Computer Science (arXiv)

Diffusion-based generators have made synthetic images ubiquitous, but detectors often fail under simultaneous shifts in generator, prompt/style, and source-domain. We study AI-generated image detection as a transfer system described by training prior, frozen encoder feature space, and decision rule, and ask when classifier head training adds value beyond what is already separable in modern features. As a controlled diagnostic, we fit a prior-conditioned Gaussian discriminant ladder: closed-form heads built from first- and second-order feature statistics under nested covariance assumptions. On Percept-Lens, a unified protocol over 39 public datasets (7.1 million images), the best rung is frequently competitive with, and sometimes exceeds, released AI-generated image detector heads when matched on both prior and encoder. We further quantify strong sensitivity to the training prior, data-efficiency of moment-based heads, and representation dependence of Gaussian shift metrics, motivating (prior, encoder, head)-level reporting and stronger analytical baselines for AIGI transfer.

Large antenna arrays allow wireless systems to serve more users and achieve higher data rates, but they also make channel feedback expensive: the receiving device must repeatedly report a large complex-valued channel matrix to the base station. Most neural compressors treat this matrix like an image and replace it with a fixed-length code that only a matched neural decoder can interpret. The message therefore does not adapt to channel complexity, and changing the antenna count typically requires retraining. We ask whether a device can instead report only the few dominant propagation paths underlying each channel. We introduce the Gramian Chebyshev Neural Operator (GCNO), a physics-based, variable-rate compressor that identifies a sample-dependent set of path directions. GCNO uses receive-transmit channel structure to locate paths, a first-order Taylor correction to refine directions that fall between grid points, and least squares to recover their complex strengths. It is trained without path labels, and the base station reconstructs the channel analytically from the transmitted path tuples rather than through a learned decoder. Across three ray-traced environments, GCNO achieves better reconstruction accuracy at the same payload - or lower payload at the same accuracy - than neural feedback baselines, and transfers to unseen antenna counts without retraining.

Dense-caption retrieval has recently been improved by introducing segmentation, edge maps, LLM-filtered captions, and cross-modal modules into contrastive fine-tuning. However, these methods largely inherit the same InfoNCE objective, whose optimization can prematurely saturate under a strong pre-trained initialization: on dense captions, the loss falls below 10^-3 on 80% of batches within the first epoch, while its gradient becomes numerically zero in 47% of measurements. We find that this behavior is closely related to the large number of near-duplicate captions in dense-caption benchmarks, where a few highly similar negatives remain unresolved after the easy majority has already been separated. As a remedy, we introduce HN-CLIP, which uses the text encoder's own text-text geometry to construct per-negative adaptive similarity margins. Specifically, a detached caption-similarity matrix is added to the negative logits, assigning larger margins to more similar captions without mining, synthesizing, or resampling negatives. The resulting objective requires only one caption-similarity matrix and a masked logit addition during training, with no auxiliary data, additional parameters, offline preprocessing, or inference-time overhead. Extensive experiments on four dense-caption retrieval benchmarks show that HN-CLIP improves over the strongest competitors by +2.5 to +4.0 R@1 while training 2.4x faster than GOAL and 5.4x faster than StructXLIP. Moreover, the proposed objective improves all six tested fine-tuning frameworks on the in-domain benchmarks and reaches the strongest full-data baseline with only 20% of the training data.

Precise segmentation of the optic disc and cup is critical for the early detection and diagnosis of glaucoma. However, achieving consistently high performance across datasets while maintaining low computational requirements remains a significant challenge. In glaucoma detection, low-computation methods are crucial for enabling rapid, large-scale screening and facilitating deployment in resource-limited clinical environments. While deep learning models such as UNets, Vision Transformers (ViTs), and Diffusion models have demonstrated strong segmentation performance but these methods often come with substantial computational overhead. UNets are efficient at capturing local features but are limited in modeling global contextual information. Conversely, ViTs excel at long-range dependency modeling but are computationally intensive. Hybrid architectures, such as UNetR, which combine transformer-based encoders with UNet-style decoders, have shown improved performance but while incurring additional complexity. Considering these, in this work, we propose OptiModNet, a light weight novel hybrid architecture tailored for optic disc and cup segmentation. The model integrates diverse attention mechanisms at multiple stages of the network to enhance both local and global feature representation. We include an Aggregated Pyramid Loss that supervises predictions at multiple decoder depths, to promote better gradient flow and structural consistency. We evaluate OptiModNet on the REFUGE2 dataset for both optic disc and cup segmentation tasks. Our method achieves state-of-the-art performance, exceeding existing approaches by over 2.5\%, while maintaining high efficiency with only 3.73 GFLOPs and 1.93M parameters. The code is available at https://github.com/SG1947/OptiModNet.

