Record linkage, the process of matching records that refer to the same entity across datasets, is essential to empirical social science but remains methodologically underdeveloped. Researchers treat it as a preprocessing step, applying ad hoc rules without quantifying the uncertainty that linkage errors introduce into downstream analyses. Existing methods either achieve low accuracy or require substantial labeled training data. I present EnsembleLink, a method that achieves high accuracy without any training labels. EnsembleLink leverages pre-trained language models that have learned semantic relationships (e.g., that "South Ozone Park" is a neighborhood in "New York City" or that "Lutte ouvriere" refers to the Trotskyist "Workers' Struggle" party) from large text corpora. On benchmarks spanning city names, person names, organizations, multilingual political parties, and bibliographic records, EnsembleLink matches or exceeds methods requiring extensive labeling. The method runs locally on open-source models, requiring no external API calls, and completes typical linkage tasks in minutes.

Explanations provided by Self-explainable Graph Neural Networks (SE-GNNs) are fundamental for understanding the model's inner workings and for identifying potential misuse of sensitive attributes. Although recent works have highlighted that these explanations can be suboptimal and potentially misleading, a characterization of their failure cases is unavailable. In this work, we identify a critical failure of SE-GNN explanations: explanations can be unambiguously unrelated to how the SE-GNNs infer labels. We show that, on the one hand, many SE-GNNs can achieve optimal true risk while producing these degenerate explanations, and on the other, most faithfulness metrics can fail to identify these failure modes. Our empirical analysis reveals that degenerate explanations can be maliciously planted (allowing an attacker to hide the use of sensitive attributes) and can also emerge naturally, highlighting the need for reliable auditing. To address this, we introduce a novel faithfulness metric that reliably marks degenerate explanations as unfaithful, in both malicious and natural settings. Our code is available at https://github.com/steveazzolin/gnn_deg_expl.

Training a single network with multiple objectives often leads to conflicting gradients that degrade shared representations, forcing them into a compromised state that is suboptimal for any single task--a problem we term latent representation collapse. We introduce Domain Expansion, a framework that prevents these conflicts by restructuring the latent space itself. Our framework uses a novel orthogonal pooling mechanism to construct a latent space where each objective is assigned to a mutually orthogonal subspace. We validate our approach across diverse benchmarks--including ShapeNet, MPIIGaze, and Rotated MNIST--on challenging multi-objective problems combining classification with pose and gaze estimation. Our experiments demonstrate that this structure not only prevents collapse but also yields an explicit, interpretable, and compositional latent space where concepts can be directly manipulated.

Latent-space optimization methods for counterfactual explanations - framed as minimal semantic perturbations that change model predictions - inherit the ambiguity of Wachter et al.'s objective: the choice of distance metric dictates whether perturbations are meaningful or adversarial. Existing approaches adopt flat or misaligned geometries, leading to off-manifold artifacts, semantic drift, or adversarial collapse. We introduce Perceptual Counterfactual Geodesics (PCG), a method that constructs counterfactuals by tracing geodesics under a perceptually Riemannian metric induced from robust vision features. This geometry aligns with human perception and penalizes brittle directions, enabling smooth, on-manifold, semantically valid transitions. Experiments on three vision datasets show that PCG outperforms baselines and reveals failure modes hidden under standard metrics.

Group Relative Policy Optimization (GRPO) significantly enhances the reasoning performance of Large Language Models (LLMs). However, this success heavily relies on expensive external verifiers or human rules. Such dependency not only leads to significant computational costs and training latency, but also yields sparse rewards that hinder optimization efficiency. To address these challenges, we propose Latent-GRPO, a framework that derives intrinsic rewards directly from latent space geometry. Crucially, our empirical analysis reveals a compelling geometric property: terminal token representations of correct reasoning trajectories form dense clusters with high intra-class similarity, whereas incorrect trajectories remain scattered as outliers. In light of this discovery, we introduce the Iterative Robust Centroid Estimation (IRCE) algorithm, which generates dense, continuous rewards by mitigating magnitude fluctuations via spherical projection and estimating a robust ``truth centroid'' through iterative aggregation. Experimental results on multiple datasets show that our method maintains model performance while achieving a training speedup of over 2x compared to baselines. Furthermore, extensive results demonstrate strong generalization ability and robustness. The code will be released soon.

