arXiv:2511.14900v2 Announce Type: replace Abstract: Vision--language models (VLMs) have recently shown promise for assisting clinical reasoning in dermatological diagnosis. However, their trustworthiness and clinical utility remain limited by three key challenges: heterogeneous datasets with inconsistent diagnostic labels and concept annotations, the lack of grounded diagnostic rationales for reliable reasoning supervision, and limited scalability when transferring knowledge from small, densely annotated datasets to large collections with sparse labels. To address these challenges, we propose Skin-R1, a dermatology-oriented VLM that integrates textbook-grounded clinical reasoning supervision with reinforcement learning (RL) to improve the accuracy and robustness of diagnostic prediction. First, we construct a textbook-based reasoning generator that synthesizes hierarchy-aware and differential-diagnosis (DDx) diagnostic trajectories derived from authoritative dermatology knowledge. Second, these trajectories are used for supervised fine-tuning (SFT), establishing a clinically grounded reasoning foundation for the model. Finally, we introduce an RL training framework that incorporates the hierarchical structure of dermatological diseases into the reward design, enabling the model to generalize grounded diagnostic reasoning to large-scale datasets with sparse annotations. Extensive experiments across multiple dermatology benchmarks demonstrate that Skin-R1 consistently improves diagnostic accuracy and robustness compared to state-of-the-art Med-VLM baselines. Ablation studies further highlight the critical role of grounded reasoning supervision introduced during the SFT stage.
Science Journals
arXiv:2507.00067v5 Announce Type: replace Abstract: Many modern areas have not learned their lessons and often hope for the wisdom of later generations, resulting in them only possessing modern technology and difficult to iterate ancient civilizations. At present, there is no way to tell how we should learn from Many modern areas have not learned their lessons and often hope for the wisdom of later generations, resulting in them only possessing modern technology and difficult to iterate ancient civilizations. At present, there is no way to tell how we should learn from history and promote the gradual upgrading of civilization. Therefore, we must tell the history of civilization's progress and the means of governance, learn from experience to improve the comprehensive strength and survival ability of civilization, and achieve an optimal solution for the tempering brought by conflicts and the reduction of internal conflicts. Firstly, we must follow the footsteps of history and explore the reasons for the long-term stability of each country in conflict, including providing economic benefits to the people and means of suppressing them; then, use mathematical methods to demonstrate how we can achieve the optimal solution at the current stage. After analysis, we can conclude that the civilization transformed from human plowing to horse plowing can easily suppress the resistance of the people and provide them with the ability to resist; The selection of rulers should consider multiple institutional aspects, such as force exams, elections, and drawing lots; Economic development follows a lognormal distribution and can be adjusted by standard deviation, the number of front-end virtual employees and all virtual employees. Using a lognormal distribution with the maximum value to divide shareholding can adjust the wealth gap.
arXiv:2507.04771v2 Announce Type: replace Abstract: Privacy protection laws, such as the GDPR, grant individuals the right to request the forgetting of their personal data not only from databases but also from machine learning (ML) models trained on them. Machine unlearning has emerged as a practical means to facilitate model forgetting of data instances seen during training. Although some existing machine unlearning methods guarantee exact forgetting, they are typically costly in computational terms. On the other hand, more affordable methods do not offer forgetting guarantees and are applicable only to specific ML models. In this paper, we present \emph{efficient unlearning with privacy guarantees} (EUPG), a novel machine unlearning framework that offers formal privacy guarantees to individuals whose data are being unlearned. EUPG involves pre-training ML models on data protected using privacy models, and it enables {\em efficient unlearning with the privacy guarantees offered by the privacy models in use}. Through empirical evaluation on four heterogeneous data sets protected with $k$-anonymity and $\epsilon$-differential privacy as privacy models, our approach demonstrates utility and forgetting effectiveness comparable to those of exact unlearning methods, while significantly reducing computational and storage costs. Our code is available at https://github.com/najeebjebreel/EUPG.