Transvaginal ultrasound (TVUS) and magnetic resonance imaging (MRI) provide complementary information for endometriosis image analysis, yet existing studies mainly focus on single-modality analysis or disease classification, leaving cross-modal ovarian segmentation largely unexplored. In this work, to tackle the increased difficulty of ovary segmentation in MRI due to ovaries' small target size and ambiguous boundaries with surrounding pelvic structures, we propose a dual branch framework for ovary segmentation across TVUS and MRI. More specifically, by adapting MedSAM3 with TVUS-derived prototype bank, we aim to align anatomically consistent feature representations across both modalities. Extensive experiments are conducted on endometriosis-related TVUS and MRI datasets. We observe quantitative and qualitative improvements of over 5 percentage points for the proposed dual-branch approach compared with multiple state-of-the-art methods. Furthermore, our ablation study shows the contribution of individual components such as the prototype bank and the importance of warm-up pretraining in the source TVUS domain.

The two-dimensional bandwidth minimization problem (2DBMP) seeks an injective embedding of a guest graph into a square grid that minimizes the maximum Manhattan distance over its edges. Heuristic methods can provide strong upper bounds, but these bounds do not by themselves certify optimality. We present an efficient exact SAT-based approach for 2DBMP that incrementally searches for the minimum feasible bandwidth and certifies optimality through satisfiability and unsatisfiability results. On the standard $\lceil\sqrt n\rceil \times \lceil\sqrt n\rceil$ host grid, under a 3600 s time limit, the proposed SAT approach certifies optimal bandwidths for 41 of 43 Regular instances and 42 of 93 Harwell--Boeing instances, achieving substantially broader optimality certification within the 3600 s time limit than a previous exact approach evaluated with a 72-hour time limit. In addition, it certifies three bandwidth values that improve all previously published comparison values considered in this study and establishes all three as optimal. We further evaluate the approach on alternative host geometries, namely $2\times\lceil n/2\rceil$ and $n\times n$ grids, to assess its effectiveness beyond the standard host. Overall, the results demonstrate that the proposed SAT approach provides an effective exact method for the small- and medium-sized benchmark instances considered in this study, with fewer than 400 vertices, while heuristic methods remain important for larger and more challenging instances.

We are witnessing an explosion of agentic systems for computational chemistry simulations: from half a dozen in 2024 to a dozen in 2025, and the current number approaches fifty, surveyed in this Perspective as of 8 August 2026. The capabilities of these agentic systems are shifting from assisting in performing a selection of computational tasks to autonomous design and execution of \textit{in silico} experiments, their analysis, and even manuscript writing. The ultimate destination is a fully autonomous AI scientist, where the entirety of computational chemistry is performed on a machine by a machine, without human supervision. While we are not there yet, and all reported systems currently involve a human in the loop, the trend is unmistakable. Even building specialized agentic systems for computational chemistry is increasingly commoditized by generalist agents, which may in the end replace the need for the specialized ones altogether, since adding a new capability will be as easy as asking AI to do it for you. Both the explosion in their number and the very limited adoption beyond their own developers point that way, and we close this Perspective on what it leaves us to do. The speed and scale of disruption agentic systems are bringing to computational chemistry leave many of us dumbfounded about the field's future and what we should spend our efforts on, as already established specialists, teachers, and students, and we have no answer.