Dynamic voltage and frequency scaling (DVFS) and task-to-core allocation are critical for thermal management and balancing energy and performance in embedded systems. Existing approaches either rely on utilization-based heuristics that overlook stall times, or require extensive offline profiling for table generation, preventing runtime adaptation. Building upon hierarchical multi-agent scheduling, we contribute model-based reinforcement learning with accurate environment models that predict thermal dynamics and performance states, enabling synthetic training data generation and converging 20 times faster than model-free methods. We introduce Large Language Model (LLM)-based semantic feature extraction that characterizes OpenMP programs through code-level features without execution, enabling zero-shot deployment for new workloads in under 5 seconds without workload-specific profiling. Two collaborative agents decompose the exponential action space, achieving 358ms latency for subsequent decisions. Experiments on Barcelona OpenMP Tasks Suite (BOTS) and PolybenchC benchmarks across NVIDIA Jetson TX2, Jetson Orin NX, RubikPi, and Intel Core i7 demonstrate 7.09 times better energy efficiency, 4.0 times better makespan, and 358ms decision latency compared to existing power management techniques.

Human-like agents must express stable dispositions while adapting to roles, relationships, and norms. We present PsyAgent, a schema-first framework that operationalizes the trait-context interface by coupling a Big Five trait prior with explicit social-structural conditioning. PsyAgent comprises (i) Individual Structure (IS), a machine-usable trait-grounded profile, and (ii) Multi-Scenario Contexting (MSC), a curated library of role-relationship-norm frames spanning eight everyday arenas. At inference, fixed structured prompts couple the active MSC frame with the IS profile, encouraging behavior that is stable yet context-sensitive. To demonstrate learnability beyond prompt engineering, we use IS and MSC to synthesize supervision and fine-tune compact backbones with PEFT (SFT and optional DPO). Under a controlled psychometric-style evaluation protocol in percentile space, PsyAgent improves trait-faithfulness and long-horizon stability, and is competitive with several larger general-purpose instruction-tuned baselines under matched decoding and scoring controls. We further triangulate the automatic protocol with external benchmarks and a small blinded human study. Overall, PsyAgent provides a precise and data-efficient approach to personality-grounded, norm-aware agents.

Recent advances in large language models (LLMs) enable agentic systems trained with reinforcement learning (RL) over multi-turn interaction trajectories, but practical deployment is bottlenecked by rapidly growing textual histories that inflate token budgets and memory usage. We introduce AgentOCR, a framework that exploits the superior information density of visual tokens by representing the accumulated observation-action history as a compact rendered image. To make multi-turn rollouts scalable, AgentOCR proposes segment optical caching. By decomposing history into hashable segments and maintaining a visual cache, this mechanism eliminates redundant re-rendering. Beyond fixed rendering, AgentOCR introduces agentic self-compression, where the agent actively emits a compression rate and is trained with compression-aware reward to adaptively balance task success and token efficiency. We conduct extensive experiments on challenging agentic benchmarks, ALFWorld and search-based QA. Remarkably, results demonstrate that AgentOCR preserves over 95\% of text-based agent performance while substantially reducing token consumption (>50\%), yielding consistent token and memory efficiency. Our further analysis validates a 20x rendering speedup from segment optical caching and the effective strategic balancing of self-compression.