arXiv:2511.15503v3 Announce Type: replace Abstract: High-performance Host processors can integrate Processing-In-Memory (PIM) devices, which can accelerate memory-intensive kernels of Machine Learning (ML) models, including Large Language Models (LLMs), by leveraging the large memory bandwidth available at PIM cores. However, Host processor needs consecutive elements distributed across DRAM banks, while PIM cores need consecutive elements within their local banks. This necessitates data rearrangements in ML kernel execution that pose significant performance and programmability challenges, further exacerbated by the need to support diverse PIM devices. Current compilation approaches lack systematic optimization for diverse ML kernels and multiple PIM devices, and may largely ignore data rearrangement costs during the compute code optimization step. We show that data rearrangements and compute code optimization are interdependent, and need to be jointly optimized during the tuning process. Therefore, we design DCC, the first data-centric ML compiler for PIM systems that jointly co-optimizes data rearrangements and compute code in a unified tuning process. DCC integrates a multi-layer PIM abstraction to support multiple PIM backends. DCC enables effective co-optimization of data partitioning strategies with compute loop partitioning schemes. DCC applies PIM-specific code optimizations, and leverages a fast and accurate performance prediction model to select the bestperforming code schedule for a given kernel on a target PIM architecture. Our evaluations in various individual ML kernels show that DCC achieves up to 7.68x speedup (2.21x average) on HBM-PIM, and up to 13.17x speedup (3.92x average) on AttAcc PIM, over GPU-only execution. In end-to-end LLM inference, DCC on AttAcc accelerates GPT-3 and LLaMA-2 by 4.52x average (up to 7.71x in LLaMA-2) over GPU. DCC is open-sourced at https://github.com/SPIN-Research-Group/DCC.
arXiv:2506.05121v3 Announce Type: replace Abstract: A recent line of research on spoken language assessment (SLA) employs neural models such as BERT and wav2vec 2.0 (W2V) to evaluate speaking proficiency across linguistic and acoustic modalities. Although both models effectively capture features relevant to oral competence, each exhibits modality-specific limitations. BERT-based methods rely on ASR transcripts, which often fail to capture prosodic and phonetic cues for SLA. In contrast, W2V-based methods excel at modeling acoustic features but lack semantic interpretability. To overcome these limitations, we propose a system that integrates W2V with Phi-4 multimodal large language model (MLLM) through a score fusion strategy. The proposed system achieves a root mean square error (RMSE) of 0.375 on the official test set of the Speak & Improve Challenge 2025, securing second place in the competition. For comparison, the RMSEs of the top-ranked, third-ranked, and official baseline systems are 0.364, 0.384, and 0.444, respectively.
arXiv:2507.07467v3 Announce Type: replace Abstract: Autonomous flight in GPS-denied indoor spaces requires trajectories that keep visual-localization error tightly bounded across varied missions. Map-based visual localization methods such as feature matching require computationally intensive map reconstruction and have feature-storage scalability issues, especially for large environments. Scene coordinate regression (SCR) provides an efficient learning-based alternative that directly predicts3D coordinates for every pixel, enabling absolute pose estimation with significant potential for onboard roboticsapplications. We present a perception-aware trajectory planner that couples an evidential learning-based SCR poseestimator with a receding-horizon trajectory optimizer. The optimizer steers the onboard camera toward reliablescene coordinates with low uncertainty, while a fixed-lag smoother fuses the low-rate SCR pose estimates with high-rate IMU data to provide a high-quality, high-rate pose estimate. In simulation, our planner reduces translationand rotation RMSE by at least 4.9% and 30.8% relative to baselines, respectively. Hardware-in-the-loop experiments validate the feasibility of our proposed trajectory planner under close-to-real deployment conditions.
