Papers

History is not preserved in complete, continuous form. Accounts of a person's activities, relationships and historical contexts are scattered across texts, chapters and narrative perspectives; historians must retrieve, identify and compare these materials to reconstruct temporal sequences and verify them against sources. Here we present AI Historian (AIH), an AI agent system that helps historians organize person-time evidence from dispersed biographical narratives. It takes source sentences as evidence units, identifies people and temporal cues, verifies candidate cross-text associations and infers comparable temporal ranges while preserving traceable source-text evidence. We evaluated AIH on six Shiji cases concerning Liu Bang, Xiang Yu and Xiao He. AIH Agent achieved a temporal-localization MicroIoU of 86.2%, compared with 81.3% for human-only annotation and 17.1% for direct large-language-model prompting; it required about 14 min, versus 1 h 32 min for human-only annotation. We further applied AIH to the Twenty-Four Histories and other ancient Chinese histories, ancient Japanese and Korean histories, and modern and contemporary historical materials, and released the results through Westlake Historian. These results indicate that AIH can reduce the cost of organizing historical materials at scale while turning connections obscured by chapter-based narration into traceable, revisable research questions for collaborative testing.

The low-rank alternating direction implicit (ADI) method is an efficient numerical technique for solving several types of large-scale matrix equations that admit low-rank solutions. The discrete-time algebraic Riccati equation (DARE) is an important matrix equation with applications in state estimation, controller design, and filter design. In the literature, the low-rank Cholesky factor ADI method for Stein equations has been used within Newton iterations to solve large-scale DAREs. However, no dedicated low-rank ADI solver is available for such DAREs. To address this gap, this paper presents a low-rank ADI solver for large-scale DAREs. We also propose an efficient approach to generate ADI shifts automatically, which makes the proposed solver fully autonomous for solving DAREs. The effectiveness of the proposed solver is compared with MATLAB's idare on a moderate-order problem. Efficiency and accuracy are further demonstrated on large-scale DAREs of order $10^6$. Numerical results confirm that the solver is efficient, accurate, and fully autonomous.

We consider a resource allocation problem with strategic agents that have private stochastic satisfaction functions and local constraints. To achieve a global optimal solution, we propose an incentive mechanism that induces a game among the agents. For the payment function of the mechanism, we construct a family of quadratic functions using the linear matrix inequality (LMI) approach that implements the social welfare maximizing outcome on the unique Nash equilibrium (NE) of the induced game while ensuring budget balance and individual rationality. Moreover, we propose a decentralized variable sample-size proximal best-response (VS-PBR) algorithm with Krasnoselskij iteration where only aggregate information is available to the agents. The algorithm is dynamically stable, as it is proven to converge in the mean-square sense to the NE of the game. The efficiency of the mechanism is then investigated on the Sioux Falls City transportation network, where electric vehicle (EV) users jointly select their destination and route.

Traditional power system analysis relies on timescale separation and the rigid-network assumption, freezing electromagnetic transients into algebraic power-flow equations via Steinmetz's phasor theory. As grid-forming converter penetration increases, magnetic energy dynamics on transmission lines interact with converter control loops on comparable timescales, challenging this rigid-network assumption. Returning to Faraday's law of electromagnetic induction driven by rotating magnetic fields, this paper models the transmission lines' rotating magnetic fields in action-angle canonical coordinates, regularizes the rigid algebraic constraints of power-flow equations into canonical equations on adiabatic symplectic manifolds, and establishes a port-Hamiltonian standard form for AC power grids. Based on the minimal-counterexample principle and using the equal-area criterion's classical two-machine system, this paper reveals a latitudinal instability channel via Bloch-sphere coordinates: Q-V control releases voltage-amplitude freedom, shifting the stability boundary from the equatorial UEP (unstable equilibrium point) to a saddle point, thereby unifying the analytical frameworks of P-delta angle stability and Q-V voltage stability in power system analysis.

