arXiv:2505.01804v2 Announce Type: replace Abstract: Air traffic can be significantly disrupted by weather. Pathfinder operations involve assigning a designated aircraft to assess whether airspace that was previously impacted by weather can be safely traversed through. Despite relatively routine use in air traffic control, there is little research on the underlying multi-agent decision-making problem. We seek to address this gap herein by formulating decision models to capture the operational dynamics and implications of pathfinders. Specifically, we construct a Markov chain to represent the stochastic transitions between key operational states (e.g., pathfinder selection). We then analyze its steady-state behavior to understand long-term system dynamics. We also propose models to characterize flight-specific acceptance behaviors (based on utility trade-offs) and pathfinder selection strategies (based on sequential offer allocations). We then conduct a worst-case scenario analysis that highlights risks from collective rejection and explores how selfless behavior and uncertainty affect system resilience. Empirical analysis of data from the US Federal Aviation Administration demonstrates the real-world significance of pathfinder operations and informs future model calibration.
Science Journals
arXiv:2505.13225v2 Announce Type: replace Abstract: Neural network pruning aims to compress models for efficient deployment, yet two fundamental challenges remain. First, many methods rely on per-component importance scores, selecting filters or neurons independently and ignoring redundancy: the retained set may include multiple components capturing similar discriminative patterns while missing others entirely. Second, determining per-layer pruning ratios typically requires manual, architecture-specific tuning with no principled stopping criterion. We propose CoSeP (Complementary Separability Pruning) to address both issues. Rather than scoring components in isolation, CoSeP represents each component by its class-separability profile across all class pairs, computed via Jeffries--Matusita distances. This defines a separability space in which nearby components are potentially redundant and distant components capture complementary information. CoSeP selects a compact set of representatives in this space: components are grouped via k-medoids clustering, candidate subset sizes are evaluated using the Mean Simplified Silhouette, and a knee-detection criterion automatically determines how many components to retain. Across CIFAR-10, CIFAR-100, and ImageNet-1K, on ResNet, VGG, MobileNet, and DenseNet architectures, CoSeP matches or improves accuracy while reducing FLOPs, with measured wall-clock inference-time reductions of up to 20%. For example, it achieves a +0.66% top-1 accuracy gain with 2.30x FLOPs reduction on ResNet-50/ImageNet-1K, and a 0.37% gain with 2.59x FLOPs reduction on VGG-16/CIFAR-10. These results demonstrate that modeling complementarity in class-separability space provides an effective and principled approach to pruning.
arXiv:2506.01052v3 Announce Type: replace Abstract: We investigate the finite-time convergence properties of Temporal Difference (TD) learning with linear function approximation, a cornerstone of reinforcement learning. We are interested in the so-called ``robust'' setting, where the convergence guarantee does not depend on the potential function's minimal curvature. While prior work has established convergence guarantees in this setting, these results typically rely on the artificial assumption that each iterate is projected onto a bounded set. Removing such a condition was left as an open problem by Bhandari et al. (COLT'18), hypothesizing the need for additional ``regularity conditions''. In this paper, we show that the simple unprojected TD(0) converges with a rate of $\widetilde{\mathcal{O}}\left(\frac{\|\theta^*\|^2_2}{\sqrt{T}}\right)$ in expectation, even in the presence of Markovian noise. We do not require an additional regularity condition, but only a minor polylog correction to the learning rate. Our analysis reveals a novel self-bounding property of the TD updates and exploits it to guarantee bounded iterates.
arXiv:2506.20699v2 Announce Type: replace Abstract: Learning in non-stationary and multi-context environments requires more than ordinary within-task generalization. A system must also discover which contexts exist, route inputs to the correct context, preserve old contexts, and revise the context library when the environment changes. This paper presents Structural Learning Theory (StrLT) as a framework of filling this missing structural gap. StrLT complements Vapnik's Statistical Learning Theory (SLT): SLT governs the \emph{funnel}, prediction or control within a fixed regime; while StrLT governs the \emph{trap}, the discovery and maintenance of structural regimes. The core StrLT object is \emph{width}, the minimum number of locally feasible contexts needed to cover a problem. We summarize three basic results: width is incomparable with VC dimension; learning exhibits a phase transition at the true width; and width can be estimated by a contractive-similarity (CS) operator that converts task-induced non-contractivity into spectral separation. Under the StrLT framework, we explain how fixed-class structural learnability leads to a \emph{structural decoupling principle}: the mechanisms that maintain the structural scaffold should not be trained by the same gradients that optimize within-context flow. This principle motivates a scaffold-flow model in which alignment and generalization separate architecturally. Finally, we argue that several safety failures, including hallucination, reward-model boundary errors, and deceptive alignment, can be interpreted as scaffold-resolution or scaffold-preservation failures rather than merely output-level prediction errors.