Although Diffusion Transformer (DiT) has emerged as a predominant architecture for image and video generation, its iterative denoising process results in slow inference, which hinders broader applicability and development. Caching-based methods achieve training-free acceleration, while suffering from considerable computational error. Existing methods typically incorporate error correction strategies such as pruning or prediction to mitigate it. However, their fixed caching strategy fails to adapt to the complex error variations during denoising, which limits the full potential of error correction. To tackle this challenge, we propose a novel fidelity-optimization plugin for existing error correction methods via cumulative error minimization, named CEM. CEM predefines the error to characterize the sensitivity of model to acceleration jointly influenced by timesteps and cache intervals. Guided by this prior, we formulate a dynamic programming algorithm with cumulative error approximation for strategy optimization, which achieves the caching error minimization, resulting in a substantial improvement in generation fidelity. CEM is model-agnostic and exhibits strong generalization, which is adaptable to arbitrary acceleration budgets. It can be seamlessly integrated into existing error correction frameworks and quantized models without introducing any additional computational overhead. Extensive experiments conducted on nine generation models and quantized methods across three tasks demonstrate that CEM significantly improves generation fidelity of existing acceleration models, and outperforms the original generation performance on FLUX.1-dev, PixArt-$α$, StableDiffusion1.5 and Hunyuan. Our code is released publicly at https://github.com/leaves162/CEM.

This research proposes "ForCM", a novel approach to forest cover mapping that combines Object-Based Image Analysis (OBIA) with Deep Learning (DL) using multispectral Sentinel-2 imagery. The study explores several DL models, including UNet, UNet++, ResUNet, AttentionUNet, and ResNet50-Segnet, applied to high-resolution Sentinel-2 Level 2A satellite images of the Amazon Rainforest. The datasets comprise three collections: two sets of three-band imagery and one set of four-band imagery. After evaluation, the most effective DL models are individually integrated with the OBIA technique to enhance mapping accuracy. The originality of this work lies in evaluating different deep learning models combined with OBIA and comparing them with traditional OBIA methods. The results show that the proposed ForCM method improves forest cover mapping, achieving overall accuracies of 94.54 percent with ResUNet-OBIA and 95.64 percent with AttentionUNet-OBIA, compared to 92.91 percent using traditional OBIA. This research also demonstrates the potential of free and user-friendly tools such as QGIS for accurate mapping within their limitations, supporting global environmental monitoring and conservation efforts.

Semi-supervised 3D object detection, aiming to explore unlabeled data for boosting 3D object detectors, has emerged as an active research area in recent years. Some previous methods have shown substantial improvements by either employing heterogeneous teacher models to provide high-quality pseudo labels or enforcing feature-perspective consistency between the teacher and student networks. However, these methods overlook the fact that the model usually tends to exhibit low sensitivity to object geometries with limited labeled data, making it difficult to capture geometric information, which is crucial for enhancing the student model's ability in object perception and localization. In this paper, we propose GeoTeacher to enhance the student model's ability to capture geometric relations of objects with limited training data, especially unlabeled data. We design a keypoint-based geometric relation supervision module that transfers the teacher model's knowledge of object geometry to the student, thereby improving the student's capability in understanding geometric relations. Furthermore, we introduce a voxel-wise data augmentation strategy that increases the diversity of object geometries, thereby further improving the student model's ability to comprehend geometric structures. To preserve the integrity of distant objects during augmentation, we incorporate a distance-decay mechanism into this strategy. Moreover, GeoTeacher can be combined with different SS3D methods to further improve their performance. Extensive experiments on the ONCE and Waymo datasets indicate the effectiveness and generalization of our method and we achieve the new state-of-the-art results. Code will be available at https://github.com/SII-Whaleice/GeoTeacher

Urban Air Mobility (UAM) is an emerging application of unmanned aerial vehicles that promises to reduce travel time and alleviate congestion in urban transportation systems. As drone density increases, UAM traffic is expected to experience congestion similar to that in ground traffic. However, the fundamental characteristics of UAM traffic, particularly under real-world operating conditions, remain largely unexplored. This study proposes a general framework for constructing the fundamental diagram (FD) of UAM traffic by integrating theoretical analysis with physical experiments. To the best of our knowledge, this is the first study to derive UAM FDs using real-world physical experiment data. On the theoretical side, we design two drone control laws for collision avoidance and develop simulation-based traffic generation methods to produce diverse UAM traffic scenarios. Based on Edie's definition, traffic flow theory is then applied with a near-stationary traffic condition filtering method to construct the FD. To account for real-world disturbances and modeling uncertainties, we further conduct physical experiments on a reduced-scale testbed using Bitcraze Crazyflie drones. Both simulation and physical experiment trajectory data are collected and organized into the UAMTra2Flow dataset, which is analyzed using the proposed framework. Preliminary results indicate that classical FD structures for ground transportation, especially the Underwood model, are applicable to UAM systems. Notably, FD curves obtained from physical experiments exhibit deviations from simulation-based results, highlighting the importance of experimental validation. Finally, results from the reduced-scale testbed are scaled to realistic operating conditions to provide practical insights for future UAM traffic systems. The dataset and code for this paper are publicly available at https://github.com/CATS-Lab/UAM-FD.