Tool-using agents are commonly evaluated by a single bit: whether an end-to-end workflow completed. This metric fails to distinguish failures that matter in production, such as expired credentials, malformed payloads, or correct execution followed by incorrect final delivery. We introduce APIFlow-Bench, a fully auditable benchmark for long-horizon, dependent REST-API workflows that decomposes performance into seven engineering capabilities and requires agents to produce answers supported by the actual call path. We generate synthetic API worlds forward, subtask by subtask; each subtask is admitted only after a zero-LLM self-test triad verifies its grader and an oracle establishes solvability, and an adversarial audit identified and fixed six grader exploits. Grading is deterministic and provenance-sensitive: a state check traces a mock-minted canary through the API data flow to the response the answer must originate from, and a typed answer card is verified field by field. We release all answer keys and 44,362 unredacted execution transcripts. Across 19 frontier and open-weight models under one neutral scaffold, we find: (1) longer dependency chains degrade success, from 93% on individual subtasks to 74% on clean 20-subtask chains and 61% when including the 8% of chain trials that a model-consensus screen flags as passed by no model; (2) reliability separates models more than best-case capability, with best-of-five spanning seven points but all-five-of-five reliability spanning 44 points; (3) the independent-error account of compounding failure does not fit the data: pass rates on 20-subtask chains are 33 percentage points above the product of subtask-level rates, and on the clean slice 77% of failing runs reached the correct final state and failed only at delivery.

We propose a scalable, validity-oriented pipeline for evaluating biomedical LLM judges when high-quality human judgments are scarce. First, we augment existing human-labelled biomedical benchmarks with deterministic, metric-grounded mutations that produce auditable preference pairs. Second, we evaluate judges beyond aggregate correctness using three deployment-relevant dimensions: correctness against metric-derived gold labels, robustness under repeated stochastic sampling, and compliance with the requested output format. We use this pipeline to assess Llama-3.1-8B-Instruct under four regimes: (1) base, using the instruct model as is; (2) SFT, distillation-based supervised fine-tuning only; (3) RL, GRPO-based reinforcement learning only; and (4) SFT$\rightarrow$RL, SFT followed by RL. The base and single-stage regimes struggle on structured medical discrimination such as PICO extraction and clinical calculations, whereas SFT$\rightarrow$RL performs best across correctness, compliance, and robustness; gains concentrate on decomposable tasks (PICO, MedCalc), at times matching or outperforming frontier models.

Referring single-object tracking enables language-grounded target initialization and subsequent tracking by jointly leveraging semantic cues and visual templates. The core difficulty is to use language differently across stages: it is indispensable for grounding but can induce semantic drift during tracking when overemphasized. Meanwhile, current methods often require costly vision-language alignment training. We present LVTrack, a pure transformer framework that introduces a mode-conditioned Gated Feature Injector to adaptively regulate textual guidance and alleviate semantic drift. Together with targeted adaptations, it directly harnesses a frozen vision-language pretrained model, greatly reducing training cost and preserving strong language understanding. To further improve temporal localization, LVTrack integrates hybrid relative-absolute positional encodings with a lightweight memory mechanism and optimizes autoregressive box prediction using a Gaussian-smoothed KL loss. Extensive experiments on standard benchmarks demonstrate that LVTrack achieves strong performance.

Training a video-generation model from scratch is hard for reasons that precede model design. The feedback loop is long: a failure that appears only after a training run can make each attempted fix another run. The data are hard to reach: the corpora and recipes behind strong models are large, heterogeneous, and often unreleased. And scoring is blunt: open-ended generation has no single correct output, and an aggregate score does not by itself establish whether a sample succeeds or which property failed. Dancing Stick Figures is a synthetic video dataset built against these three obstacles. For iteration speed, its 64x64, 64-frame reference task is sized for practical repeated training on a single workstation GPU. For accessibility, the release is a 0.79-GB training tier of 4,020 video clips–1,340 six-second source motions, each rendered from three cameras by a deterministic dataset-generation harness–with checkpoints and a Colab workflow that reruns the reference training pipeline at reduced budget on a 16 GB Tesla T4. For scoring, every frame retains its generating state (ARDY cskel27 joint positions, camera, body parameters, and source motion) and per-pixel depth, surface normals, and part labels. These annotations support dataset-specific metrics for visible topology and part-wise motion; corruptions expose their sensitivities and blind spots.