arXiv:2506.22614v3 Announce Type: replace Abstract: We present a framework based on computer-assisted proofs that turns geometry optimization simulations for atomistic structures into mathematical proofs. Starting from a numerically computed approximation of a local minimizer or saddle point, we use validated numerical computations to prove the existence of a critical point of the potential energy close to this approximation. We demonstrate this framework in two settings. In the first, we study capped carbon nanotubes modeled as minimizers of carbon interatomic potentials (harmonic, Tersoff, and a Huber potential) and obtain proven bounds on tube diameter, bond lengths, and bond angles. In particular, we show that caps induce diameter oscillations along the tube. As a second application, we consider a finite Lennard-Jones crystal in a face-centered cubic (fcc) lattice and provide computer-assisted proofs of a local minimizer representing the perfect crystal, a local minimizer with a single vacancy defect, and a saddle point that connects two single-vacancy configurations on the energy landscape.
arXiv:2507.09751v3 Announce Type: replace Abstract: Large language models (LLMs) have demonstrated impressive capabilities in natural language understanding and generation, but exhibit problems with logical consistency in their output. How can we harness LLMs' broad-coverage parametric knowledge in formal reasoning despite their inconsistency? We present a method for directly integrating an LLM into the interpretation function of the formal semantics for a paraconsistent logic. We evaluate the method empirically using datasets derived from the short-form factuality benchmarks GPQA and SimpleQA, showing that bilateral factuality evaluation improves macro-F1 over a unilateral baseline by roughly 6 percentage points on both benchmarks (at the cost of reduced coverage, as abstention is triggered on inconsistent or uncertain cases). We further describe a proof-of-concept tableau reasoner implementing the method, and apply it to a medication-safety knowledge base of 228 asserted and 712 inferred statements: the system detects 92 gluts corresponding to medically significant errors (e.g., opioids inferred as non-addictive, beta-blockers inferred as safe in asthma) while remaining satisfiable, demonstrating that contradictions are localized rather than causing logical explosion. Unlike prior work, our method offers a theoretical framework with a practical implementation for neurosymbolic reasoning that leverages an LLM's knowledge while preserving the underlying logic's soundness and completeness properties.
arXiv:2507.12069v3 Announce Type: replace Abstract: Taylor's hypothesis (TH) converts temporal observations to spatial information of the flow while carrying out measurements on a micrometeorological tower. Other than TH, there exists a more general elliptic model, which converts time to space by focusing on the geometry of the space-time correlation function. In elliptic model, TH is recovered when the space-time correlation functions are straight lines and when TH is invalid, they are approximated as elliptic curves. To test whether TH or an elliptic model was appropriate for a highly heterogeneous forest clearcut flow, we examined the geometry of the space-time correlation function of temperature by using an extensive distributed temperature sensing (DTS) dataset collected during buoyant conditions at a height of 3.1 m above the clearing. This was complemented with an eddy covariance (EC) dataset that measured the turbulence characteristics. When the mean wind was parallel to a nearby forest edge, the DTS-derived space-time correlation function of temperature fluctuations resembled elliptic curves, rather than straight lines as predicted by TH. Due to large turbulence intensities, the curvatures in the space-time correlation contours were caused by the random sweeping events associated with large scale eddies that invalidated the frozen turbulence assumption in TH. The velocity scale of these sweeping events correlated with the turbulence kinetic energy of the clearcut flow, thereby lending support to the random sweeping hypothesis. Upon converting time to space through an elliptic and TH-based scaling, our results demonstrated that both temporal DTS and EC temperature measurements were impacted by the random sweeping events.