Transformer-based language models have achieved remarkable performance across a wide range of tasks, yet their high inference latency poses a significant challenge for real-timeand large-scale deployment. While existing caching mechanisms,such as token-level key-value caches, offer speedups in autore-gressive decoding, they are limited in scope and applicability. In this paper, we present LLMCache, a novel layer-wise caching framework that accelerates transformer inference by reusing intermediate activations based on semantic similarity of input sequences. Unlike prior work, LLMCache is model-agnostic,operates across both encoder and decoder architectures, and supports caching at arbitrary transformer layers. We introduce a lightweight fingerprinting mechanism for matching seman-tically similar inputs and propose adaptive eviction strategies to manage cache staleness. Experiments on BERT and GPT-2 across SQuAD, WikiText-103, and OpenBookQA show up to 3.1 X speedup in inference time with <0.5% accuracy degradation. Our results highlight LLMCache as a practical and general-purpose solution for optimizing transformer inference in real-world applications

Dermatological conditions affect 1.9 billion people globally, yet accurate diagnosis remains challenging due to limited specialist availability and complex clinical presentations. Family history significantly influences skin disease susceptibility and treatment responses, but is often underutilized in diagnostic processes. This research addresses the critical question: How can AI-powered systems integrate family history data with clinical imaging to enhance dermatological diagnosis while supporting clinical trial validation and real-world implementation? We developed a comprehensive multi-modal AI framework that combines deep learning-based image analysis with structured clinical data, including detailed family history patterns. Our approach employs interpretable convolutional neural networks integrated with clinical decision trees that incorporate hereditary risk factors. The methodology includes prospective clinical trials across diverse healthcare settings to validate AI-assisted diagnosis against traditional clinical assessment. In this work, validation was conducted with healthcare professionals to assess AI-assisted outputs against clinical expectations; prospective clinical trials across diverse healthcare settings are proposed as future work. The integrated AI system demonstrates enhanced diagnostic accuracy when family history data is incorporated, particularly for hereditary skin conditions such as melanoma, psoriasis, and atopic dermatitis. Expert feedback indicates potential for improved early detection and more personalized recommendations; formal clinical trials are planned. The framework is designed for integration into clinical workflows while maintaining interpretability through explainable AI mechanisms.

At the boundary between the known and the unknown, an agent inevitably confronts the dilemma of whether to explore or to exploit. Epistemic uncertainty reflects such boundaries, representing systematic uncertainty due to limited knowledge. In this paper, we propose a Bayesian reinforcement learning (RL) algorithm, $\texttt{EUBRL}$, which leverages epistemic guidance to achieve principled exploration. This guidance adaptively reduces per-step regret arising from estimation errors. We establish nearly minimax-optimal regret and sample complexity guarantees for a class of sufficiently expressive priors in infinite-horizon discounted MDPs. Empirically, we evaluate $\texttt{EUBRL}$ on tasks characterized by sparse rewards, long horizons, and stochasticity. Results demonstrate that $\texttt{EUBRL}$ achieves superior sample efficiency, scalability, and consistency.

Vision-based imitation learning has enabled impressive robotic manipulation skills, but its reliance on object appearance while ignoring the underlying 3D scene structure leads to low training efficiency and poor generalization. To address these challenges, we introduce \emph{Implicit Scene Supervision (ISS) Policy}, a 3D visuomotor DiT-based diffusion policy that predicts sequences of continuous actions from point cloud observations. We extend DiT with a novel implicit scene supervision module that encourages the model to produce outputs consistent with the scene's geometric evolution, thereby improving the performance and robustness of the policy. Notably, ISS Policy achieves state-of-the-art performance on both single-arm manipulation tasks (MetaWorld) and dexterous hand manipulation (Adroit). In real-world experiments, it also demonstrates strong generalization and robustness. Additional ablation studies show that our method scales effectively with both data and parameters. Code and videos will be released.