Continuum arm aerial manipulation systems leverage soft-manipulator compliance and dexterity for tasks in confined or hazardous environments, but propeller downwash can degrade performance, particularly near walls and the ground. This effect remains uncharacterized for continuum manipulators. This letter experimentally studies downwash-induced kinematic deviations of a tendon-driven continuum manipulator integrated with a multirotor platform. Under still-air conditions, the CM is compared with a constant-curvature (CC) model. Downwash- induced end-effector pose deviations are then quantified relative to the mean still-air experimental baseline at four propeller throttle levels in free space, and at maximum throttle near a wall, and near the ground. Vertical position and yaw show the largest deviations and are amplified by ground effect. A CC-guided Gaussian process regression (GPR) residual model is learned from experimental data that improves forward pose prediction RMSE (position by 89-95%, orientation by 47-79%), and support compensation-oriented, downwash-aware modeling of continuum arm aerial manipulation systems.

Universal multimodal retrieval aims to support diverse instruction-aware retrieval tasks, demanding both efficient corpus-scale matching and fine-grained semantic reasoning. Recent MLLM-based embedding methods typically derive representations from hidden states, while Chain-of-Thought (CoT) reasoning is emerging as a promising strategy for embedding enhancement by encoding intermediate semantic evidence into the representation space. However, existing CoT methods typically use item-wise reasoning over queries and candidates in isolation, providing no explicit evidence to distinguish a positive from a semantically confusable hard negative. Moreover, contrastive embeddings capture global similarity but struggle with meta-tasks requiring answer verification, category judgment or fine-grained reasoning. In this paper, we propose UMER, a Unified Multimodal Embedding and Ranking framework for universal multimodal retrieval. UMER replaces item-wise reflection with Pair-Aware Discriminative Reasoning, which compares query--candidate pairs to identify instruction-relevant matching and discrepancy evidence. UMER jointly learns contrastive embeddings for efficient global matching and discriminative ranking for explicit pairwise relevance judgment within a single MLLM. A complementary mutual distillation strategy further transfers reliable pairwise preferences between the embedding and ranking functions. On the MMEB-V2 benchmark, UMER achieves state-of-the-art performance under comparable experimental settings while supporting budget-adjustable inference.

The growing demand for AI-driven workloads, particularly from Large Language Models (LLMs), has raised concerns about the significant energy and resource consumption in data centers. This work introduces a novel LLM-based predictive scheduling system designed to enhance operational efficiency while reducing the environmental impact of data centers. Our system utilizes an LLM to predict key metrics such as execution time and energy consumption from source code, and it has the potential to extend to other sustainability-focused metrics like water usage for cooling and carbon emissions, provided the data center can track such data. The predictive model is followed by a real-time scheduling algorithm that allocates GPU resources, aiming to improve sustainability by optimizing both energy consumption and queuing delays. With fast inference times, the ability to generalize across diverse task types, and minimal data requirements for training, our approach offers a practical solution for data center scheduling. This framework demonstrates strong potential for advancing sustainability objectives in AI-driven infrastructure. Through our collaboration with a data center, we achieved a 32% reduction in energy consumption and a 30% decrease in waiting time.

Tropical cyclones (TCs) pose severe risks from strong winds and heavy rainfall. However, forecasting their track and intensity remains challenging due to chaotic atmosphere and the rapid amplification of initial condition errors, leading to growing forecast uncertainty. While numerical weather prediction (NWP) and deep learning models have made progress, they remain computationally demanding and often fail under complex meteorological scenarios. Here, we present Tianmu-TC, a physics-constraints generative framework for global TC forecasting. Trained on Western North Pacific data, Tianmu-TC leverages physics-constraints to generate controllable outputs with reduced uncertainty thus improving forecast reliability. Experiments show Tianmu-TC outperforms deterministic and ensemble meteorological artificial intelligence models and authoritative NWP systems such as ECMWF in global ocean basins, with significantly lower computational cost. We further show Tianmu-TC performs well in challenging scenarios such as data sparsity, anomaly tracks, rapid intensification and weakening. These findings suggest physics-constraints generative AI offers a promising approach for reliable, efficient global TC forecasting.

