arXiv:2603.22570v2 Announce Type: replace
Abstract: Active computer vision promises efficient, biologically plausible perception through sequential, localized glimpses, but lacks scalable general-purpose architectures and pretraining pipelines, leaving Active-Vision Foundation Models (AVFMs) underexplored. We introduce CanViT, the first task- and policy-agnostic AVFM. CanViT uses scene-relative RoPE to bind a retinotopic Vision Transformer backbone and a spatiotopic scene-wide latent workspace, the canvas. Efficient interaction with this high-capacity working memory is supported by Canvas Attention, a novel asymmetric cross-attention mechanism. We decouple thinking (backbone-level) and memory (canvas-level), eliminating canvas-side self-attention and fully-connected layers to achieve fast sequential inference and scalability to high output resolutions. We propose a label-free active vision pretraining scheme, policy-agnostic passive-to-active dense latent distillation: reconstructing scene-wide DINOv3 embeddings from sequences of low-resolution glimpses with randomized locations, zoom levels, and lengths. We pretrain CanViT-B from a random initialization on 13.2 million ImageNet-21k scenes--an order of magnitude more than previous active models--and 1 billion random glimpses, in 166 hours on a single H100. On ADE20K segmentation, a frozen CanViT-B achieves 38.5% mIoU in a single low-resolution glimpse, outperforming the best active model's 27.6% with 20x fewer inference FLOPs as well as its FLOP- or input-matched DINOv3 teacher. Given additional glimpses, CanViT-B reaches 45.9% ADE20K mIoU. On ImageNet-1k classification, CanViT-B also sets a new active-vision state of the art, with 84.5% top-1 accuracy after fine-tuning. CanViT generalizes to longer rollouts, larger scenes, and new policies. Our work narrows the wide gap between passive and active computer vision, demonstrating the potential of task- and policy-agnostic AVFM pretraining.
Science Journals
arXiv:2601.13839v2 Announce Type: replace
Abstract: Social media imagery provides a low-latency source of situational information during natural and human-induced disasters, enabling rapid damage assessment and response. While Visual Question Answering (VQA) has shown strong performance in general-purpose domains, its suitability for the complex and safety-critical reasoning required in disaster response remains unclear. We introduce DisasterVQA, a benchmark dataset designed for perception and reasoning in crisis contexts. DisasterVQA consists of 1,395 real-world images and 4,405 expert-curated question-answer pairs spanning diverse events such as floods, wildfires, and earthquakes. Grounded in humanitarian frameworks including FEMA ESF and OCHA MIRA, the dataset includes binary, multiple-choice, and open-ended questions covering situational awareness and operational decision-making tasks. We benchmark seven state-of-the-art vision-language models and find performance variability across question types, disaster categories, regions, and humanitarian tasks. Although models achieve high accuracy on binary questions, they struggle with fine-grained quantitative reasoning, object counting, and context-sensitive interpretation, particularly for underrepresented disaster scenarios. DisasterVQA provides a challenging and practical benchmark to guide the development of more robust and operationally meaningful vision-language models for disaster response. The dataset is publicly available at https://doi.org/10.5281/zenodo.18267769.
arXiv:2601.11919v2 Announce Type: replace
Abstract: We study task-oriented lossy compression through the lens of rate-distortion-classification (RDC) representations. The source is Bernoulli, the distortion measure is Hamming, and the binary classification variable is coupled to the source via a binary symmetric model. Building on the one-shot common-randomness formulation, we first derive closed-form characterizations of the one-shot RDC and the dual distortion-rate-classification (DRC) tradeoffs. We then use a representation-based viewpoint and characterize the achievable distortion-classification (DC) region induced by a fixed representation by deriving its lower boundary via a linear program. Finally, we study universal encoders that must support a family of DC operating points and derive computable lower and upper bounds on the minimum asymptotic rate required for universality, thereby yielding bounds on the corresponding rate penalty. Numerical examples are provided to illustrate the achievable regions and the resulting universal RDC/DRC curves.
