate toward a continuously vocalizing target relying solely on visual observations and acoustic cues. Currently, systems lack the ability to adaptively correct and replan when faced with incomplete or misleading visual perception. Furthermore, relying on physical collisions to compensate for missing visual information results in inefficient and unsafe navigation, whereas existing methods are overly dependent on passive visual perception. To address these issues, we propose the Transformer-based Token Fusion and Dynamic Graph Planning (TDGP) model, which incorporates high-level perception layers and leverages the Transformer model to fuse multimodal cues for precise local planning. Next, a low-level planning layer is designed that uses physical collision penalties to remove edges that collide with the map in real time and apply corresponding penalties, forcing the agent to automatically re-plan to compensate for the lack of visual information. Experiments show that our TDGP model outperforms baseline models on the Replica and Matterport3D (MP3D) datasets, and that the model's sound enhancement strategy significantly improves generalization in unheard acoustic scenarios.

Hallucination and abstention benchmarks rarely establish that a model could not have known the correct answer, making it difficult to distinguish appropriate abstention from an unsupported prediction. Seven large language models were evaluated on the TAME Pain speech corpus. Participants read phonetically balanced Harvard Sentences while one hand was immersed in cold or warm water and reported pain only during periodic pain statements. This protocol generated 5,750 no signal Harvard Sentence utterances whose transcripts contained no lexical pain information and 1,294 signal pain statement utterances in which the pain rating was explicitly spoken. In the no signal arm, pain was recoverable from acoustic features (AUC 0.622, 95% CI 0.553 to 0.662), whereas transcript based prediction was near chance (AUC 0.489, 95% CI 0.418 to 0.504). Because automatic speech recognition removes the acoustic pain cues, any pain score inferred solely from the transcript is unsupported by the available evidence. Under cooperative prompting, six models abstained on nearly all no signal transcripts, correctly extracted spoken pain ratings in the positive control task with accuracies ranging from 0.939 to 1.00, and maintained an expected calibration error of at most 0.100. Under authority framed prompts, abstention became prompt dependent, with the same model ranging from 0.18 to 1.00 across equivalent prompt phrasings. Most models produced low confidence estimates when forced to answer, whereas Gemini 2.5 Flash and Llama 3.1 8B consistently generated confident pain scores with confident fabrication rates of 0.53 and 0.76, compared with at most 0.15 for all other models. No significant demographic effects were observed in forced responses, with all $p$ values greater than or equal to 0.20.