Open-Vocabulary Audio-Visual Semantic Segmentation (OV-AVSS) aims to perform pixel-level segmentation of sound-emitting objects from an open set of categories. The previous method relies on a class-agnostic foreground definition, which groups semantically diverse objects into a heterogeneous positive set, causing the model to learn unstable sounding patterns and produce unreliable proposals. To address this, we reformulate the objective to be category-specific and propose a novel Acoustically Grounded Cost Learning (AGCL) framework to transform the static, audio-agnostic visual-text priors into dynamic, audio-grounded cost representations. For intra-category soundingness discovery, we devise Audio-Modulated Cost Generation (AMCG) and Audio-Guided Temporal Aggregation (AGTA) modules to enable both frame-level sounding region highlighting and video-level temporal refinement with a low-intrusive audio injection mechanism. For inter-category distractor discrimination, we introduce a Synergistic Distractor Mining (SDM) strategy, which selectively penalizes acoustically and semantically confusing negative categories to learn more discriminative decision boundaries. Extensive experiments on the AVSBench-OV dataset demonstrate that our method significantly outperforms previous state-of-the-art approaches, particularly on unseen categories. Code is available at https://github.com/spyflying/AGCL.

Speech Language Models (SLMs) are increasingly deployed in multi-speaker environments, yet their ability to attribute speech to the correct speaker and reason over speaker identities remains unclear. Hence, we introduce HEAR, a conceptually hierarchical benchmark diagnosing the foundational capabilities of speaker-attributed reasoning, comprising 2.4K human-verified samples from 887 diverse multi-party audio clips. Evaluating 20 leading SLMs on HEAR reveals they struggle with these foundational tasks, often relying on semantic priors rather than actual vocal cues. To address this, we present A2R, a 30B model optimized on Counterfactual Audio with Speaker-level Hard negatives (CASH), a dataset designed to guide the model to prioritize acoustic vocal cues over linguistic signals. A2R achieves strong performance on HEAR and exhibits zero-shot generalization to diverse multi-speaker downstream tasks, demonstrating that learned speaker attribution unlocks the model's latent capacity for speaker-aware reasoning. All resources are available at https://attributetoreason.github.io/AttributeToReason/

Fine-tuning large language models (LLMs) on narrowly harmful datasets can lead to misalignment broadly, a phenomenon known as emergent misalignment (EM). EM poses a challenge for AI safety and our understanding of LLMs. Prior work often frames EM as an unexpected behavior, and explains it by appealing to general misalignment directions or anthropomorphizing it as acquiring an evil persona. However, the mechanisms behind these framings remain obscure. In this work, we show that EM is a predictable and data-dependent generalization phenomenon. By examining the base model's representation of EM training data and evaluation prompts, we find that evilness after EM training is highly predictable from representational distance: the closer an evaluation prompt is to training data centroid, the more evilness it elicits from EM models after training (with an average Spearman correlation of -0.73 across 12 model-dataset settings). Building upon this analysis, we further demystify EM by showing that (1) its effectiveness changes significantly based on training data format; (2) there is not a general misalignment direction that transfers across different EM models; (3) the effect of EM is fundamentally different from persona changes. Furthermore, we extend the EM generalization metric from a scalar distance to a dataset-specific generalization direction, which robustly predicts EM models' evilness under semantics-preserving prompt perturbations including appending random tokens and paraphrasing, where other methods do not reliably generalize.