arXiv:2508.00724v2 Announce Type: replace Abstract: The increasing demand for flexible automation has accelerated the adoption of heterogeneous automated guided vehicles (AGVs). This work investigates a new scheduling problem in a material transportation system consisting of attachable heterogeneous AGVs, including carriers and shuttles, that flexibly attach and detach for cooperative task execution. While such collaboration enhances operational efficiency, the attachment-induced synchronization renders the system highly coupled and susceptible to deadlocks. To address this, we propose a Petri net (PN)-based deadlock-free scheduling framework integrated into an adaptive large neighborhood search (ALNS) algorithm. The PN is introduced to map candidate solutions from static permutations into dynamic collaborative processes, enabling performance evaluation via state evolution and proactive deadlock prevention through structural analysis. Extensive experiments on real-world and synthetic instances demonstrate that the proposed framework significantly improves computational efficiency, with the developed ALNS outperforming the current on-site policy, exact solvers, and state-of-the-art metaheuristics. Finally, sensitivity analysis yields managerial insights for optimal fleet sizing.
arXiv:2508.05950v2 Announce Type: replace Abstract: We propose CLONE, a 3DGS-based Closed-Loop differentiable Optimization framework for single-image Normal Estimation. The core idea is to construct an "image-geometry-image" consistency loop that unifies and jointly constrains the limitations of both paradigms: the reliance on explicit supervision without cross-domain geometric constraints in discriminative methods, and the absence of stable differentiable optimization pathways in generative methods despite strong generative priors. Specifically, we first employ 3D Gaussian Splatting to explicitly parameterize the scene and derive continuous and differentiable surface normals via covariance eigen-decomposition, providing an analytical gradient pathway for geometric modeling. We then introduce a differentiable illumination model with a learnable light modulation kernel to establish a continuous mapping between surface normals and image radiance, enabling reprojection errors to directly supervise the underlying 3D geometry. Furthermore, to compensate for the limited local detail expressiveness of Gaussian representations, we design a one-step deterministic diffusion-inspired refinement network, which enhances local geometric details while preserving end-to-end differentiability. A cross-domain gating fusion mechanism is introduced to coordinate global geometric consistency and local detail reconstruction. Finally, all components are jointly optimized under a unified reprojection objective, forming a closed-loop and stable gradient propagation pathway. This enables effective constraint of the multi-solution space and improved geometric consistency without requiring ground-truth normal supervision.
arXiv:2508.07011v5 Announce Type: replace Abstract: Creating ultra-high-resolution spatially varying bidirectional reflectance functions (SVBRDFs) is critical for photorealistic 3D content creation, to faithfully represent fine-scale surface details required for close-up rendering. However, achieving 4K generation faces two key challenges: (1) the need to synthesize multiple reflectance maps at full resolution, which multiplies the pixel budget and imposes prohibitive memory and computational cost, and (2) the requirement to maintain strong pixel-level alignment across maps at 4K, which is particularly difficult when adapting pretrained models designed for the RGB image domain. We introduce HiMat, a diffusion-based framework tailored for efficient and diverse 4K SVBRDF generation. To address the first challenge, HiMat performs generation in a high-compression latent space via DC-AE, and employs a pretrained diffusion transformer with linear attention to improve per-map efficiency. To address the second challenge, we propose CrossStitch, a lightweight convolutional module that enforces cross-map consistency without incurring the cost of global attention. Our experiments show that HiMat achieves high-fidelity 4K SVBRDF generation with superior efficiency, structural consistency, and diversity compared to prior methods. Beyond materials, our framework also generalizes to related applications such as intrinsic decomposition.
arXiv:2508.08572v2 Announce Type: replace Abstract: Concrete is the most widely used construction material globally. Despite its versatility, it is typically poured into stiff, rectilinear formwork that restricts formal exploration and leads to considerable material waste and higher carbon output. Fabric formwork offers an alternative in which flexible textiles shape fresh concrete into structurally efficient geometries such as thin shells and catenary arches. However, a persistent challenge remains that forms optimized in tension under gravity often crack when rotated into their final compression orientation. Previous research has focused on form-finding and fabrication workflows, with little attention to damage-free reorientation. This paper addresses this gap through two contributions: a CNC-milled repositionable frame with soft-to-rigid connection details enabling controlled tilt-up reorientation without damage, and a scalar reframing that embeds small repeating catenary units within larger building components such as walls and slabs. The research pursues three objectives: (1) to design and refine compatible textile-concrete combinations, with particular focus on non-woven geotextiles; (2) to develop a CNC-cut, repositionable frame system that redistributes stresses during reorientation; and (3) to devise robust soft-to-rigid connection details that permit safe demolding and handling. Through material testing and iterative prototyping, the study identifies concrete paste-geotextile pairings that produce high-quality surface finishes. A tilt-up method was developed where the frame rotates with the arch, minimizing tensile stress. Results demonstrate that catenary arches can be cast, released, and reoriented without cracking or damage. These findings advance fabric-formed concrete toward low-tech, materially efficient structures with reduced environmental impact.