Can large language models introspect, that is, accurately detect perturbations to their own internal states? We systematically investigate this question using activation steering in Meta-Llama-3.1-8B-Instruct. First, we show that the binary detection paradigm used in prior work conflates introspection with a methodological artifact: apparent detection accuracy is entirely explained by global logit shifts that bias models toward affirmative responses regardless of question content. However, on tasks requiring differential sensitivity, we find robust evidence for partial introspection: models localize which of 10 sentences received an injection at up to 88\% accuracy (vs.\ 10\% chance) and discriminate relative injection strengths at 83\% accuracy (vs.\ 50\% chance). These capabilities are confined to early-layer injections and collapse to chance thereafter -- a pattern we explain mechanistically through attention-based signal routing and residual stream recovery dynamics. Our findings demonstrate that LLMs can compute meaningful functions over perturbations to their internal states, establishing introspection as a real but layer-dependent phenomenon that merits further investigation. Our code is open-sourced here: https://github.com/elyhahami18/llama-introspection-new

Generalist robot policies, trained on large and diverse datasets, have demonstrated the ability to generalize across a wide spectrum of behaviors, enabling a single policy to act in varied real-world environments. However, they still fall short on new tasks not covered in the training data. When finetuned on limited demonstrations of a new task, these policies often overfit to the specific demonstrations--not only losing their prior abilities to solve a wide variety of generalist tasks but also failing to generalize within the new task itself. In this work, we aim to develop a method that preserves the generalization capabilities of the generalist policy during finetuning, allowing a single policy to robustly incorporate a new skill into its repertoire. Our goal is a single policy that both learns to generalize to variations of the new task and retains the broad competencies gained from pretraining. We show that this can be achieved through a simple yet effective strategy: interpolating the weights of a finetuned model with that of the pretrained model. We show, across extensive simulated and real-world experiments, that such model merging produces a single model that inherits the generalist abilities of the base model and learns to solve the new task robustly, outperforming both the pretrained and finetuned model on out-of-distribution variations of the new task. Moreover, we show that model merging performance scales with the amount of pretraining data, and enables continual acquisition of new skills in a lifelong learning setting, without sacrificing previously learned generalist abilities.

We propose Synchronous Dual-Arm Rearrangement Planner (SDAR), a task and motion planning (TAMP) framework for tabletop rearrangement, where two robot arms equipped with 2-finger grippers must work together in close proximity to rearrange objects whose start and goal configurations are strongly entangled. To tackle such challenges, SDAR tightly knit together its dependency-driven task planner (SDAR-T) and synchronous dual-arm motion planner (SDAR-M), to intelligently sift through a large number of possible task and motion plans. Specifically, SDAR-T applies a simple yet effective strategy to decompose the global object dependency graph induced by the rearrangement task, to produce more optimal dual-arm task plans than solutions derived from optimal task plans for a single arm. Leveraging state-of-the-art GPU SIMD-based motion planning tools, SDAR-M employs a layered motion planning strategy to sift through many task plans for the best synchronous dual-arm motion plan while ensuring high levels of success rate. Comprehensive evaluation demonstrates that SDAR delivers a 100% success rate in solving complex, non-monotone, long-horizon tabletop rearrangement tasks with solution quality far exceeding the previous state-of-the-art. Experiments on two UR-5e arms further confirm SDAR directly and reliably transfers to robot hardware. Source code and supplementary materials are available at https://github.com/arc-l/dual-arm.