Vision-and-Language Navigation (VLN) requires agents to reason over accumulated observations while continuously exploring unseen regions. However, existing environment representations often struggle to jointly support explicit semantic memory and continuous exploration guidance. To address this challenge, we propose Cognitive Graph-Field Memory (CGFM), a persistent multimodal scene representation that couples explicit relational memory with continuous spatial intuition. CGFM organizes objects, spatial relations, and visual observations into a multimodal scene graph, enabling target retrieval and long-horizon reasoning across navigation tasks. When no reliable target match is identified, graph-based evidence is projected into a goal-conditioned semantic-frontier field to guide exploration toward semantically promising frontiers and regions. Building upon CGFM, we introduce CGFM-Nav, a foundation-model-based framework for lifelong multimodal navigation that integrates task-relevant subgraph selection, VLM reasoning, and verification feedback into a closed decision loop. Preliminary experiments on GOAT-Bench show that, under the same Qwen3-VL-8B backbone, CGFM-Nav improves the overall success rate from 53.2% to 63.0% and SPL from 30.0% to 39.6%, demonstrating the effectiveness of combining explicit semantic memory with semantic-guided exploration.

We aim to improve frozen DINOv3 dense-prediction models under distribution shift by adding inference computation inside the visual backbone, without changing model weights, task adapters, or prediction heads. The challenge is that repeated transformer-block computation must refine dense features without disrupting the pairwise patch relations that DINOv3 uses to preserve spatial structure. We introduce GramLoop, a training-free framework that replays a short transformer window and controls each replay through final-layer cosine-Gram consistency. Each proposal is propagated through the frozen suffix, measured against the standard DINOv3 trajectory, and accepted through a patchwise gate at the replay-window endpoint. Across object detection and semantic segmentation under corruptions, perturbations, and natural shifts, GramLoop improves all five shifted benchmarks over the paired DINOv3 baseline. On COCO-O, it improves mAP by +0.252 and Effective Robustness by +0.250, while preserving clean ADE20K performance. Code will be released at https://github.com/cheyan9/GramLoop.

Recent advances in anomaly detection (AD) for industrial inspection have pushed performance on standard benchmarks toward saturation. However, strong benchmark performance does not necessarily translate to real-world deployment, as these benchmarks are primarily collected under controlled acquisition conditions. Changes in illumination, background, viewpoint, and other environmental factors can shift normal samples away from the learned normal distribution and cause false anomaly responses. We address AD under such distribution shifts by explicitly modeling nuisance variation from changing imaging conditions in feature space. Without anomaly labels or target-domain data, our Nuisance-Filtered Anomaly Detection (NFAD) framework estimates a nuisance subspace from matched feature displacements induced by content-preserving perturbations and suppresses its contribution to anomaly residuals at inference. The same subspace supports two complementary branches: full projection for image-level detection and selective suppression for pixel-level localization, preserving evidence of localized defects. On AeBAD-S, a benchmark specifically designed for AD under acquisition shifts, NFAD achieves 91.0% image-level AUROC, establishing a new state of the art. Notably, this robustness does not come at the expense of conventional AD performance: NFAD remains competitive on standard benchmarks that do not explicitly evaluate distribution shift, including VisA, Real-IAD, and MVTec AD. These results show that explicitly suppressing such nuisance variation improves AD under distribution shift while preserving strong performance in standard settings.

Applications such as personalized assistance and proprietary document analysis require large language models (LLMs) to generate outputs from private data. Yet powerful LLMs typically cannot be deployed on the resource-constrained devices where private data resides, and uploading private data to cloud-hosted LLMs exposes sensitive information. Recent work addresses this tension with a cloud-edge collaborative decoding paradigm, where private data are kept on the edge with a small language model (SLM) producing next-token distributions, which are fused with predictions from a cloud LLM operating solely on public data. In this paper, we systematically analyze the privacy risks of such a paradigm with a novel evaluation framework using constructed QA datasets, which show that such collaboration can expose substantial private-context information. To address such privacy leakage, we propose CoVeil, a defense mechanism which dynamically optimizes transmitted signals to suppress leakage during decoding time while preserving the collaborative quality. Extensive evaluations demonstrate that CoVeil consistently improves the privacy-utility trade-off over existing baselines by reducing data leakage by up to 87.2%, with minimal accuracy loss.