Breaking the Curse of Knowledge: Designing Personalized Jargon Support for Real-Time Online Meetings
arXiv:2508.10239v3 Announce Type: replace Abstract: Cross-disciplinary communication is often hindered by specialized language (i.e., jargon) and uneven background knowledge. Recent advances in speech-to-text and large language models make it possible to provide jargon support during online meetings, but generic support (i.e., defining the same terms for everyone) can overwhelm listeners with definitions they do not need. We present ParseJargon, a system for personalized jargon support in real-time online meetings. We begin with an initial prototype to probe the use of single-sentence user profiles for personalization. We conducted a controlled study and showed that even this minimal personalization enhanced listeners' comprehension and engagement over generic support because of more precise jargon identification. Guided by insights from participants' feedback, we refined the system with more advanced personalization techniques, including in-session user feedback and portable glossary-based profiles. We evaluated how these techniques can further improve jargon identification precision using data collected in the controlled study to simulate personalization over time. We also conducted a latency test, complemented by a lightweight deployment, to analyze the system's real-time capability and usability.
arXiv:2508.19857v3 Announce Type: replace Abstract: Many successful families of generative models leverage a low-dimensional latent distribution that is mapped to a data distribution. Though simple latent distributions are often used, the choice of distribution has a strong impact on model performance. Recent experiments have suggested that the probability distributions produced by quantum processors, which are typically highly correlated and classically intractable, can lead to improved performance on some datasets. However, when and why latent distributions produced by quantum processors can improve performance, and whether these improvements are connected to quantum properties of these distributions, are open questions that we investigate in this work. We show in theory that, under certain conditions, these "quantum latent distributions" enable generative models to produce data distributions that classical latent distributions cannot efficiently produce. We provide intuition as to the underlying mechanisms that could explain a performance advantage on real datasets. Based on this, we perform extensive benchmarking on a synthetic quantum dataset and the QM9 molecular dataset, using both simulated and real photonic quantum processors. We find that the statistics arising from quantum interference lead to improved generative performance compared to classical baselines, suggesting that quantum processors can play a role in expanding the capabilities of deep generative models.
arXiv:2508.20734v2 Announce Type: replace Abstract: Accurate cardiac motion estimation from cine cardiac magnetic resonance (CMR) images is vital for assessing cardiac function and detecting its abnormalities. Existing methods often struggle to accurately capture heart motion because they rely on intensity-based image registration similarity losses that may overlook cardiac anatomical regions. To address this, we propose CardioMorphNet, a recurrent Bayesian deep learning framework for 3D cardiac shape-guided deformable registration using short-axis (SAX) CMR images. It employs a recurrent variational autoencoder to model spatio-temporal dependencies across the cardiac cycle, along with two posterior models for bi-ventricular segmentation and motion estimation. The derived loss function from the Bayesian formulation guides the framework to focus on anatomical regions by recursively registering segmentation maps without using intensity-based image registration similarity loss, while leveraging sequential SAX volumes and spatio-temporal features. The Bayesian modelling also enables the computation of uncertainty maps for the estimated motion fields. Validated on the UK Biobank and M&M datasets by comparing warped mask shapes with ground-truth masks, CardioMorphNet demonstrates superior performance in cardiac motion estimation, outperforming state-of-the-art methods. Uncertainty assessment shows that it also yields lower uncertainty values for estimated motion fields in the cardiac region compared with other probabilistic-based cardiac registration methods, indicating higher confidence in its predictions. In addition, the clinical indices extraction assessment shows that CardioMorphNet estimates the clinical indices more accurately than other approaches.