arXiv:2511.15517v2 Announce Type: replace Abstract: Modern high-throughput BFT consensus protocols use streamlined push-pull mechanisms to disseminate blocks and keep happy-path performance optimal. Yet state-of-the-art designs lack a principled and efficient way to exchange blocks, which leaves them open to targeted attacks and performance collapse under network asynchrony. This work introduces the concept of a block synchronizer, a simple abstraction that drives incremental block retrieval and enforces resource-aware exchange. Its interface and role fit cleanly inside a modern BFT consensus stack. We also uncover a new attack, where an adversary steers honest validators into redundant, uncoordinated pulls that exhaust bandwidth and stall progress. Beluga is a modular and scarcity-aware instantiation of the block synchronizer. It achieves optimal common-case latency while bounding the cost of recovery under faults and adversarial behavior. We integrate Beluga into Mysticeti, the consensus core of the Sui blockchain, and show on a geo-distributed AWS deployment that Beluga sustains optimal performance in the optimistic path and, under attack, delivers up to 3x higher throughput and 25x lower latency than prior designs. The Sui blockchain adopted Beluga in production.
arXiv:2506.07069v2 Announce Type: replace Abstract: 3D Gaussian Splatting (3DGS) has emerged as a powerful technique for novel view synthesis, combining high-quality reconstruction with efficient rendering. It has been widely adopted in domains such as AR/VR, robotics, and autonomous driving. However, achieving real-time performance on resource-constrained platforms remains challenging due to strict power and area budgets. Prior accelerators improve hardware performance but still overlook key inefficiencies, including insufficient rasterization efficiency, poor sorting scalability, and pipeline imbalance. This paper presents an architecture-algorithm co-design to address these challenges. First, we propose axis-shared rasterization, which precomputes and reuses common terms along the X- and Y-axes, reducing multiply-and-accumulate (MAC) operations by up to 38% while preserving high parallelism. Second, we develop a novel order-independent transmittance method that removes the need for explicit sorting by leveraging a lightweight multilayer perceptron (MLP) to directly approximate the transmittance of each Gaussian, enabling efficient alpha blending with negligible quality loss. Third, we design a unified reconfigurable PE array that supports both rasterization and MLP inference, sustaining high utilization without costly sorting hardware. Our experiments demonstrate that our design preserves rendering quality while achieving a 1.33 to 1.88x speedup over state-of-the-art 3DGS accelerators. Our code is open source at https://github.com/WangZhican/ISCA26_3DGS_Acc.
arXiv:2506.08585v4 Announce Type: replace Abstract: We introduce, for every surface $\Sigma$, a two-way connection between definability of a graph class $\mathcal C$ by FO transductions (first-order logical transformations) of the graphs embeddable in $\Sigma$ and a certain variant of fan-crossing drawings of the graphs from $\mathcal C$ in $\Sigma$. If the considered class $\mathcal C$ is additionally of bounded maximum degree, then the restriction on drawings of the graphs from $\mathcal C$ in $\Sigma$ is simply to have a bounded number of crossings per edge (such as being $k$-planar for fixed~$k$ if $\Sigma$ is the plane). For graph classes, this connection allows us to derive non-transducibility results from the nonexistence of the said drawings and, conversely, from the nonexistence of a transduction to derive nonexistence of the said drawings. One example of such reasoning is as follows; since the class of 3D-grids is not transducible from the class of planar graphs, we derive the class of 3D-grids is not $k$-planar for any fixed~$k$. On the other hand, the fact that the class of 3D-grids is not $k$-planar for any fixed~$k$ is known also via other means, and this conversely implies that the class of 3D-grids is not transducible from the class of planar graphs. We hope that this connection will help to draw a path to a possible proof that not all toroidal graphs are transducible from planar graphs. The result is based on a recent characterization of weakly sparse FO transductions of classes of bounded expansion by [Gajarsk\'y, G{\l}adkowski, Jedelsk\'y, Pilipczuk and Toru\'nczyk, arXiv:2505.15655].