The United States has allocated approximately $65 billion through the Infrastructure Investment and Jobs Act for broadband expansion, yet evidence-based methods for targeting these investments remain underdeveloped. This paper presents an explainable machine learning framework for profiling broadband adoption disparities at census-tract granularity across 83,359 tracts nationwide. Using 65 socioeconomic, demographic, and infrastructure features derived from the American Community Survey 2022, we train a LightGBM model under spatial five-fold cross-validation, achieving R^2 = 0.533 and Spearman rho = 0.763; state-held-out cross-validation (51 folds) confirms generalization (R^2 = 0.525). TreeSHAP analysis identifies income and education as the dominant factor group (with the engineered interaction term absorbing attribution from its constituent features), and SHAP-based clustering reveals three exploratory factor profiles: Well-Connected Moderate (~49K tracts), Affordability-Limited Severe (~21K tracts), and Rural-Elderly (~13K tracts). As a screening tool, ML-based tract selection captures 38.0% of the total adoption gap within the top 10% of tracts versus 35.2% for income-only heuristics (+2.8 pp, p < 0.002, county-block bootstrap); in regret-reduction terms, the model closes 19% of the remaining gap between income-only and oracle selection. The primary contribution is the per-tract factor decomposition: SHAP identifies which feature groups (income/education, rurality, age) are most strongly associated with each tract's predicted gap, and informs differentiated investigation. A temporal stability check, training on ACS 2017 and predicting ACS 2022 with zero survey-year overlap, confirms ranking stability (rho = 0.784, noting hyperparameters tuned on 2022 data).

Large language models often answer structurally unanswerable questions, such as computing cot(-540{\deg}) or evaluating (1).startswith("1"), instead of abstaining. We ask whether this failure reflects missing recognition or failed routing from recognition to abstention. Across instruction-tuned models from 1.7B to 70B parameters, a single linear direction in the hidden state separates answerable from structurally impossible math and code prompts, showing that models represent impossibility before generation. Yet this recognition direction is nearly orthogonal to the canonical safety-refusal direction that mediates trained harmful-content refusal. An in-domain behavior-defined invalidity-aware direction is closer to recognition, but only partially aligned with it, and remains near-orthogonal to safety refusal. Generation-time steering along the recognition direction changes invalidity-aware behavior bidirectionally and dose-responsively on structural math and code cells, while random directions do not. Base/instruct comparisons further show that the low-cosine geometry is already present at the pretraining endpoint. The confident-on-impossible failure is therefore better explained as a routing failure than as an encoding failure: the model has a usable "no admissible answer" signal, but the safety-refusal pathway is not aligned to use it.

Four-wheel independent steering (4WIS) mobile robots support multiple motion modes, offering high maneuverability in narrow and complex environments. However, existing planning methods often fail to fully exploit these capabilities, leading to suboptimal trajectory quality. To address this limitation, this paper proposes a multi-modal global trajectory planning framework that couples mode-augmented front-end search with mode-consistent segment-wise trajectory optimization. In the front-end stage, Hybrid A* is extended to a four-dimensional state space incorporating motion modes, while mode-switching-aware cost and heuristic functions embed mode decisions into the global search process. Multi-modal Reeds-Shepp curves and an intelligent terminal connection strategy are further designed to improve search efficiency. In the back-end stage, a segment-wise trajectory optimization framework based on an improved iterative safe corridor scheme is developed to convert discrete multi-modal paths into smooth, kinematically feasible trajectories with stationary mode transitions. Experimental results show that the proposed method achieves the best overall performance in safety, arrival time, terminal accuracy and computation time. Real-world experiments on a physical 4WIS robot further validate the practical effectiveness and executability of the generated trajectories, providing a flexible and high-performance solution for multi-modal mobile robot trajectory planning.