arXiv:2605.16972v2 Announce Type: replace Abstract: Cultural heritage exhibitions often struggle to sustain attention and support reflective engagement. Physical exhibitions rely on fixed interpretive aids that lack adaptability to individual backgrounds or curiosity, and their effectiveness depends heavily on a visitor's Personal Context, prior knowledge, and cultural literacy. Meanwhile, digital exhibitions prioritize convenience and accessibility but risk weakening the Physical and Social Contexts that define embodied cultural experience. WhiteTesseract addresses this gap by enabling in-situ interpretation through high-resolution XR and conversational AI. The system integrates spatial intelligence via artwork recognition to allow visitors to selectively reduce environmental distractions (via diminished reality) and engage in context-aware dialogue (via large language models). The goal is to preserve the richness of the physical and social environment while providing a flexible space for personal reflection, enhancing Personal Context without compromising physical authenticity. We deployed the system in a Claude Monet exhibition and conducted a controlled user study with 26 participants. Quantitative results showed that WhiteTesseract modulation significantly increased average viewing duration from 35.3 to 98.3 seconds (p < 0.001). Analysis of 529 visitor-AI interactions revealed that 60% extended beyond factual queries to include analytical, emotional, and comparative inquiries. These findings demonstrate how XR and AI can enrich the physical exhibition experience by supporting deeper, more personalized engagement without displacing the embodied value of cultural heritage. We discuss technical and social constraints for real-world deployment and limitations of our controlled setting.
arXiv:2509.15017v2 Announce Type: replace Abstract: Accurate brain tumor segmentation is essential for preoperative evaluation and personalized treatment. Multi-modal MRI is widely used due to its ability to capture complementary tumor features across different sequences. However, in clinical practice, missing modalities are common, limiting the robustness and generalizability of existing deep learning methods that rely on complete inputs, especially under non-dominant modality combinations. To address this, we propose AdaMM, a multi-modal brain tumor segmentation framework tailored for missing-modality scenarios, centered on knowledge distillation and composed of three synergistic modules. The Graph-guided Adaptive Refinement Module explicitly models semantic associations between generalizable and modality-specific features, enhancing adaptability to modality absence. The Bi-Bottleneck Distillation Module transfers structural and textural knowledge from teacher to student models via global style matching and adversarial feature alignment. The Lesion-Presence-Guided Reliability Module predicts prior probabilities of lesion types through an auxiliary classification task, effectively suppressing false positives under incomplete inputs. Extensive experiments on the Pretreat-MetsToBrain-Masks and BraTS 2018, 2024 datasets demonstrate that AdaMM consistently outperforms existing methods, exhibiting superior segmentation accuracy and robustness, particularly in single-modality and weak-modality configurations. In addition, we conduct a systematic evaluation of six categories of missing-modality strategies, supporting the superiority of knowledge distillation and offering practical guidance for method selection and future research. Our source code is available at https://github.com/Quanato607/AdaMM.
arXiv:2509.16136v5 Announce Type: replace Abstract: Designing effective reward functions remains a major challenge in reinforcement learning (RL), often requiring considerable human expertise and iterative refinement. Recent advances leverage Large Language Models (LLMs) for automated reward design, but these approaches are limited by hallucinations, reliance on human feedback, and challenges with handling complex, multi-step tasks. In this work, we introduce Reward Evolution with Graph-of-Thoughts (RE-GoT), a novel bi-level framework that enhances LLMs with structured graph-based reasoning and integrates Visual Language Models (VLMs) for automated rollout evaluation. RE-GoT first decomposes tasks into text-attributed graphs, enabling comprehensive analysis and reward function generation, and then iteratively refines rewards using visual feedback from VLMs without human intervention. Extensive experiments on 10 RoboGen and 4 ManiSkill2 tasks demonstrate that RE-GoT consistently outperforms existing LLM-based baselines. On RoboGen, our method improves average task success rates by 32.25%, with notable gains on complex multi-step tasks. On ManiSkill2, RE-GoT achieves an average success rate of 93.73% across four diverse manipulation tasks, significantly surpassing prior LLM-based approaches and even exceeding expert-designed rewards. Our results indicate that combining LLMs and VLMs with graph-of-thoughts reasoning provides a scalable and effective solution for autonomous reward evolution in RL.