arXiv:2506.08774v2 Announce Type: replace Abstract: Different machine learning models can represent the same underlying concept in different ways. This variability is particularly valuable for in-the-wild multimodal retrieval, where the objective is to identify the corresponding representation in one modality given another modality as input. This challenge can be effectively framed as a representation alignment problem. For example, given a sentence encoded by a language model, retrieve the most semantically aligned image based on representations produced by an image encoder, or vice versa. To gain insights into the performance impact of different metrics, embedding spaces, and representation alignment for retrieval tasks, we first empirically investigate the geometric relationships between visual and textual embeddings derived from both vision-language models and combined unimodal models. We then align these representations using four standard similarity metrics as well as two learned ones, implemented via neural networks of different architectures with varying losses across multiple benchmarks. Our experimental findings indicate that cosine similarity consistently outperforms all the investigated metrics in representation alignment tasks, and that Wasserstein distance provides a complementary perspective on cross-modal distributional differences. We also observe that our proposed custom contrastive loss is advantageous over the MSE loss for aligning image and text representations, for both multilayer perceptrons and transformer-based models. Taken together, our findings offer novel insights and practical considerations for researchers working in multimodal information retrieval, particularly in real-world, cross-modal applications. Our code is publicly available.
arXiv:2506.08795v2 Announce Type: replace Abstract: Limb loss affects millions globally, impairing physical function and reducing quality of life. Most traditional surface electromyographic (sEMG) and semi-autonomous methods require users to generate myoelectric signals for each control, imposing physically and mentally taxing demands. This study aims to develop a fully autonomous control system that enables a prosthetic hand to automatically grasp and release objects of various shapes using only a camera attached to the wrist. By placing the hand near an object, the system will automatically execute grasping actions with a proper grip force in response to the hand's movements and the environment. To release the object being grasped, just naturally place the object close to the table and the system will automatically open the hand. Such a system would provide individuals with limb loss with a very easy-to-use prosthetic control interface and may help reduce mental effort while using. To achieve this goal, we developed a teleoperation system to collect human demonstration data for training the prosthetic hand control model using imitation learning, which mimics the prosthetic hand actions from human. By training the model on data from a limited set of objects collected from a single participant's demonstration, we showed that the imitation learning algorithm can achieve high success rates and generalize effectively to new users and previously unseen objects with varying weights. The demonstrations are available at https://sites.google.com/view/autonomous-prosthetic-hand.
arXiv:2508.02178v3 Announce Type: replace Abstract: Large reasoning models (LRMs) often exhibit overthinking, producing verbose Chain-of-Thought (CoT) traces that increase inference cost and obscure the underlying reasoning process. Existing CoT compression methods mainly rely on global length rewards, which conflate necessary intermediate reasoning with redundant text and may therefore compromise reasoning fidelity. This paper revisits overthinking from a semantic-efficiency perspective and decomposes CoT redundancy into two distinct forms: internal redundancy, defined as informational stagnation before the first correct answer, and external redundancy, defined as superfluous continuation after the first correct answer. Based on this decomposition, we propose a dual-penalty reinforcement learning framework that separately optimizes reasoning progress and termination behavior. Specifically, a sliding-window semantic similarity metric penalizes low-progress reasoning segments, while a normalized external-redundancy metric discourages post-answer continuation. Experiments on GSM8K, MATH500, and AIME24 across different model scales show that our method reduces average reasoning length by 41.3% on the 1.5B model and 40.1% on the 7B model, while preserving competitive accuracy and achieving the best overall accuracy-efficiency score among evaluated baselines. The learned compression behavior further transfers to out-of-domain reasoning tasks, including GPQA and LiveCodeBench. More importantly, our analysis reveals a clear asymmetry between the two redundancy types: external redundancy can be largely removed with little performance loss, whereas internal redundancy compression follows a sensitive accuracy-efficiency trade-off. These results suggest that effective CoT compression should optimize semantic efficiency rather than sequence length alone, offering a principled route toward more concise, efficient, and interpretable LRMs.