While modern generative models excel at modeling complex data, precise inference-time control in conditional generation remains a critical challenge. Classifier-free guidance (CFG) is a primary mechanism for such control, yet it is typically treated as a static tuning parameter. In flow-based models, however, the guidance scale fundamentally dictates the velocity field and the resulting probability path, making guidance selection a dynamic path-optimization problem. We introduce PathGuide, a framework that reformulates scalar CFG selection as an on-policy transport problem. Leveraging the weak form of the continuity equation, we derive a selection criterion with a direct path-correctness interpretation: we prove that if the guided field is weakly equivalent to the exact conditional field along the generated rollout, the sampler's path coincides with the target conditional law. For scalar CFG, this criterion yields a strictly quadratic local objective with an efficient, closed-form selector for each solver interval. PathGuide enables optimal guidance scales to be computed and used online during generation or fitted offline as a reusable piecewise-constant schedule. We validate our method on low-resolution image manifolds and controlled settings across various continuous-time flow constructions, demonstrating that this transport-based selector improves path alignment and sample fidelity over both fixed and state-of-the-art adaptive guidance baselines.

While neural rendering methods such as 3D Gaussian Splatting achieve remarkable visual fidelity, traditional polygonal meshes remain the backbone of established graphics pipelines. Triangle splatting bridges this gap by optimizing triangle primitives as differentiable splats, producing representations that are closer to mesh-based workflows. Central to these methods is the kernel function that softens triangle boundaries to propagate gradients to vertex positions. Existing triangle splatting methods make inconsistent choices of kernel functions, and analysis of these kernels' optimization behavior has been limited to unstructured triangle soups for novel-view synthesis. In this work, we consider triangle splatting as a generic tool for photometric optimization, comparing kernel properties through two complementary tasks: mesh optimization for shape reconstruction and triangle soup optimization for novel-view synthesis. Along with the analysis, we introduce an elastic kernel function that features bilateral gradient support across the boundary and an adaptive boundary value, which are shown to be essential for robust optimization. Under isolated comparison, our elastic kernel outperforms existing kernels on shape reconstruction and in the majority of novel-view synthesis benchmarks, demonstrating the importance of kernel design in the effectiveness and versatility of triangle splatting.

This paper presents a convergence analysis for a newly developed nonlinear model reduction method: parametric probabilistic manifold decomposition (PPMD)~\cite{guo2026parametric}. In addition, existing analyzes of nonlinear reduced order models typically treat subspace reduction, manifold representation, regression, and nonlinear reconstruction as separate components and often remain at the level of discrete state vectors. To the best of our knowledge, no theory tracks the complete error propagation in a data-dependent model whose basis, residual geometry, spectral coordinates, parameter maps, and lifting operator are all learned from the same numerical solution data. We develop a coupled perturbation analysis for the entire PPMD procedure. A trajectory geometry induced by the spatial discretization and temporal quadrature connects discrete trajectory vectors isometrically with the corresponding PDE norm. Population spectral objects are introduced to align the empirical residual coordinates and derive a uniform coordinate error estimate, whose propagation through the Hilbert-valued kernel lifting estimator is then quantified. Combining these results with the full order discretization error, weighted low-rank approximation, parameter regression, and residual representation defect yields deterministic and high-probability trajectory error bounds and consistency in probability in the continuous PDE trajectory space. The theory identifies how the principal errors interact and which components limit the accuracy of the nonlinear reduced order model.

Stateful serverless (Function-as-a-Service) environments, whose workers host state servers, are increasingly used for stream processing. A stream application is a pipeline of operators, where each operator forwards intermediate data downstream through a chained request. As input rates fluctuate, the system should adjust operator parallelism and place instances across workers to sustain the incoming rate. Existing approaches do so without fully accounting for chained-request overhead, leading them to misestimate the required number of workers. Too few leave the cluster unable to keep up with the input rate, while too many route a larger fraction of chained requests across worker boundaries, increasing end-to-end latency. We propose CLASP, a scaling and scheduling strategy for stream processing in stateful serverless environments. At runtime, CLASP estimates execution cost and chained-request cost from observed metrics. Under a capacity model that covers the two costs, it adjusts operator parallelism and packs operators onto the fewest workers that can sustain the target input rate. Once a scaling decision is made, CLASP migrates each operator's state together with its instances, thereby minimizing execution pause time. Experiments show that CLASP improves throughput by up to 3.3x and reduces median end-to-end latency by up to 76% compared with state-of-the-art scaling strategies.