arXiv:2601.08989v3 Announce Type: replace
Abstract: We study the Torus Puzzle, a solitaire game in which the elements of an input $m \times n$ matrix need to be rearranged into a target configuration via a sequence of unit rotations (i.e., circular shifts) of rows and/or columns. Amano et al. proposed a more permissive variant of the above puzzle, where each row and column rotation can shift the involved elements by any amount of positions. The number of rotations needed to solve the original and the permissive variants of the puzzle are respectively known as the \emph{push number} and the \emph{drag number}, where the latter is always smaller than or equal to the former and admits an existential lower bound of $\Omega(mn)$. While this lower bound is matched by an $O(mn)$ upper bound, the push number is not so well understood. Indeed, to the best of our knowledge, only an $O(mn \cdot \max\{ m, n \})$ upper bound is currently known. In this paper, we provide an algorithm that solves the Torus Puzzle using $O(mn \cdot \log \max \{m, n\})$ unit rotations in a model that is more restricted than that of the original puzzle. This implies a corresponding upper bound on the push number and reduces the gap between the known upper and lower bounds from $\Theta(\max\{m,n\})$ to $\Theta(\log \max\{m, n\})$.
arXiv:2601.08454v2 Announce Type: replace
Abstract: Constructing physically accurate simulation environments (Real2Sim) traditionally relies on manual system identification or rigid, exhaustive exploration routines. These task-agnostic pipelines often fail to leverage semantic scene context, leading to redundant physical interactions and inefficient data acquisition. In this paper, we present an autonomous, intent-driven Real2Sim framework that leverages Vision-Language Models (VLMs) for Semantic Task Decomposition. Given a high-level natural language request, an incomplete simulation description, and a visual observation, the framework autonomously identifies the minimal subset of missing physical parameters required for the simulation task. It then generates a reactive Behavior Tree (BT) composed of atomic motion and sensing primitives to selectively acquire these parameters through contact-rich robotic interaction. Extensive real-world experiments on a torque-controlled Franka Emika Panda demonstrate that our approach accurately estimates object mass, surface geometry, and derived parameters such as friction. Quantitative evaluations reveal significant operational efficiency gains compared to exhaustive baseline methods, while ablation studies confirm the robustness of the prompt architecture across different state-of-the-art VLMs. Furthermore, the reactive hierarchy of the BT acts as a deterministic safety filter, successfully mitigating generative VLM hallucinations and preventing unsafe physical anomalies. Ultimately, this work provides a scalable, efficient, and interpretable pipeline for building physics-aware digital twins directly from unstructured human intent.
arXiv:2601.07971v2 Announce Type: replace
Abstract: The transmission matrix of a disordered medium, experimentally accessible for classical waves and central to the theory of mesoscopic electronic transport, supports transmission eigenchannels ranging from complete to vanishing transmission. This range reflects wave coherence, yet the evolution of coherence with depth across eigenchannels has not been examined. Using microwave measurements and numerical simulations, we show how wave interference evolves with depth within the sample to produce constructive or destructive interference in high- and low-transmission eigenchannels, respectively. In the highest-transmission eigenchannel, the alignment of modal contributions from the waveguide modes of an incident eigenchannel can become nearly perfect as the sample length increases, allowing transmission to remain high despite extensive multiple scattering. Although the contributions in low-transmission eigenchannels are somewhat reduced relative to those in high-transmission channels, they remain appreciable, and transmission is suppressed by their destructive interference rather than by their small magnitude. Because these contributions remain appreciable, it is possible to measure eigenchannel transmission far below the noise floor of conventional transmission and more than nine orders of magnitude below the highest transmission eigenvalue when the frequency is tuned through a transmission zero. In simulations, we determine the forward- and backward-propagating modal contributions to each eigenchannel throughout the sample and extract the corresponding flux, energy density, and velocity, whose mutual consistency validates the analysis. These results reveal how modal alignment evolves throughout disordered media and underlies the contrasting characteristics of transmission eigenchannels.