arXiv:2508.07683v2 Announce Type: replace Abstract: Video Temporal Grounding (VTG) aims to localize specific video segments corresponding to natural language queries. While recent Large Vision-Language Models (LVLMs) employ Reinforcement Learning to generate Chains-of-Thought (CoT), they typically rely solely on outcome-based supervision. Consequently, this often leads to hallucinations, where the reasoning process becomes disconnected from the visual content and the final prediction. Existing attempts to mitigate this by relying on external supervision from larger models or separate reward models are computationally expensive and prone to rigid patterns. To address these challenges, we propose TAR (Temporal Anchor-Constrained Reasoning), a framework that introduces the temporal anchor (T-anchor) as a transparent and auditable checkpoint mechanism. T-anchor enforces progressive refinement within the CoT, compelling the model to continuously ground its intermediate thoughts in visual evidence and iteratively calibrate temporal predictions, thereby significantly enhancing the faithfulness and autonomy of the reasoning process and final accuracy. Furthermore, we introduce a bootstrapping paradigm that automatically harvests high-quality CoT data using only a standard 7B model, eliminating the dependency on ultra-large models. Extensive experiments demonstrate that TAR achieves state-of-the-art performance and generates faithful, autonomous, and progressively refined reasoning traces.
arXiv:2506.18295v2 Announce Type: replace Abstract: Neural ray tracing (RT) has emerged as a promising paradigm for channel modeling by integrating physical propagation principles with neural networks. However, existing neural RT methods remain limited by strong spatial dependence and weak adherence to electromagnetic laws. We propose GeNeRT, a generalizable neural RT framework that improves generalization and accuracy through relative geometric features, scatterer semantics, and a Fresnel-inspired polarization-driven architecture. GeNeRT is trained through a three-stage strategy: polarization-specific module-wise pre-training captures general ray-surface interaction behavior; system-wise end-to-end training uses only receiver-side channel impulse responses to learn site-specific propagation characteristics; and measurement-based fine-tuning employs sparse measured multipath components (MPCs) to adapt polarization-related modules to real-world environments. Extensive outdoor simulations demonstrate robust intra-scenario transferability and inter-scenario zero-shot generalization. In an unseen scenario, GeNeRT achieves an overall error of $-35.36$ dB and an average-delay error of 4.91 ns, compared with $-10.85$ dB and 32.38 ns for the best baseline. With only 75 measured reflected MPCs, fine-tuning further reduces the overall error from $-14.48$ to $-22.90$ dB and the average-delay error from 6.28 to 3.58 ns. Ablation studies confirm the effectiveness of the proposed architecture and training strategy.
arXiv:2507.02097v3 Announce Type: replace Abstract: Large language models (LLMs) are evolving from passive text generators into agentic systems that can plan, maintain state, invoke tools, and coordinate with other agents. This perspective paper examines what this shift means for recommender systems (RS). We define agentic recommender systems as pipelines in which one or more stateful agents observe, plan, call tools, and verify, rather than score in a single shot, while operating over users, item catalogs, candidate sets, and recommendation objectives. Their value is strongest when this machinery measurably improves recommendation-layer outcomes such as relevance, constraint satisfaction, bundle coherence, grounding, explanation faithfulness, or user effort, rather than merely because a pipeline contains an LLM or several modules. We introduce a recommender-specific formalism that models an agent by its state (user, context, history, candidate set), a reasoning core, tools, a hierarchical memory, and explicit policy constraints, and casts a multi-agent recommender as a triple of agents, a shared environment, and a communication protocol. Within this framework we develop four representative task families and an agenda tying five recurring challenge families to measurable RS signals. Finally, we run a controlled study comparing single-shot and multi-agent pipelines under shared histories, candidate sets, prompts, and metrics. A pilot next-item ranking study on Amazon-2023 shows multi-agent systems are not uniformly superior: on representative samples the single-shot baseline is Pareto-efficient, whereas decomposition and ensemble agents help mainly on high-diversity histories. This supports a conditional design principle: agentic complexity should be routed to cases where its marginal quality gain justifies the added latency, cost, and governance risk. Code: https://github.com/RezaYM/agenticrecsys.git
arXiv:2508.11423v2 Announce Type: replace Abstract: Living systems exhibit a range of fundamental characteristics: they are active, self-referential, self-modifying systems. This paper explores how these characteristics create challenges for conventional scientific approaches and why they require new theoretical and formal frameworks. We introduce a distinction between 'natural time', the continuing present of physical processes, and 'representational time', with its framework of past, present and future that emerges with life itself. Representational time enables memory, learning and prediction, functions of living systems essential for their survival. Through examples from evolution, embryogenesis and metamorphosis we show how living systems navigate the apparent contradictions arising from self-reference as natural time unwinds self-referential loops into developmental spirals. Conventional mathematical and computational formalisms struggle to model self-referential and self-modifying systems without running into paradox. We identify promising new directions for modelling self-referential systems, including domain theory, co-algebra, genetic programming, and self-modifying algorithms. There are broad implications for biology, cognitive science and social sciences, because self-reference and self-modification are not problems to be avoided but core features of living systems that must be modelled to understand life's open-ended creativity.