The statistical over-representation of phonological features in the basic vocabulary of languages is often interpreted as reflecting potentially universal sound symbolic patterns. However, most of those results have not been tested explicitly for reproducibility and might be prone to biases in the study samples or models. Many studies on the topic do not adequately control for genealogical and areal dependencies between sampled languages, casting doubts on the robustness of the results. In this study, we test the robustness of a recent study on sound symbolism of basic vocabulary concepts which analyzed 245 languages.The new sample includes data on 2864 languages from Lexibank. We modify the original model by adding statistical controls for spatial and phylogenetic dependencies between languages. The new results show that most of the previously observed patterns are not robust, and in fact many patterns disappear completely when adding the genealogical and areal controls. A small number of patterns, however, emerges as highly stable even with the new sample. Through the new analysis, we are able to assess the distribution of sound symbolism on a larger scale than previously. The study further highlights the need for testing all universal claims on language for robustness on various levels.

Large-scale pre-trained Vision-Language Models (VLMs) have demonstrated strong few-shot learning capabilities. However, these methods typically learn holistic representations where an image's domain-invariant structure is implicitly entangled with its domain-specific style. This presents an opportunity to further enhance generalization by disentangling these visual cues. In this paper, we propose Fourier-Attentive Representation Learning (FARL), a novel framework that addresses this by explicitly disentangling visual representations using Fourier analysis. The core of our method is a dual cross-attention mechanism, where learnable representation tokens separately query an image's structural features (from the phase spectrum) and stylistic features (from the amplitude spectrum). This process yields enriched, disentangled tokens that are then injected deep into the VLM encoders to guide adaptation. Our design, which includes an asymmetric injection strategy, forces the model to learn a more robust vision-language alignment. Extensive experiments on 15 datasets demonstrate the effectiveness of our approach.

Memory and computation remain core bottlenecks in long-horizon LLM inference due to the quadratic cost of self-attention and the ever-growing key-value (KV) cache. Existing strategies for memory-bounded inference, such as quantization, offloading, or heuristic KV eviction, either incur high orchestration costs or rely on unreliable attention-based proxies of importance. We propose TRIM-KV, a novel approach that learns each token's intrinsic importance at creation time via a lightweight retention gate. Each gate predicts a scalar retention score that decays over time, reflecting the long-term utility of the token for a specific layer and head. Tokens with low scores are evicted when the memory budget is exceeded, ensuring that the cache always contains the most critical tokens. TRIM-KV is trained efficiently through distillation from a frozen LLM combined with a capacity loss, requiring only gate fine-tuning and adding negligible inference overhead. Across mathematical reasoning (GSM8K, MATH-500, AIME24), procedural generation (LongProc), conversational long-memory benchmarks (LongMemEval), and long-context understanding (LongBenchV2 and SCBench), TRIM-KV consistently outperforms strong eviction and learnable retrieval baselines, especially in low-memory regimes. Remarkably, it even surpasses full-cache models in some settings, showing that selective retention can serve as a form of regularization, suppressing noise from uninformative tokens. Qualitative analyses further reveal that learned retention scores align with human intuition, naturally recovering heuristics such as sink tokens, sliding windows, and gist compression without explicit design. Beyond efficiency, retention scores provide insights into layer- and head-specific roles, suggesting a new path toward LLM interpretability.

LLMs and Agents have achieved impressive progress in code generation, mathematical reasoning, and scientific discovery. However, existing benchmarks primarily measure correctness, overlooking the diversity of methods behind solutions. True innovation depends not only on producing correct answers but also on the originality of the approach. We present InnoGym, the first benchmark and framework designed to systematically evaluate the innovation potential of AI agents. InnoGym introduces two complementary metrics: performance gain, which measures improvement over the best-known solutions, and novelty, which captures methodological differences from prior approaches. The benchmark includes 18 carefully curated tasks from real-world engineering and scientific domains, each standardized through resource filtering, evaluator validation, and solution collection. In addition, we provide iGym, a unified execution environment for reproducible and long-horizon evaluations. Extensive experiments show that while some agents produce novel approaches, their lack of robustness limits performance gains. These results highlight a key gap between creativity and effectiveness, underscoring the need for benchmarks that evaluate both.