arXiv:2601.06943v2 Announce Type: replace
Abstract: In real-world video question answering scenarios, videos often provide only localized visual cues, while verifiable answers are distributed across the open web; models therefore need to jointly perform cross-frame clue extraction, iterative retrieval, and multi-hop reasoning-based verification. To bridge this gap, we construct the first video deep research benchmark, VideoDR. VideoDR centers on video-conditioned open-domain video question answering, requiring cross-frame visual anchor extraction, interactive web retrieval, and multi-hop reasoning over joint video-web evidence; through rigorous human annotation and quality control, we obtain high-quality video deep research samples spanning six semantic domains. We evaluate multiple closed-source and open-source multimodal large language models under both the Workflow and Agentic paradigms, and the results show that Agentic is not consistently superior to Workflow: its gains depend on a model's ability to maintain the initial video anchors over long retrieval chains. Further analysis indicates that goal drift and long-horizon consistency are the core bottlenecks. In sum, VideoDR provides a systematic benchmark for studying video agents in open-web settings and reveals the key challenges for next-generation video deep research agents.
arXiv:2601.06162v4 Announce Type: replace
Abstract: Text-to-image diffusion models have achieved remarkable progress, yet their use raises copyright and misuse concerns, prompting research into machine unlearning. However, extending multi-concept unlearning to large-scale scenarios remains difficult due to three challenges: (i) conflicting weight updates that hinder unlearning or degrade generation; (ii) imprecise mechanisms that cause collateral damage to similar content; and (iii) reliance on additional data or modules, creating scalability bottlenecks. To address these, we propose Scalable-Precise Concept Unlearning (ScaPre), a unified framework tailored for large-scale unlearning. ScaPre introduces a conflict-aware stable design, integrating spectral trace regularization and geometry alignment to stabilize optimization, suppress conflicts, and preserve global structure. Furthermore, an Informax Decoupler identifies concept-relevant parameters and adaptively reweights updates, strictly confining unlearning to the target subspace. ScaPre yields an efficient closed-form solution without requiring auxiliary data or sub-models. Comprehensive experiments on objects, styles, and explicit content demonstrate that ScaPre effectively removes target concepts while maintaining generation quality. It forgets up to $\times \mathbf{5}$ more concepts than the best baseline within acceptable quality limits, achieving state-of-the-art precision and efficiency for large-scale unlearning. Code is available at https://github.com/kaiyuan02415/scapre
arXiv:2512.12598v3 Announce Type: replace
Abstract: We focus on the foundational task of Scene Staging: given a reference scene image and a text condition specifying an actor category to be generated in the scene and its spatial relation to the scene, the goal is to synthesize an output image that preserves the same scene identity as the reference image while correctly generating the actor according to the spatial relation described in the text. Existing methods struggle with this task, largely due to the scarcity of high-quality paired data and unconstrained generation objectives. To overcome the data bottleneck, we propose a novel data construction pipeline that combines real-world photographs, entity removal, and image-to-video diffusion models to generate training pairs with diverse scenes, viewpoints and correct entity-scene relationships. Furthermore, we introduce a novel correspondence-guided attention loss that leverages cross-view cues to enforce spatial alignment with the reference scene. Experiments on our scene-consistent benchmark show that our approach achieves better scene alignment and text-image alignment than state-of-the-art baselines, according to both automatic metrics and human preference studies. Our method generates images with diverse viewpoints and compositions while faithfully following the textual instructions and preserving the reference scene identity.