Modeling object dynamics from limited visual observations is a fundamental problem for enabling accurate motion trajectory prediction in embodied interaction scenarios. Existing dynamics modeling methods first compress reconstructed particle representations into sparse Key Points and model their evolution using locally constrained interactions, thereby discarding fine-grained local details and obscuring discriminative interaction modeling across spatial and temporal scales, leading to drifting trajectories and inaccurate appearance prediction. To tackle these issues, we propose DyG$^2$T, a dynamics modeling framework that infers object motion trajectories by spatially completing and temporally discriminating Key Point representations and modeling multi-scale interaction over particle graphs. Spatially, DyG$^2$T enriches each Key Point by aggregating neighboring raw particle positions to recover fine-grained local details, while explicitly encoding relative offsets among Key Points to enhance geometric structure perception. Temporally, we introduce a Temporal Disentangling Network (TDN) to identify dominant cross-frame variations in latent space and amplify inter-frame differences, yielding temporally discriminative representations that are subsequently aggregated via Temporal Attention to capture frame-wise temporal evolution cues. For comprehensive interaction modeling, a Particle Graph Transformer leverages global attention to preserve discriminative long-range dependencies among Key Points, mitigating representation homogenization induced by locality-constrained modeling and providing a robust basis for accurate trajectory prediction. Experiments on both synthetic and real-world datasets demonstrate that DyG$^2$T achieves accurate dynamics modeling and reasoning, and exhibits strong cross-object and real-world generalization.

We give the first deterministic algorithm for fully sparse matrix multiplication that attains the optimal running-time exponent. This result matches the best previously known randomized algorithm running-time exponent. Given compatible matrices $A$ and $B$ over an arbitrary associative ring with identity, with $\operatorname{nnz}(A),\operatorname{nnz}(B)=O(n^{δ_{\mathrm{in}}})$ and $\operatorname{nnz}(AB)=O(n^{δ_{\mathrm{out}}})$, our algorithm finds the support of $AB$ and computes the product exactly in $$O\!\left(n^{β_R(δ_{\mathrm{in}},\min\{δ_{\mathrm{out}},2δ_{\mathrm{in}}\})+\varepsilon}\right)$$ operations, where $β_R(δ_{\mathrm{in}},δ)$ denotes the maximum of $δ_{\mathrm{in}}$ and $ω_{δ_{\mathrm{in}},R}(a,1,b)$ over all $a,b\in[0,1]$ satisfying $a+b=δ$. For dense inputs over a commutative ring, this bound simplifies to $O(n^{ω_R((δ_{\mathrm{out}}-1)_+,1,1)+\varepsilon})$. With the current rectangular matrix multiplication bounds, this is nearly quadratic, namely $O(n^{2+\varepsilon})$, for every $δ_\mathrm{out}\le1.321334$, improving the previous deterministic range of $δ_{\mathrm{out}}\le 0.642668$. To prove this result, we develop a general deterministic recovery technique that finds and fixes sparse parts of an unknown matrix while keeping temporary errors in denser parts under control.

Radio maps are essential for wireless decision-making tasks such as access-point placement, coverage planning, and localization, but their fine spatial details are governed by complex propagation effects and are costly to simulate accurately. Machine learning offers a path to high-fidelity radio-map prediction without running expensive high-fidelity simulations for every scene. However, generating high-quality training labels at scale is also difficult: the affordable labels come from finite-ray simulations, which are richer than low-fidelity inputs but carry residual Monte Carlo noise. We address this challenge with Physics-Unrolled Hybrid Neural Operator (PU-HNO), a three-stage cascade that predicts high-fidelity indoor radio maps from low-fidelity ray-tracing outputs and scene priors by progressively capturing reflection, diffraction, and scattering effects, rather than treating radio maps as generic images. We prove that, under conditionally unbiased label noise, the model can learn stable propagation structure and outperform its own training labels. Experiments across diverse floorplans show that PU-HNO outperforms image-to-image baselines, wireless learning models, and monolithic neural operators across both image-quality and wireless deployment metrics.