arXiv:2511.18267v3 Announce Type: replace Abstract: Residential buildings are increasingly integrating large devices that run natively on direct current (DC), such as solar photovoltaics, electric vehicles, stationary batteries, and DC motors that drive heat pumps and other major appliances. Today, these natively-DC devices typically connect within buildings through alternating current (AC) distribution systems, entailing significant energy losses due to conversions between AC and DC. This paper investigates the alternative of connecting DC devices through DC distribution. Specifically, this paper shows through laboratory and field experiments that an off-the-shelf residential heat pump designed for conventional AC systems can be powered directly on DC with few hardware modifications and little change in performance. Supporting simulations of a DC nanogrid including {historical heat pump and rest-of-house load measurements,} a solar photovoltaic array, and a stationary battery suggest that connecting these devices through DC distribution could decrease annual electricity bills by 12.5% with an after-market AC-to-DC heat pump retrofit and by 16.7% with a heat pump designed to run on DC. The associated savings in gross nanogrid energy are 8% and 9.2%, respectively.
arXiv:2511.20771v3 Announce Type: replace Abstract: Phylogenetic networks allow modeling reticulate evolution, capturing events such as hybridization and horizontal gene transfer. A fundamental computational problem in this context is the Tree Containment problem, which asks whether a given phylogenetic network is compatible with a given phylogenetic tree. However, the classical statement of the problem is not robust to poorly supported branches in biological data, possibly leading to false negatives. In an effort to address this, a relaxed version that accounts for uncertainty, called Soft Tree Containment, has been introduced by Bentert, Mal\'ik, and Weller [SWAT'18]. We present an algorithm that solves Soft Tree Containment in $2^{O(\Delta_T \cdot k \cdot \log(k))} \cdot n^{O(1)}$ time, where $k = \operatorname{sw}(\Gamma) + \Delta_N$, with $\Delta_T$ and $\Delta_N$ denoting the maximum out-degrees in the tree and the network, respectively, and $\operatorname{sw}(\Gamma)$ denoting the "scanwidth" [Berry, Scornavacca, and Weller, SOFSEM'20] of a given tree extension of the network, while $n$ is the input size. Our approach leverages the fact that phylogenetic networks encountered in practice often exhibit low scanwidth, making the problem more tractable.
arXiv:2511.21256v2 Announce Type: replace Abstract: Generative world models for autonomous driving (AD) are of great value in applications such as data augmentation, closed-loop simulation, and safety-critical scenario evaluation. Unlike the widely studied image modality, in this work we explore generative world models for LiDAR data. Existing generation methods for LiDAR predominantly focus on single frame generation or lack the capacity for interactive simulation, while existing prediction approaches require multiple frames of historical input and can only deterministically predict multiple frames at once. Both paradigms fail to support long-horizon interactive generation. To this end, we introduce \textbf{LaGen}, which, to the best of our knowledge is the first autoregressive framework capable of generating long-horizon LiDAR scenes in a frame-by-frame, interactive manner. LaGen is able to take a single-frame input as a starting point and effectively utilize bounding box information as conditions to generate high-fidelity 4D scene. In addition, we introduce a scene decoupling estimation module to enhance the model's interactive generation capability for object-level content, as well as a noise modulation module to mitigate error accumulation during long-horizon generation. We extensively evaluate LaGen's performance in controlled data generation and long-horizon scene generation on the nuScenes dataset. The experimental results demonstrate that LaGen achieves state-of-the-art performance, especially on later frames. The code is publicly available at: https://github.com/szzhou88/LaGen.