arXiv:2512.04746v2 Announce Type: replace
Abstract: Extremely low-bit quantization is critical for efficiently deploying Large Language Models (LLMs), yet it often leads to severe performance degradation at 2 bits and even at 4 bits (e.g., MXFP4). We present SignRoundV2, a post-training quantization framework designed to maintain high performance even under aggressive compression. SignRoundV2 introduces (1) a simple yet efficient adaptive mixed-precision strategy that leverages gradient information and quantization-induced reconstruction errors to guide layer-wise bit allocation, and (2) a set of lightweight stabilization techniques, including loss filtering and a pre-tuning scale search, to improve tuning effectiveness in extremely low-bit regimes. Our approach takes a significant step toward closing the performance gap between quantized and full-precision models. Experimental results across diverse LLMs demonstrate that SignRoundV2 achieves near-lossless performance in mixed MXFP settings, narrowing the gap to $\sim$1\% at an average of 4.5 bits, while substantially improving accuracy in challenging 2-bit weight-only quantization. The source code is available at \url{https://github.com/intel/auto-round}.
arXiv:2603.14936v3 Announce Type: replace
Abstract: Users often possess a clear visual intent but struggle to articulate it precisely in language. This intention-expression gap makes aligning generated images with latent visual preferences a fundamental challenge in text-to-image diffusion models. Existing methods either require model training, sacrificing flexibility, or rely on textual feedback, imposing a heavy cognitive burden. Although recent training-free methods use click-based binary preference feedback to reduce user effort, they force Foundation Models (FMs) to infer preferences at the semantic level. When faced with multi-dimensional preferences, FMs suffer from inference overload and fail to identify exact preferred feature values under conflicting user signals. Consequently, a flexible framework for multi-dimensional feature alignment remains absent. To address this, we propose a Hierarchical Relevance Feedback-Driven (HRFD) framework. Recognizing that multiple features struggle to converge simultaneously, HRFD organizes them into a three-tier hierarchy and adapts relevance feedback to enforce coarse-to-fine convergence, minimizing cognitive load. To bypass FM inference overload, HRFD decouples the process into independent single-feature preference inference tasks. Furthermore, to overcome FMs' failure in identifying preferred values, HRFD employs statistical inference to quantify the distribution divergence of features between "liked" and "disliked" image sets, achieving robust and transparent preference measurement. Crucially, HRFD operates entirely within the external text space, remaining strictly training-free and model-agnostic. Extensive experiments demonstrate that HRFD effectively captures the user's true visual intent, significantly outperforming baseline approaches.
arXiv:2510.18822v4 Announce Type: replace
Abstract: Due to the varying granularity of target states across different tasks, most existing trackers are tailored to a single task, which specificity limits their generalization, preventing them from effectively utilizing multi-task training data and leading to redundancy in both model design and parameters. Although recent unified vision models share partial architectures across tasks, they usually retain task-specific interfaces and overlook the common tracking principle behind different granularities, leaving a gap for truly unified video tracking. To unify video tracking tasks, we present SAM 2++, a unified framework that can handle target states at different granularities, including masks, boxes, and points, through an integrated design of prompt encoding, output decoding, and memory representation. First, to handle different target granularities, we design task-specific prompts that map diverse task inputs into general prompt embeddings, together with a Unified Decoder that produces task results in a common output form without redesigning the overall pipeline. Next, to satisfy memory matching, the core operation of tracking, we introduce a task-adaptive memory mechanism that unifies memory across different granularities while preserving their distinct state semantics, preventing full parameter sharing from causing interference across granularities. Finally, we introduce Tracking-Any-Granularity, the first large and diverse video tracking dataset with rich annotations at three granularities. It is constructed through a customized data engine with phased manual annotation and model-assisted completion, providing a comprehensive resource for training, benchmarking, and analyzing unified tracking models. Comprehensive experiments confirm that SAM 2++ sets a new state of the art across diverse tracking tasks at different granularities, establishing a unified and robust tracking framework.