This paper develops a unified theoretical framework showing that a broad family of clustering methods, including k-means, fuzzy c-means, kernel k-means, kernel FCM, and spectral clustering, can all be expressed as structured low-rank projectors acting on a signal-derived matrix. By formulating each method as an instance of min over B in C of ||M - M P_B||_F^2, with different constraint sets C, we establish a common optimization template that clarifies the algebraic links among hard, fuzzy, kernel-induced, and orthonormal projections. Within this framework, we derive non-trivial theoretical results, including geodesic convexity properties on the projection manifold, perturbation bounds quantifying stability to matrix noise, and exact recovery guarantees under ideal block-model conditions. The analysis further explains when different clustering families collapse to the same optimal subspace and how deviations arise under small inter-cluster leakage. Overall, the work provides a coherent, theory-first foundation for understanding clustering through structured projectors.

Agricultural-robot development requires simulation environments that can jointly support realistic scene construction, virtual sensing, autonomous navigation, motion planning, and manipulation-task execution. This paper presents Agri-Sim, a Unity and ROS2-based simulation platform for the closed-loop development and functional evaluation of agricultural robots. The platform contains a configurable tomato-greenhouse environment, a mobile dual-arm harvesting robot, virtual RGB-D, LiDAR, IMU, and joint sensors, and a bidirectional communication interface between Unity and ROS2. Unity is responsible for scene rendering, rigid-body dynamics, collision detection, virtual sensing, and task-state execution, whereas ROS2 and MoveIt 2 provide localization, navigation, collision-aware motion planning, inverse kinematics, and trajectory generation. Autonomous greenhouse navigation and dual-arm tomato harvesting were used to evaluate the complete simulation workflow. The experiments covered virtual sensor publication, ROS2-based navigation, collision-aware motion planning, mobile-base control, tomato acquisition, inter-arm handover, and box placement. The results demonstrate that Agri-Sim supports closed-loop integration and repeatable functional evaluation of navigation and manipulation workflows in a controlled virtual greenhouse, providing a practical foundation for subsequent algorithm development and Sim-to-Real studies.

Temperature scaling is a core component of knowledge distillation, yet its role and effect are still not fully understood. Transformed Teacher Matching (TTM) clarifies the role of temperature scaling by applying it only to the teacher distribution and interpreting the resulting objective as standard distillation with an implicit Rényi entropy regularization on the student. However, TTM still relies on a fixed temperature and does not specify how the teacher-side temperature should be adapted for individual samples. In this paper, we introduce a sample-wise inverse-temperature update for TTM by locally minimizing the Kullback-Leibler divergence between the temperature-scaled teacher distribution and the student's prediction. We derive closed-form first and second derivatives with respect to the inverse temperature, and show that they can be expressed using variance and covariance statistics of centered teacher and student logits under the transformed teacher weighting. This yields an efficient curvature-aware update that requires one softmax evaluation and a constant number of class-wise weighted sums. Experiments on standard image classification distillation benchmarks show that our temperature adaptation generally improves TTM and WTTM, while remaining competitive with or outperforming prior temperature-adaptive distillation baselines.

Multimodal safety moderation requires distinguishing risks arising from visual content, user intent, and assistant behavior. Existing safeguards, however, are typically trained for a single judgment target and reduce safety assessment to a binary decision. Consequently, risk becomes difficult to compare across a multimodal interaction, and ambiguous cases are obscured. We introduce SafeAtlas-VL, a dataset of 1.5M training instances that places image-, request-, and response-level judgments on a five-level ordered scale. We curate a broad collection of safety-relevant data from both real-world and synthetic sources and apply a disagreement-aware annotation procedure. The resulting dataset spans 15 harm categories and 55 fine-grained subcategories, covering a broad range of multimodal safety scenarios. We also construct SafeAtlas-Bench, a held-out set of 5,000 instances for evaluating five-level predictions and continuous risk scores. Upon this dataset, we train the SafeAtlas Guard series of models via target-conditioned tuning for multimodal safety detection. Our models not only perform five-way classification of safety levels but also map safety to continuous scores through a soft cumulative ordinal head. Experimental results demonstrate that guard models trained on our dataset exhibit strong generalization: even without using the training sets of other benchmarks, they achieve competitive performance on the corresponding test sets. Notably, our 8B model attains the overall best performance, outperforming the previous SOTA by approximately 4% in F1 score. Code, data, and models are released to support further research. Warning: this paper contains example data that may be offensive, harmful, graphic, or disturbing.