Despite advances, video diffusion transformers still struggle to generalize beyond their training length, a challenge we term video length extrapolation. We identify two failure modes: model-specific periodic content repetition and a universal quality degradation. Prior works attempt to solve repetition via positional encodings, overlooking quality degradation and achieving only limited extrapolation. In this paper, we revisit this challenge from a more fundamental view: attention maps, which directly govern how context influences outputs. We identify that both failure modes arise from a unified cause: attention dispersion, where tokens beyond the training window dilute learned attention patterns. This leads to quality degradation and repetition emerges as a special case when this dispersion becomes structured into periodic attention patterns, induced by harmonic properties of positional encodings. Building on this insight, we propose UltraViCo, a training-free, plug-and-play method that suppresses attention for tokens beyond the training window via a constant decay factor. By jointly addressing both failure modes, we outperform a broad set of baselines largely across models and extrapolation ratios, pushing the extrapolation limit from 2x to 4x. Remarkably, it improves Dynamic Degree and Imaging Quality by 233% and 40.5% over the previous best method at 4x extrapolation. Furthermore, our method generalizes seamlessly to downstream tasks such as controllable video synthesis and editing.

Aligning large language models (LLMs) is a central objective of post-training, often achieved through reward modeling and reinforcement learning methods. Among these, direct preference optimization (DPO) has emerged as a widely adopted technique that fine-tunes LLMs on preferred completions over less favorable ones. While most frontier LLMs do not disclose their curated preference pairs, the broader LLM community has released several open-source DPO datasets, including TuluDPO, ORPO, UltraFeedback, HelpSteer, and Code-Preference-Pairs. However, systematic comparisons remain scarce, largely due to the high computational cost and the lack of rich quality annotations, making it difficult to understand how preferences were selected, which task types they span, and how well they reflect human judgment on a per-sample level. In this work, we present the first comprehensive, data-centric analysis of popular open-source DPO corpora. We leverage the Magpie framework to annotate each sample for task category, input quality, and preference reward, a reward-model-based signal that validates the preference order without relying on human annotations. This enables a scalable, fine-grained inspection of preference quality across datasets, revealing structural and qualitative discrepancies in reward margins. Building on these insights, we systematically curate a new DPO mixture, UltraMix, that draws selectively from all five corpora while removing noisy or redundant samples. UltraMix is 30% smaller than the best-performing individual dataset yet exceeds its performance across key benchmarks. We publicly release all annotations, metadata, and our curated mixture to facilitate future research in data-centric preference optimization.

Searches are conducted to find missing persons and/or objects given uncertain information, imperfect observers and large search areas in Search and Rescue (SAR). In many scenarios, such as Maritime SAR, expected survival times are short and optimal search could increase the likelihood of success. This optimization problem is complex for nontrivial problems given its probabilistic nature. Stochastic optimization methods search large problems by nondeterministically sampling the space to reduce the effective size of the problem. This has been used in SAR planning to search otherwise intractably large problems but the stochastic nature provides no formal guarantees on the quality of solutions found in finite time. This paper instead presents $\rm{A}^{\rm{SAR}}$, an $\varepsilon$-optimal search algorithm for SAR planning. It calculates a heuristic to bound the search space and uses graph-search methods to find solutions that are formally guaranteed to be within a user-specified factor, $\varepsilon$, of the optimal solution. It finds better solutions faster than existing optimization approaches in operational simulations. It is also demonstrated with a real-world field trial on Lake Ontario, Canada, where it was used to locate a drifting manikin in only 150s.

Collision detection is a core component of robotics applications such as simulation, control, and planning. Traditional algorithms like GJK+EPA compute witness points (i.e., the closest or deepest-penetration pairs between two objects) but are inherently non-differentiable, preventing gradient flow and limiting gradient-based optimization in contact-rich tasks such as grasping and manipulation. Recent work introduced efficient first-order randomized smoothing to make witness points differentiable; however, their direction-based formulation is restricted to convex objects and lacks robustness for complex geometries. In this work, we propose a robust and efficient differentiable collision detection framework that supports both convex and concave objects across diverse scales and configurations. Our method introduces distance-based first-order randomized smoothing, adaptive sampling, and equivalent gradient transport for robust and informative gradient computation. Experiments on complex meshes from DexGraspNet and Objaverse show significant improvements over existing baselines. Finally, we demonstrate a direct application of our method for dexterous grasp synthesis to refine the grasp quality. The code is available at https://github.com/JYChen18/DiffCollision.