arXiv:2509.23986v2 Announce Type: replace
Abstract: Scientific discovery is often slowed by the manual development of computational tools needed to analyze complex experimental data. Building such tools is costly and time-consuming because scientists must iteratively review literature, test modeling and scientific assumptions against empirical data, and implement these insights into efficient software. Large language models (LLMs) have demonstrated strong capabilities in synthesizing literature, reasoning with empirical data, and generating domain-specific code, offering new opportunities to accelerate computational method development. Existing LLM-based systems either focus on performing scientific analyses using existing computational methods or on developing computational methods or models for general machine learning without effectively integrating the often unstructured knowledge specific to scientific domains. Here, we introduce TusoAI , an agentic AI system that takes a scientific task description with an evaluation function and autonomously develops and optimizes computational methods for the application. TusoAI integrates domain knowledge into a knowledge tree representation and performs iterative, domain-specific optimization and model diagnosis, improving performance over a pool of candidate solutions. We conducted comprehensive benchmark evaluations demonstrating that TusoAI outperforms state-of-the-art expert methods, MLE agents, and scientific AI agents across diverse tasks, such as single-cell RNA-seq data denoising and satellite-based earth monitoring. Applying TusoAI to two key open problems in genetics improved existing computational methods and uncovered novel biology, including 9 new associations between autoimmune diseases and T cell subtypes and 7 previously unreported links between disease variants linked to their target genes. Our code is publicly available at https://github.com/Alistair-Turcan/TusoAI.
arXiv:2509.06984v3 Announce Type: replace
Abstract: Federated Learning with LoRA fine-tuning offers an efficient and privacy-aware solution for institutions to collaboratively leverage their large datasets to train VLLMs. However, participating institutions often possess heterogeneous computational resources, resulting in imbalanced LoRA ranks, which pose a major challenge for effective collaboration. In addition, real-world applications in domains such as healthcare and transportation frequently suffer from missing modalities due to user mistakes or device failures, which significantly degrade global model performance in federated settings. To the best of our knowledge, no prior work has addressed these two challenges simultaneously in federated VLLMs. To tackle these issues, we propose FediLoRA, a lightweight federated LoRA aggregation framework that effectively mitigates the impact of missing modalities in heterogeneous environment. FediLoRA is explicitly motivated by the observation that simple averaging and structured editing can jointly benefit both global and personalized models. Our approach achieves strong performance across multiple general-domain and medical-domain benchmark datasets. Additional experiments on healthcare data further demonstrate that FediLoRA is well-suited for practical, real-world deployment scenarios. Our code is released at https://github.com/gotobcn8/FediLoRA.
arXiv:2508.20836v3 Announce Type: replace
Abstract: In this letter, we report the first experimental demonstration of the recently emerged new paradigm in hovering and flapping flight physics called (Natural Hovering Extremum Seeking (NH-ES)) [doi.org/10.1103/4dm4-kc4g], which theorized that stable hovering flight physics observed in nature by flapping insects and hummingbirds can be generated via a model-free, real-time, computationally-basic, sensory-based feedback mechanism that only needs the built-in natural oscillations of the flapping wing as both the control and the propulsive input. We run experiments of moth-like, light source-seeking, on a flapping-wing body in a total model-free setting that is agnostic to morphological parameters and body/aerodynamic models. We show that the flapping body using NH-ES gains altitude and stabilizes autonomously the servos responsible for flapping, including with pitching dynamics (believed in literature to be a main reason of instability in open-loop hovering). The flapping body effectively/stably hovers about the light source, needing only feedback of local measurements of light intensity. Our results were also achieved under delay/noise effects, supporting earlier observations that NH-ES is robust against potential processing delays and noisy-sensations.