arXiv:2509.17078v3 Announce Type: replace Abstract: While one-stage detectors like YOLOv8 offer fast training speed, they often under-perform on detecting small objects as a trade-off. This becomes even more critical when detecting tiny objects in aerial imagery due to low-resolution targets and cluttered backgrounds. To address this, we introduce four enhancement strategies-input image resolution adjustment, data augmentation, attention mechanisms, and an alternative gating function for attention modules-that can be easily implemented on YOLOv8. We demonstrate that image size enlargement and the proper use of augmentation can lead to enhancement. Additionally, we designed a Mixture of Orthogonal Neural-modules Network (MoonNet) pipeline which consists of multiple attention-module-augmented CNNs. Two well-known attention modules, Squeeze-and-Excitation (SE) Block and Convolutional Block Attention Module (CBAM), were integrated into the backbone of YOLOv8 to form the MoonNet design, and the MoonNet backbone obtained improved detection accuracy compared to the original YOLOv8 backbone and single-type attention-module-augmented backbones. MoonNet further proved its adaptability and potential by achieving state-of-the-art performance on a tiny-object benchmark when integrated with the YOLC model. Our code is available at: https://github.com/Kihyun11/MoonNet
arXiv:2509.17455v2 Announce Type: replace Abstract: State-of-the-art NLP benchmarks require interpretation of natural language that specifies conditions, procedures, and exceptions, often relying on implicit assumptions and external knowledge. Constructing complete semantic representations with proof-theoretic guarantees is frequently impractical at scale, and purely text-based reasoning offers limited means of inspection. This paper asks how much understanding of benchmark language can be achieved when formal semantic guarantees are weakened. We investigate this question by extracting computables: executable representations whose runtime behavior provides operational evidence of semantic adequacy, including executability, execution traces, and runtime failures. We induce and iteratively refine computables for benchmark instances using retrieval from external knowledge. Across mathematical reasoning, multi-step reasoning, causal inference, and rule- and exception-heavy legal and biomedical benchmarks, we find that the proposed approach consistently exceeds text-only reasoning and one-shot code execution. Beyond accuracy, our analyses show that these computables provide scalable, inspectable semantic evidence: they expose conditions and exceptions benchmark language forces into executable form, offering a practical bridge between proof-oriented semantics and purely textual reasoning.
arXiv:2509.20714v2 Announce Type: replace Abstract: In this paper we show that cryptographic backdoors in a neural network (NN) can be highly effective in two directions, namely mounting the attacks as well as in presenting the defenses as well. On the attack side, a carefully planted cryptographic backdoor enables powerful and invisible attack on the NN. Considering the defense, we present applications: first, a provably robust NN watermarking scheme; second, a protocol for guaranteeing user authentication; and third, a protocol for tracking unauthorized sharing of the NN intellectual property (IP). From a broader theoretical perspective, borrowing the ideas from Goldwasser et. al. [FOCS 2022], our main contribution is to show that all these instantiated practical protocol implementations are provably robust. The protocols for watermarking, authentication and IP tracking resist an adversary with black-box access to the NN, whereas the backdoor-enabled adversarial attack is impossible to prevent under the standard assumptions. While the theoretical tools used for our attack is mostly in line with the Goldwasser et. al. ideas, the proofs related to the defense need further studies. Finally, all these protocols are implemented on state-of-the-art NN architectures with empirical results corroborating the theoretical claims. Further, one can utilize post-quantum primitives for implementing the cryptographic backdoors, laying out foundations for quantum-era applications in machine learning (ML).
arXiv:2509.22497v2 Announce Type: replace Abstract: Fluid antenna system (FAS) is emerging as a key technology for enhancing spatial flexibility and sensing accuracy in future wireless systems. This paper investigates an unmanned aerial vehicle (UAV)-enabled FAS for multi-target wireless sensing in low-altitude wireless consumer networks (LAWCNs) for achieving the low-altitude economy (LAE) missions. We formulate an optimization problem aimed at minimizing the average Cram\'er-Rao bound (CRB) for multiple target estimations. To tackle this non-convex problem, an efficient alternating optimization (AO) algorithm is proposed, which jointly optimizes the UAV trajectory, the antenna position of the transmit fluid antennas (FAs) and the receive FAs, and the transmit beamforming at the UAV. Simulation results demonstrate significant performance improvements in estimation accuracy and sensing reliability compared to conventional schemes, e.g., the fixed position antenna scheme. The proposed system achieves enhanced sensing performance through adaptive trajectory design and beamforming, alongside effective interference suppression via the flexible FAS antenna repositioning, underscoring its practical potential for precision sensing in the UAV-enabled LAWCNs.