In the era of AI-driven science and engineering, we often want to design discrete objects in silico according to user-specified properties. For example, we may wish to design a protein to bind its target, arrange components within a circuit to minimize latency, or find materials with certain properties. Given a property predictive model, in silico design typically involves training a generative model over the design space (e.g., protein sequence space) to concentrate on designs with the desired properties. Distributional optimization$\unicode{x2013}$which can be formalized as an estimation of distribution algorithm or as reinforcement learning policy optimization$\unicode{x2013}$finds the generative model that maximizes an objective function in expectation. Optimizing a distribution over discrete-valued designs is in general challenging because of the combinatorial nature of the design space. However, many property predictors in scientific applications are decomposable in the sense that they can be factorized over design variables in a way that could in principle enable more effective optimization. For example, amino acids at a catalytic site of a protein may only loosely interact with amino acids of the rest of the protein to achieve maximal catalytic activity. Current distributional optimization algorithms are unable to make use of such decomposability structure. Herein, we propose and demonstrate use of a new distributional optimization algorithm, Decomposition-Aware Distributional Optimization (DADO), that can leverage any decomposability defined by a junction tree on the design variables, to make optimization more efficient. At its core, DADO employs a soft-factorized "search distribution"$\unicode{x2013}$a learned generative model$\unicode{x2013}$for efficient navigation of the search space, invoking graph message-passing to coordinate optimization across linked factors.

This paper presents a quantitative comparison between centralised and distributed multi-agent reinforcement learning (MARL) architectures for controlling a soft robotic arm modelled as a Cosserat rod in simulation. Using PyElastica and the OpenAI Gym interface, we train both a global Proximal Policy Optimisation (PPO) controller and a Multi-Agent PPO (MAPPO) under identical budgets. Both approaches are based on the arm having $n$ number of controlled sections. The study systematically varies $n$ and evaluates the performance of the arm to reach a fixed target in three scenarios: default baseline condition, recovery from external disturbance, and adaptation to actuator failure. Quantitative metrics used for the evaluation are mean action magnitude, mean final distance, mean episode length, and success rate. The results show that there are no significant benefits of the distributed policy when the number of controlled sections $n\le4$. In very simple systems, when $n\le2$, the centralised policy outperforms the distributed one. When $n$ increases to $4< n\le 12$, the distributed policy shows a high sample efficiency. In these systems, distributed policy promotes a stronger success rate, resilience, and robustness under local observability and yields faster convergence given the same sample size. However, centralised policies achieve much higher time efficiency during training as it takes much less time to train the same size of samples. These findings highlight the trade-offs between centralised and distributed policy in reinforcement learning-based control for soft robotic systems and provide actionable design guidance for future sim-to-real transfer in soft rod-like manipulators.

Tensor decomposition of high-dimensional data often struggles to capture semantically or physically meaningful structures, particularly when relying on reconstruction objectives and fixed-rank constraints. We introduce a no-rank tensor decomposition framework based on metric learning, which replaces reconstruction objectives with a similarity-driven optimization. By combining a triplet loss with diversity and uniformity regularization, the method learns embeddings where distances naturally reflect semantic and physical relationships, supported by theoretical guarantees on convergence and metric properties. We evaluate the approach on diverse datasets, including face recognition (LFW, Olivetti), brain connectivity (ABIDE), and simulated physical systems (galaxies, crystals). In comprehensive comparisons against classical methods (PCA, t-SNE, UMAP), tensor decompositions (CP, Tucker, t-SVD), and deep learning models (VAE, DEC, transformer based embeddings), our method produces embeddings that preserve physically and semantically relevant relationships and achieve competitive clustering performance. While transformers often excel in predictive accuracy on large datasets, our method provides interpretable embeddings and remains effective in small-data regimes where transformer training may be infeasible. This work establishes metric learning as a principled paradigm for tensor analysis, emphasizing physical interpretability and semantic relevance over pixel-level reconstruction, and offering an efficient and robust alternative in data-scarce scientific domains.