arXiv:2507.05091v3 Announce Type: replace
Abstract: The stochastic finite volume method (SFV method) is a high-order accurate method for uncertainty quantification (UQ) in hyperbolic conservation laws. However, the computational cost of SFV method increases for high-dimensional stochastic parameter spaces due to the curse of dimensionality. To address this challenge, we incorporate interpolation-based reduced order model (ROM) techniques that reduce the cost of computing stochastic integrals in the SFV method. Further efficiency gains are achieved through hyper-reduction with a QR factorization-based discrete empirical interpolation method (Q-DEIM). Numerical experiments suggest that this approach can lower both computational cost and memory requirements for high-dimensional stochastic parameter spaces.
arXiv:2506.22901v2 Announce Type: replace
Abstract: A key challenge in learning from multimodal biological data is missing modalities, where data from one or more modalities are absent for some patients. Existing approaches either exclude patients with missing modalities, impute missing modalities, or make predictions directly with partial modalities. However, most of these methods rely on inflexible, patient-agnostic fusion strategies and do not scale computationally to the combinatorial growth of missing-modality patterns as the number of modalities increases. To address these limitations, we propose MAGNET (Missing-modality-Aware Graph neural NETwork) to enhance multimodal prediction with partial modalities, featuring a dynamic patient-modality multi-head attention mechanism to fuse lower-dimensional modality embeddings based on their contribution and missingness. MAGNET fusion's complexity increases linearly with the number of modalities while adapting to missing-pattern variability. To generate predictions, MAGNET further constructs a patient graph with fused multimodal embeddings as node features and connectivity determined by the modality missingness, followed by a graph neural network. Experiments on three public multiomics datasets for cancer classification, with real-world missingness, show that MAGNET outperforms state-of-the-art fusion methods. The data and code are available at https://github.com/SinaTabakhi/MAGNET.
arXiv:2506.14009v2 Announce Type: replace
Abstract: Autonomous drones capable of interpreting and executing high-level language instructions in unstructured environments remain a long-standing goal. Yet existing approaches are constrained by their dependence on hand-crafted skills, extensive parameter tuning, or computationally intensive models unsuitable for onboard use. We introduce GRaD-Nav++, a lightweight Vision-Language-Action (VLA) framework that runs fully onboard and follows natural-language commands in real time. Our policy is trained in a photorealistic 3D Gaussian Splatting (3DGS) simulator via Differentiable Reinforcement Learning (DiffRL), enabling efficient learning of low-level control from visual and linguistic inputs. At its core is a Mixture-of-Experts (MoE) action head, which adaptively routes computation to improve generalization while mitigating forgetting. In multi-task generalization experiments, GRaD-Nav++ achieves a success rate of 83% on trained tasks and 75% on unseen tasks in simulation. When deployed on real hardware, it attains 67% success on trained tasks and 50% on unseen ones. In multi-environment adaptation experiments, GRaD-Nav++ achieves an average success rate of 81% across diverse simulated environments and 67% across varied real-world settings. These results establish a new benchmark for fully onboard Vision-Language-Action (VLA) flight and demonstrate that compact, efficient models can enable reliable, language-guided navigation without relying on external infrastructure.
arXiv:2506.05442v2 Announce Type: replace
Abstract: Vision-Language Models (VLMs) offer a promising approach to end-to-end autonomous driving due to their human-like reasoning capabilities. However, troublesome gaps remains between current VLMs and real-world autonomous driving applications. One major limitation is that existing datasets with loosely formatted language descriptions are not machine-friendly and may introduce redundancy. Additionally, high computational cost and massive scale of VLMs hinder the inference speed and real-world deployment. To bridge the gap, this paper introduces a structured and concise benchmark dataset, NuScenes-S, which is derived from the NuScenes dataset and contains machine-friendly structured representations. Moreover, we present FastDrive, a compact VLM baseline with 0.9B parameters. In contrast to existing VLMs with over 7B parameters and unstructured language processing(e.g., LLaVA-1.5), FastDrive understands structured and concise descriptions and generates machine-friendly driving decisions with high efficiency. Extensive experiments show that FastDrive achieves competitive performance on structured dataset, with approximately 20% accuracy improvement on decision-making tasks, while surpassing massive parameter baseline in inference speed with over 10x speedup. Additionally, ablation studies further focus on the impact of scene annotations (e.g., weather, time of day) on decision-making tasks, demonstrating their importance on decision-making tasks in autonomous driving.