This tutorial introduces the algebraic foundations underlying the weight structure of polar codes. Using a monomial-based polynomial formalism, we explain how polar and Reed-Muller codes can be viewed as decreasing monomial codes, enabling systematic characterization and enumeration of low-weight codewords. Its goal is to provide an accessible introduction to affine automorphisms, orbit-based descriptions of minimum and low-weight codewords, and their role in weight enumeration. Through illustrative examples and high-level overviews of recursive and coset-based techniques, the paper aims to prepare readers for deeper engagement with the recent technical literature on the weight distribution of polar codes.

Multi-agent Large Language Model (LLM) systems often struggle to collaborate with new teammates whose strategies shift mid-task. Because agents execute multi-step or temporally extended skills, they frequently continue executing outdated plans long after public evidence shows that a partner has changed its skill. Existing methods either treat partner tracking as passive context-leaving the agent aware of the shift but slow to act-or replan indiscriminately. We introduce BayesBeliefAgent, which pairs a hierarchical LLM planner with a Bayesian tracking module. Rather than replanning constantly, our agent interrupts its current skill only when a partner's actions directly contradict the inferred skill. Beyond standard reward, we evaluate performance using replanning efficiency and the belief-action gap: the fraction of total decisions where an agent with a correct partner estimate executes a non-complementary skill. Across benchmark Overcooked environments, contradiction-conditioned control drastically narrows this belief-action gap while requiring an order of magnitude fewer replans than heuristic methods

Knowledge graph question answering (KGQA) and knowledge-graph-based retrieval-augmented generation (KG-RAG) aim to ground answers in explicit graph evidence, but real-world knowledge graphs are often sparse, outdated, and incomplete. Existing robustness evaluations usually report aggregate changes in answer quality after evidence is removed or perturbed, which measures sensitivity to incomplete support but leaves the source of degradation under-specified: the same score change can conflate the type of missing evidence, the response of the evaluated system, and the sensitivity of the answer-matching protocol. To address this gap, we propose \textbf{MissDiag}, a diagnostic evaluation framework for incomplete-knowledge robustness in KGQA and KG-RAG. MissDiag keeps the question and gold answer fixed while applying structurally typed missingness interventions to benchmark-provided support graphs, enabling paired comparisons that decompose robustness changes by evidence type, system response, and evaluation protocol rather than reducing them to a single aggregate score drop. Experiments across multiple system families show that incomplete-knowledge robustness is better understood as a typed degradation phenomenon than as a uniform property: answer-adjacent evidence loss produces the largest observed degradation, source-context removal is often neutral and can be beneficial, and semantic answer matching changes absolute scores while preserving the main typed degradation patterns. By transforming aggregate robustness measurement into typed diagnostic attribution, MissDiag provides a more interpretable basis for comparing, diagnosing, and stress-testing KGQA and KG-RAG systems under incomplete knowledge.

Social robots have been widely explored as tools for autism intervention, yet this literature has focused predominantly on children and has rarely involved autistic adults as active contributors to design. This creates a mismatch between existing systems and the social-cognitive challenges autistic adults actually face in everyday life, including navigating ambiguous interpersonal contexts, managing conversational timing, and interpreting implied emotional meaning. To address this gap, we conducted an online focus group and co-design session with five autistic adults to explore what a social robot for social-cognition training should do, how it should interact, and under what conditions it would be genuinely useful. The 90-minute session combined open discussion with structured co-design activities on a shared digital whiteboard, and the resulting verbal and visual data were analysed using reflexive thematic analysis. The analysis yielded seven themes that define core design requirements: the robot should function as a scaffold rather than a substitute, prioritise authenticity over comfort, provide personalised and user-controlled feedback, accommodate emotional self-awareness gaps, respect privacy and contextual boundaries, support rehearsal for real-world social situations, and remain configurable in identity, form, and expression. Together, the findings suggest that autistic adults envision the robot not as a companion or live social assistant, but as a private, configurable rehearsal partner designed to support independence over time.