arXiv:2509.24189v4 Announce Type: replace Abstract: Large Language Models (LLMs) are increasingly used to model user preferences, with the typical output as a directly-generated ranked item list per user. However, this generative paradigm inherits the bias and opacity of autoregressive decoding. It over-emphasizes frequent (head) preferences and suppresses minority, long-tail ones. To address this, we propose SPECTRA (Softmax Probing for Extracted Category-level Token Readouts and Analysis), which treats the finetuned LLM as an implicit probabilistic model and probes its softmax to infer a probability distribution over semantically interpretable preference categories. We evaluate SPECTRA on MovieLens, Yelp, and a large-scale short-video platform. SPECTRA delivers (i) distributional alignment, reducing Jensen-Shannon divergence to the empirical preference distribution by 38 to 44 percent across public datasets; (ii) long-tail recovery with cross-user fairness, raising top-3 category exposure entropy by 23 percent on MovieLens and producing a larger gain on tail-preference users than on head-preference users; and (iii) downstream application value, with a 41 to 46 percent category-NDCG boost on MovieLens and Yelp, and a 7x improvement on long-tail category ranking on a large-scale deployment against a head-optimized production ranker.
arXiv:2509.24531v2 Announce Type: replace Abstract: Diffusion Bridge and Flow Matching have both demonstrated compelling empirical performance in transformation between arbitrary distributions. However, there remains confusion about which approach is generally preferable, and the substantial discrepancies in their modeling assumptions and practical implementations have hindered a unified theoretical account of their relative merits. We have, for the first time, provided a unified theoretical and experimental validation of these two models. We recast their frameworks through the lens of Stochastic Optimal Control and prove that the cost function of the Diffusion Bridge is lower, guiding the system toward more stable and natural trajectories. Simultaneously, from the perspective of Optimal Transport, interpolation coefficients $t$ and $1-t$ of Flow Matching become increasingly ineffective when the training data size is reduced. To corroborate these theoretical claims, we propose a novel, powerful architecture for Diffusion Bridge built on a latent Transformer, and implement a Flow Matching model with the same structure to enable a fair performance comparison in various experiments. Comprehensive experiments are conducted across Image Restoration, Translation, and Style Transfer tasks, systematically varying both the distributional discrepancy (different difficulty) and the training data size. Extensive empirical results align perfectly with our theoretical predictions and allow us to delineate the respective advantages and disadvantages of these two models. Our code is available at https://github.com/zhukaizhen/diffusion_bridge_flow_matching.
arXiv:2509.24762v3 Announce Type: replace Abstract: Modeling event sequences of multiple event types with marked temporal point processes (MTPPs) provides a principled way to uncover governing dynamical rules and predict future events. Current neural network approaches to MTPP inference rely on training separate, specialized models for each target system. We pursue a radically different approach: drawing on amortized inference and in-context learning, we pretrain a deep neural network to infer, in-context, the conditional intensity functions of event histories from a context defined by sets of event sequences. Pretraining is performed on a large synthetic dataset of MTPPs sampled from a broad distribution of Hawkes processes. Once pretrained, our Foundation Inference Model for Point Processes (FIM-PP) can estimate MTPPs from real-world data without any additional training, or be rapidly finetuned to target systems. Experiments show that this amortized approach matches the performance of specialized models on next-event prediction across common benchmark datasets.
arXiv:2510.06052v2 Announce Type: replace Abstract: Reasoning models enhance performance by tackling problems in a step-by-step manner, decomposing them into sub-problems and exploring long chains of thought before producing an answer. However, applying extended reasoning to every step introduces substantial redundancy, as sub-problems vary widely in difficulty and complexity: a small number of pivotal steps are genuinely challenging and decisive for the final answer, while many others only involve straightforward revisions or simple computations. Therefore, a natural idea is to endow reasoning models with the ability to adaptively respond to this variation, rather than treating all steps with the same level of elaboration. To this end, we propose MixReasoning, a framework that dynamically adjusts the depth of reasoning within a single response. The resulting chain of thought then becomes a mixture of detailed reasoning on difficult steps and concise inference on simpler ones. Experiments on GSM8K, MATH-500, and AIME show that MixReasoning shortens reasoning length and substantially improves efficiency without compromising accuracy.