arXiv:2505.17352v2 Announce Type: replace
Abstract: Diffusion models have become a central paradigm for image and multimodal generation, yet their deployment raises persistent questions about alignment, safety, preference satisfaction, and robustness to misuse. This survey reviews recent progress on aligning text-to-image diffusion models through reinforcement learning, reward modeling, preference optimization, and safety-specific fine-tuning. We organize the literature along five axes: the source of feedback, the form of the reward or preference signal, the optimization mechanism, the treatment of distribution shift and reward overoptimization, and the extent to which safety is addressed as an explicit constraint rather than a generic preference. The review covers reinforcement learning from human feedback, KL-regularized policy optimization, direct preference optimization, binary utility optimization, differentiable reward fine-tuning, surrogate reward learning, region-aware fine-tuning, and safety-oriented DPO variants. To make the survey accessible, we include tutorial explanations of diffusion sampling, reward modeling, and preference optimization, and briefly connect image diffusion alignment to emerging text and masked language diffusion models. We also compare representative methods in terms of feedback requirements, computational cost, scalability, susceptibility to reward hacking, and suitability for safety-critical deployment. Finally, we synthesize the literature into a set of open challenges: multi-objective alignment, feedback-efficient preference learning, adversarially robust safety alignment, continual alignment under changing norms, and interpretable reward modeling. The goal of this survey is to provide a coherent technical map of the emerging area of diffusion model alignment and to identify the methodological gaps that must be addressed before aligned generative models can be reliably deployed.
arXiv:2503.02161v3 Announce Type: replace
Abstract: Synthetic tabular data are increasingly being used to replace real data, serving as an effective solution that simultaneously protects privacy and addresses data scarcity. However, in addition to preserving global statistical properties, synthetic datasets must also maintain domain-specific logical consistency**-**especially in complex systems like supply chains, where fields such as shipment dates, locations, and product categories must remain logically consistent for real-world usability. Existing generative models often overlook these inter-column relationships, leading to unreliable synthetic tabular data in real-world applications. To address these challenges, we propose LLM-TabLogic, a novel approach that leverages Large Language Model reasoning to capture and compress the complex logical relationships among tabular columns, while these conditional constraints are passed into a Score-based Diffusion model for data generation in latent space. Through extensive experiments on real-world industrial datasets, we evaluate LLM-TabLogic for column reasoning and data generation, comparing it with five baselines including SMOTE and state-of-the-art generative models. Our results show that LLM-TabLogic demonstrates strong generalization in logical inference, achieving over 90% accuracy on unseen tables. Furthermore, our method outperforms all baselines in data generation by fully preserving inter-column relationships while maintaining the best balance between data fidelity, utility, and privacy. This study presents the first method to effectively preserve inter-column relationships in synthetic tabular data generation without requiring domain knowledge, offering new insights for creating logically consistent real-world tabular data. The code is available at https://github.com/Yunbo-max/TabKG.
arXiv:2412.14836v4 Announce Type: replace
Abstract: Many natural computational problems, including e.g. Max Weight Independent Set, Feedback Vertex Set, or Vertex Planarization, can be unified under an umbrella of finding the largest sparse induced subgraph, that satisfies some property definable in CMSO$_2$ logic.
It is believed that each problem expressible with this formalism can be solved in polynomial time in graphs that exclude a fixed path as an induced subgraph.
This belief is supported by the existence of a quasipolynomial-time algorithm by Gartland, Lokshtanov, Pilipczuk, Pilipczuk, and Rz\k{a}\.zewski [STOC 2021], and a recent polynomial-time algorithm for $P_6$-free graphs by Chudnovsky, McCarty, Pilipczuk, Pilipczuk, and Rz\k{a}\.zewski [SODA 2024].