arXiv:2508.09883v2 Announce Type: replace Abstract: Large language models (LLMs) demonstrate remarkable reasoning capabilities in tasks such as algorithmic coding and mathematical problem-solving. Recent methods have improved reasoning through expanded corpus and multistage training combining reinforcement learning and supervised fine-tuning. Although some methods suggest that small but targeted dataset can incentivize reasoning via only distillation, a reasoning scaling laws is still taking shape, increasing computational costs. To address this, we propose a data-efficient distillation framework (DED) that optimizes the Pareto frontier of reasoning distillation. Inspired by the on-policy learning and diverse roll-out strategies of reinforcement learning, the key idea of our approach is threefold: (1) We identify that benchmark scores alone do not determine an effective teacher model. Through comprehensive comparisons of leading reasoning LLMs, we develop a method to select an optimal teacher model. (2) While scaling distillation can enhance reasoning, it often degrades out-of-domain performance. A carefully curated, smaller corpus achieves a balanced trade-off between in-domain and out-of-domain capabilities. (3) Diverse reasoning trajectories encourage the student model to develop robust reasoning skills. We validate our method through evaluations on mathematical reasoning (AIME 2024/2025, MATH-500) and code generation (LiveCodeBench), achieving state-of-the-art results with only 0.8k carefully curated examples, bypassing the need for extensive scaling. Our systematic analysis demonstrates that DED outperforms existing methods by considering factors beyond superficial hardness, token length, or teacher model capability. This work offers a practical and efficient pathway to advanced reasoning while preserving general capabilities.
arXiv:2509.02292v2 Announce Type: replace Abstract: What if large language models could not only infer human mindsets but also expose every blind spot in team dialogue such as discrepancies in the team members' joint understanding? We present a novel, two-step framework that leverages large language models (LLMs) both as human-style annotators of team dialogues to track the team's shared mental models (SMMs) and as automated discrepancy detectors among individuals' mental states. In the first step, an LLM generates annotations by identifying SMM elements within task-oriented dialogues from the Cooperative Remote Search Task (CReST) corpus. Then, a secondary LLM compares these LLM-derived annotations and human annotations against gold-standard labels to detect and characterize divergences. We define an SMM coherence evaluation framework for this use case and apply it to six CReST dialogues, ultimately producing: (1) a dataset of human and LLM annotations; (2) a reproducible evaluation framework for SMM coherence; and (3) an empirical assessment of LLM-based discrepancy detection. Our results reveal that, although LLMs exhibit apparent coherence on straightforward natural-language annotation tasks, they systematically err in scenarios requiring spatial reasoning or disambiguation of prosodic cues.
arXiv:2509.03664v2 Announce Type: replace Abstract: We reproduce the consistently-seen experimental voltage versus pressure (V-p) dependence of DC magnetron sputtering (DCMS) with 2D-RZ particle-in-cell (PIC) simulation. Informed by PIC simulation, we develop a steady-state, 1D-axial fluid model of the sheath and presheath that also reproduces this V-p dependence. The V-p dependence is the relationship between the steady-state voltage needed to maintain a constant discharge current and the neutral gas pressure. V-p dependence is fundamental to device performance, but has not previously been reproduced with simulation or satisfactorily explained. We find that the decrease in voltage with increasing pressure is not due to electron recapture at the cathode. Rather, the constant current dictates a constant global ionization rate, so the voltage decrease compensates for the increase in neutral gas density by lowering the energy of the plasma electrons, which decreases their ionization probability. The PIC simulations also reveal that the presheath and bulk plasma are unaffected by the electron reflection coefficient at the cathode; the only effect of increasing reflection is a reduction in the sheath voltage and width. In addition to the potential structure, we explore how pressure affects the plasma density, particle drifts, and particle energy distributions.