This paper studies the problem of proportionally fair clustering, where the goal is to select $k$ “centers” from a metric space that fairly represent a set of agents who also lie in the metric space. Specifically, we focus on finding a clustering satisfying a fairness property known as the Droop core. In the practical special case in which the set of feasible center locations contains every agent location, the previous best-known result guaranteed a $(1 + \sqrt{2})$-approximation of the Droop core, while the best-known lower bound was $2$. In this paper, we show that this lower bound is tight and that a clustering in the $2$-Droop core always exists. Further, we show that such a clustering can be achieved by only selecting centers from locations in the metric space where an agent resides. We establish this using Scarf's theorem guaranteeing a nonempty core for balanced non-transferable utility games. This result has several interesting corollaries. Most notably, it resolves the $\beta$-plurality problem of Aronov et al. [2021] for general metric spaces. The main result of this paper was generated by $\mathtt{ChatGPT}$-$\mathtt{5.6}$-$\mathtt{Sol}$ through a series of interactions with the authors. The authors of this paper verified the generated proof and rewrote it for clarity.

The ongoing changes in software engineering requirements have created a substantial need for automated tools which can create secure source code from natural language input. The performance of traditional Large Language Models (LLMs) becomes limited by their "one-shot" capability which results in logical hallucinations together with reduced algorithmic performance during complicated operations. The research presents an autonomous AI Coding Agent which establishes a connection between LLM-generated content and production-ready software through its organized methodology for decision making. Our framework uses the Gemini 2.5 Flash API for essential reasoning capabilities while employing a tailored Monte Carlo Tree Search (MCTS) method to solve code generation challenges as a search operation. The agent uses a "Self-Critic" evaluator system to test different implementation methods which it ranks according to their accuracy and difficulty level before it improves its operational framework through backpropagation. The system operates through a Flask-based web interface which delivers instant feedback together with syntax highlighting features. Our experimental results show that the MCTS-based method achieves a 92% success rate on complex logical prompts while surpassing standard zero-shot generation models.

This paper will discuss the relationships among three pillars of mathematics: important research in codes and automata by Marcel-Paul Schutzenberger and others; random walks on finite semigroups by Persi Diaconis and others; and advanced techniques from finite semigroup theory used in proving Krohn-Rhodes complexity c is decidable by Stuart Margolis, Anne Schilling, and myself. Very surprising connections exist between the Fundamental Lemma of Complexity c (epimorphisms between finite semigroups that are one-to-one on subgroups preserve c) and coupling from the past in Markov chains, Diaconis' strong stationary time, and the Crick-Franklin-Watson genes of a finite automaton (which will be defined in the paper).

We propose Titans-QFWP, a hybrid reinforcement learning architecture integrating a Quantum Fast Weight Programmer with Titans-style memory (Persistence, Surprise, and Forgetting) for adaptive portfolio optimization. To address high-dimensional market features, we introduce an enhanced A3C^2 framework with Hungarian-aligned K-means clustering and scaled log-return rewards. Evaluated on 468 S&P 500 stocks under an Equal-Parameter-Count (EPC) benchmark with approximately 3,000 trainable parameters, Titans-QFWP achieves strong performance (median ARR 0.4260, Calmar 8.5504, IR 0.8427). Ablation results reveal that quantum gating fundamentally reshapes memory component roles, with Persistence supporting drawdown control, Surprise contributing to return generation, and Forgetting providing additional stabilization. By stabilizing these quantum representations, the model enables defensive allocation during market drawdowns while preserving upside potential.