In this work we extend polynomial-time tractability of all such problems to $P_7$-free graphs of bounded clique number.
arXiv:2409.10102v2 Announce Type: replace
Abstract: Retrieval-Augmented Generation (RAG) has quickly grown into a pivotal paradigm in the development of Large Language Models (LLMs). Although existing research mainly emphasizes accuracy and efficiency, the trustworthiness of RAG systems remains insufficiently explored. RAG can improve LLM reliability by grounding responses in external and up-to-date knowledge, reducing hallucinations. However, unreliable retrieval or improper knowledge utilization may still lead to undesirable outputs. To address these concerns, we propose a unified framework, Trust-RAG Compass, that assesses the trustworthiness of RAG systems across six key dimensions: factuality, robustness, fairness, transparency, accountability, and privacy. Within this framework, we provide a thorough review of the existing literature along each dimension. Furthermore, we introduce an evaluation benchmark, TRC Bench (\underline{T}rust-\underline{R}AG \underline{C}ompass \underline{Bench}mark), regarding the six dimensions and conduct comprehensive evaluations for a variety of proprietary and open-source models. Our results shed light on the performance gaps between different types of LLMs across varying dimensions of trustworthiness. Finally, we identify key challenges and promising directions for future research based on our findings. Through this work, we aim to provide a structured foundation for subsequent investigations and practical guidance for developing trustworthy RAG systems in real-world scenarios.
arXiv:2602.19745v2 Announce Type: replace
Abstract: BioFabrics were introduced by Longabaugh in 2012 as a way to draw large graphs in a clear and uncluttered manner. The visual quality of BioFabrics crucially depends on the order of vertices and edges, which can be chosen independently. Effective orders can expose salient patterns, which in turn can be summarized by motifs, allowing users to take in complex networks at-a-glance. However, so far there is no efficient layout algorithm which automatically recognizes patterns and delivers both a vertex and an edge ordering that allows these patterns to be expressed as motifs. In this paper we show how to use well-ordered matrices as a tool to efficiently find good vertex and edge orders for BioFabrics. Specifically, we order the adjacency matrix of the input graph using Moran's $I$ and detect (noisy) patterns with our recent algorithm. In this note we show how to "unfold" the ordered matrix and its patterns into a high-quality BioFabric. Our pipelines easily handles graphs with up to 250 vertices.
arXiv:2605.16596v1 Announce Type: cross
Abstract: Spin-photon interfaces, realized by coupling optically active spin systems to photonic cavities, are essential for quantum networking and quantum information processing. Implementing such an interface for polarization-encoded photons requires a cavity that supports arbitrary polarization, provides efficient optical access through its far-field mode, and maintains sufficiently high quality factors to enable high cooperativity with the system's optical transitions. However, inherent trade-offs between the Q-factor and far-field emission mode make the simultaneous optimization of these parameters toward the realization of spin-photon interfaces challenging. In this work, we implement a gradient-based inverse-design framework using guided-mode expansion with automatic differentiation to obtain the geometrical features of a circular ring cavity that supports arbitrary polarization while simultaneously optimizing the cavity quality factor and far-field mode profile. The resulting optimized non-periodic cavity achieves a quality factor of approximately $9,000$, about an order-of-magnitude higher than that of a periodic ("bullseye") cavity while preserving a Gaussian-like far-field emission pattern. Furthermore, by varying the cavity geometry within a $\pm 6$ nm fabrication tolerance, we demonstrate the robustness of the design against fabrication errors and identify the innermost ring width and central disk radius as the parameters with the greatest impact on the quality factor and far-field mode. These results establish guided mode expansion-based inverse design as a powerful and computationally efficient approach for developing high-cooperativity spin-photon interfaces for quantum photonic applications.