In a Transformer, each layer attends to past tokens only through KV produced at its own depth, despite the presence of deeper representations during autoregressive decoding. Feedback architectures allow shallow consumer layers to attend to KV produced by deeper past-token representations, but give all consumer layers the same fixed connection patterns to source layers. We propose WhiteMatter, which connects every attention layer to the representations from all layers of each past token, with connection weights that can vary across consumer layers and adapt to the source token. For each token, a router implements these connections by mixing its $L$ layer states into $k$ KV channels that are cached for subsequent tokens; each consumer layer attends to one of the channels. The number of channels $k$ controls the KV-cache size. Setting $k<L$ reduces the cache's memory footprint. In our pretraining experiments, WhiteMatter outperforms a vanilla Transformer with 50% more layers and retains most of this gain with a 50% KV-cache compression.

Training-free block-sparse attention can accelerate video transformers, but row-wise attention concentration does not by itself specify an executable sparse operator. Queries sharing a block route may have poorly overlapping supports, while retained attention mass alone does not determine the post-softmax error from skipped interactions. We show that partition geometry affects both pooled support and the predictability of the remaining residual from the sparse output. We introduce SparsePR, which combines Response-Coupled Partitioning with Probe-Fitted Residual Reconstruction. Sampled-query key responses form paired K/V groups, whose centroids induce query-response coordinates for shared routing. A small set of exact query rows then calibrates a call-specific affine correction from the sparse output within the output subspace observed in the probe residuals. Across four heterogeneous video generation and world models, SparsePR consistently reduces attention-reconstruction error. Ablations show that probe fitting accounts for most of this reduction, while response-coupled partitioning lowers hard-drop error and improves reconstruction under a finite probe budget. SparsePR preserves generation quality at 22.0-26.0% realized executed-pair density while achieving 1.48x-2.61x end-to-end speedups. Project page: https://pardistaghavi.github.io/SparsePR-website/

Hardware functional verification relies on high-quality assertions to expose design bugs and establish confidence in Register Transfer Level (RTL) designs. Yet existing assertion mining methods still struggle to produce complete and reliable assertion sets: random or limited traces fail to cover hard-to-reach behaviors, and one-shot generation provides little feedback about what remains unverified or how the assertion set should be improved. As a result, critical design behaviors can remain uncovered even when many assertions are generated. We present NeuroAssertion, a coverage-driven assertion generation framework that combines formal trace generation, syntax-guided synthesis (SyGuS), and an agent-inspired refinement process within a unified framework. Our framework first converts hard-to-reach control-flow conditions into formal reachability objectives, uses model checking to generate behaviorally diverse traces, and mines initial assertions from these traces with SyGuS. It then performs targeted agent-inspired refinement under verification feedback: one LLM first proposes candidate assertions for uncovered regions, and if a candidate fails formal checking, a second LLM generates a repair grammar that guides constrained symbolic synthesis in a neuro-symbolic repair procedure. Experimental results show that this framework delivers around 2X more assertions and about 2X higher mutation coverage than traditional assertion mining methods.

Digital twins (DTs) increasingly leverage artificial intelligence (AI) and machine learning (ML) pipelines, both to build real-time DTs from high-fidelity simulations and to instantiate them with historical data. However, engineering these pipelines remains largely ad-hoc: pipelines are hard to specify, validate, and reuse, with scarce dedicated tooling. Function+Data Flow (FDF) addresses this by defining a visual domain-specific language (DSL) that represents functions (ML models) explicitly, enabling their composition and reuse. We implemented FDF in DesCartes Builder, an integrated modeling environment supporting FDF-based DT synthesis and validation. In this paper, we report on an empirical user study evaluating whether FDF and DesCartes Builder can make AI-based DT development more accessible and reliable. Participants implemented a representative real-time DT prototype within DesCartes Builder, and we measured perceived usability and feature adequacy through quantitative and qualitative measures. Our results indicate that DesCartes Builder and FDF achieve a good level of usability across a broad range of potential users, and particularly for the intended audience of domain experts. The study additionally surfaces concrete strengths and areas for improvement of both the tool and the underlying FDF framework. Informed by these findings, we propose H-FDF, a Hierarchical extension of FDF supporting iterative and modular pipelines, enabling the formal specification of more complex DT pipelines such as dual training. Our findings suggest that integrated, model-driven platforms are a promising direction to transform AI-based DT engineering into a disciplined modeling practice.