arXiv:2606.29093v1 Announce Type: new Abstract: A deep defogging pipeline pretrained on controlled laboratory fog and fine-tuned with domain-randomized synthetic fog applied to clear outdoor scenes generalizes across a graded sequence of out-of-distribution settings with no target-domain training, from chamber-free free-flowing fog to iPhone video recorded through an aircraft cabin window in flight, an entirely unseen sensor, scene, and optical path. This directly addresses an open transfer limitation reported for real-world binocular defogging. Two design choices support the transfer. First, a single-camera fog imager photographs a flat-panel display through an artificial-fog enclosure with a fixed 114~mm scattering path, producing 5{,}495 pixel-aligned foggy/clear pairs. Exact registration permits a paired Laplacian ratio that predicts per-image restoration quality far better than single-image proxies (Spearman $\rho = 0.632$ versus $0.399$) and supports pixel-exact $L_1$ reconstruction training that avoids adversarial hallucination. Second, the fog-chamber checkpoint is fine-tuned on Mapillary Vistas crops overlaid with on-the-fly randomized synthetic fog spanning a broad range of strengths, spatial variations, airlights, and noise conditions. On a 552-image held-out split, a uniform comparison of 30 restoration backbones places NAFNet at the top (24.33~dB~/~0.7912~SSIM), with a compact alternative within 1.29~dB at 3\% of the parameter count, and a ResNet-50 classifier confirms that the restoration preserves semantic content rather than only pixel-level structure. On unpaired aircraft-window video, NIQE decreases from a mean of 6.22 to 4.97 after fine-tuning, with temporally stable output across full-motion sequences. The same backbone, under paired supervision, also reaches 20.71~dB~/~0.683~SSIM on a non-overlapping O-HAZE/NH-HAZE split (a transferability check rather than a competitive ranking).
arXiv:2507.07445v3 Announce Type: replace Abstract: Autonomous agents navigating human society must master both production activities and social interactions, yet existing benchmarks rarely evaluate these skills simultaneously. To bridge this gap, we introduce StarDojo, a novel benchmark based on Stardew Valley, designed to assess AI agents in open-ended production-living simulations. In StarDojo, agents are tasked to perform essential livelihood activities such as farming and crafting, while simultaneously engaging in social interactions to establish relationships within a vibrant community. StarDojo features 1,000 meticulously curated tasks across five key domains: farming, crafting, exploration, combat, and social interactions. Additionally, we provide a compact subset of 100 representative tasks for efficient model evaluation. The benchmark offers a unified, user-friendly interface that eliminates the need for keyboard and mouse control, supports all major operating systems, and enables the parallel execution of multiple environment instances, making it particularly well-suited for evaluating the most capable foundation agents, powered by multimodal large language models (MLLMs). Extensive evaluations of state-of-the-art MLLMs agents demonstrate substantial limitations, with the best-performing model, GPT-4.1, achieving only a 12.7% success rate, primarily due to challenges in visual understanding, multimodal reasoning and low-level manipulation. As a user-friendly environment and benchmark, StarDojo aims to facilitate further research towards robust, open-ended agents in complex production-living environments.
arXiv:2509.07201v2 Announce Type: replace Abstract: This paper proposes a linear input-output observer design methodology for a population of systems in which each observer uses knowledge of the linear time-invariant dynamics of the particular device. Observers are typically composed of a known model of the system and a correction mechanism to produce an estimate of the state. The proposed design procedure characterizes the variation within the population in the frequency domain and synthesizes a single robust correction filter. The correction filter is compatible with all system models that satisfy the variation characterization such that a given level of estimation performance is guaranteed. This is accomplished by posing a robust performance problem using the observer error dynamics and solving it using $DK$-iteration. The design procedure is experimentally demonstrated on a flexible joint robotic manipulator with varied joint stiffnesses. It is shown that the proposed method that uses a single correction filter achieves comparable estimation performance to a method that uses a correction gain tailored toward each joint stiffness configuration.