Semantic segmentation of aerial point cloud is trapped in a generalization crisis under distinct domain shifts. While test-time adaptation offers a privacy-preserving and computationally efficient way to adapt pre-trained models to unlabeled target-domain data during inference, existing methods, bound to closed-set label assumptions and non-scalable point-wise segmentation pipelines, still struggle with semantic shifts. We ask: can we adapt any given pre-trained aerial point cloud segmentation model to a shifted target domain at the inference phase alone, without additional training, while segmenting target-specific categories beyond the source label space on demand? This paper introduces COSTA, which breaks this limitation by shifting from closed-set point-wise adaptation to cluster-centric open-set semantic propagation. Our core discovery is that, once effectively adapted at test time, the rich feature distribution of aerial point clouds can be distilled into a compact set of well-separated semantic centroids that are transferable across label spaces. COSTA leverages this to reformulate open-set semantic segmentation as a cluster-level propagating process: it first bridges the domain gap through proven test-time adaptation, then groups each batch of target-domain points into a small set of semantic clusters based on the similarity distribution in the adapted feature space, and finally propagates high-confidence pseudo labels obtained from an open-vocabulary vision-language model to all points through cluster-level voting. This cluster-centric paradigm enables test-time adaptation of aerial point clouds under significant domain gaps with mixed semantic shifts. With DALES as the source domain, COSTA enables on-demand segmentation across three aerial point cloud benchmarks with distinct domains and heterogeneous category spaces, achieving up to 70.09% mIoU under this new setting.

Cross-lingual sequence alignment is fundamental for building and exploiting parallel corpora, spanning mappings from documents and sentences down to words and subwords. Existing tools, however, typically specialize in a single granularity, so practitioners often need separate systems for word- and sentence-level alignment---especially in multilingual and long-text settings. We present OmniAlign, a unified multilingual aligner that supports both word-level and sentence-level alignment with a single lightweight model. Built on an encoder-only backbone with strong long-context modeling, OmniAlign induces word alignments from contextualized token similarity matrices, and obtains document-level $m$--$n$ sentence alignments via sentence embeddings combined with dynamic programming. To balance fine-grained alignment accuracy and sentence-representation quality, we use a four-stage training pipeline: alignment-oriented continued pre-training, self-supervised learning, supervised fine-tuning on human annotations, and sentence-embedding distillation from a strong multilingual teacher. Experiments show that OmniAlign achieves highly competitive performance on both word- and sentence-alignment benchmarks and generalizes well to unseen language pairs. Surprisingly, later-stage supervised fine-tuning on short texts further improves alignment quality while retaining the long-context understanding acquired in earlier training, keeping the model robust on long-text word alignment. \normalsize {\color{blue}\textbf{Code}: https://github.com/MilkDargon/OmniAlign}\par {\color{blue}\textbf{Model}: https://huggingface.co/WPS-Qingqiu/OmniAlign}

Methane field monitoring requires the integration of sampling design, meteorological interpretation, sensor processing, plume analysis, visualization, and reporting, but these steps are often distributed across separate expert-driven workflows. We developed a locally deployable, tool-grounded large language model (LLM) multi-agent framework for our low-cost methane sensing and field-monitoring campaigns. The framework uses LLM agents as workflow coordinators that link field measurements, meteorological data, deterministic sensor-processing routines, Gaussian plume inversion, and report generation, rather than directly estimating methane concentrations or emissions. Extensive field deployments across diverse real-world environments (e.g., wastewater treatment facilities, landfills, and oil and gas sites) demonstrate that our framework can achieve 92.0\% accuracy in workflow routing and parameter extraction, 85.0\% success in emission-rate estimation and plume prediction, and 95.0\% success in generating editable reports under practical operating conditions. Compared with manual and general-purpose LLM-assisted workflows, it reduced workflow time from hours-level to minutes-level, lowered manual coordination and prompt-engineering requirements, and retained traceable plume-based outputs. In addition, most processing can be performed locally, reducing exposure of sensitive facility and field data to cloud services. These results indicate that tool-grounded LLM coordination can reduce the time, labor, usability, and data-security barriers of methane field monitoring.