arXiv:2509.01231v4 Announce Type: replace
Abstract: Care is primarily a collective phenomenon, with a practice that involves sharing health and wellbeing information within a trusted "care circle" of family members and companions for sensemaking, interpretation, decision-making, and follow-through. However, current digital health tools and information systems are designed for individuals and primarily intended for Personal Health Informatics (PHI). This mismatch between collective practice and individualistic design creates new challenges for the proactive use of such systems in care settings and limits adoption, sustained engagement, and meaningful use. To examine how people practice collective care and how (if) they perceive, adopt, and integrate PHI systems for proactive care, we conducted a sequential mixed-methods study. Through an initial survey (n=87) and semi-structured interviews (n=22), we found that their practices involve collectively understanding, analyzing, and sensemaking health information. However, we also found that their use of existing systems to support such practices is constrained by factors at personal, relational, technological, and structural levels that evolve over time. To explore redesigning PHI toward "Collective Health Informatics", we conducted stakeholder-specific interviews (n=12), a follow-up survey (n=116), and co-design workshops (n=6) to understand the dynamics required for collective settings while retaining agency. Using a design probe evaluation (n=38), we refine a design vision for coordinated, trustworthy action across such care relationships. Our findings motivate CC-Proact, an operational map that translates ecological influences into three design levers: Agency, Elicitation, and Engagement. Using this map, our work empirically examines collective care practices and offers ten design recommendations for building responsible systems that proactively support collective care.
Science Journals
arXiv:2509.14839v3 Announce Type: replace
Abstract: City administrations increasingly rely on comprehensive databases and digital twins of city assets, such as traffic signs and trees, as well as incidents such as graffiti or road damage, to maintain an effective overview of urban conditions. Digitization has increased the demand for continuously updated spatial datasets, yet current data acquisition and maintenance processes still involve considerable manual effort, posing significant scalability challenges. This paper introduces MapAnything, a systematic evaluation pipeline that automates the spatial mapping of urban objects and incidents from a single monocular image. By leveraging advanced Metric Depth Estimation models, MapAnything accurately calculates object geocoordinates, converting 2D image data into valuable 3D spatial information. The methodology integrates the estimated camera-to-object distance with geometric principles and known camera specifications. We present a detailed validation of the framework, comparing its distance-estimation accuracy against high-precision LiDAR point clouds in complex urban environments. Our evaluation provides a granular analysis of spatial performance across various distance intervals and semantic areas, such as roads and vegetation. Finally, we demonstrate the framework's practical efficacy through specific use cases, including mapping traffic signs and road pavement damage, and provide recommendations for its integration into automated urban inventory systems.
arXiv:2509.19244v3 Announce Type: replace
Abstract: We propose Lavida-O, a unified Masked Diffusion Model (MDM) for multimodal understanding and generation. Unlike existing multimodal MDMs such as MMaDa and Muddit which only support simple image-level understanding tasks and low-resolution image generation, Lavida-O presents a single framework that enables image-level understanding, object grounding, image editing, and high-resolution (1024px) text-to-image synthesis. Lavida-O incorporates a novel Elastic Mixture-of-Transformers (Elastic-MoT) architecture that couples a lightweight generation branch with a larger understanding branch, supported by token compression, universal text conditioning and stratified sampling for efficient and high-quality generation. Lavida-O further incorporates planning and iterative self-reflection in image generation and editing tasks, seamlessly boosting generation quality with its understanding capabilities. Lavida-O achieves state-of-the-art performance on a wide range of benchmarks including RefCOCO object grounding, GenEval text-to-image generation, and ImgEdit image editing, outperforming existing autoregressive models and continuous diffusion models such as Qwen2.5-VL and FluxKontext-dev, while offering considerable speedup at inference. These advances establish Lavida-O as a new paradigm for scalable multimodal reasoning and generation.
Micro-macro kinetic flux-vector splitting schemes for the multidimensional Boltzmann-ES-BGK equation
arXiv:2509.21832v2 Announce Type: replace
Abstract: The kinetic Boltzmann equation models gas dynamics over a wide range of spatial and temporal scales. Simplified versions of the full Boltzmann collision operator, such as the classical Bhatnagar-Gross-Krook (BGK) and the closely related Ellipsoidal-Statistical-BGK (ES-BGK) operators, can dramatically reduce the computational cost of solving kinetic equations numerically. Classical BGK yields incorrect transport coefficients (relative to the full Boltzmann collision operator) at low Knudsen numbers, whereas ES-BGK captures them correctly. In this work, we develop a finite-volume method based on a micro-macro decomposition of the distribution function, which requires a smaller velocity mesh than direct kinetic methods for low and intermediate Knudsen numbers. The macro portion of the model is a fluid model with a moment closure derived from the heat-flux tensor calculated from the micro portion. The micro portion is obtained by applying to the original kinetic equation a projector into the orthogonal complement of the null space of the collision operator -- this projector depends on the macro portion. In particular, we extend the technique of Bennoune, Lemou, and Mieussens [{\it Uniformly stable schemes for the Boltzmann equation preserving the compressible Navier-Stokes asymptotics, J. Comput. Phys. (2008)}] to two-space dimensions, the ES-BGK collision operator, and problems with reflecting wall boundary conditions. The collision operator in the micro and macro equations is handled via L-stable implicit time discretizations, while the transport terms are computed via kinetic flux vector splitting (for the macro equations) and upwind differencing (for the micro equation). The resulting scheme is applied to various test cases in 1D and 2D. The 2D version of the code is parallelized using MPI, and we present weak- and strong-scaling studies with varying numbers of processors.
arXiv:2607.14890v1 Announce Type: new
Abstract: Autonomous coding agents increasingly execute multi-step software work, but lifecycle states such as reviewed, tested, DONE, and ready-to-merge remain claims unless supported by current evidence. We present Proof-or-Stop Lifecycle Control, a method that permits lifecycle transitions only when fresh, tracked-source-state-bound, mechanically verifiable evidence satisfies the relevant gate. The method treats agent outputs as claims rather than lifecycle state, and uses proof operationally to mean gate-admissible evidence under a stated trust model, not semantic program correctness.
We evaluate an open-source implementation through mechanism tests, a powered control-policy ablation, and operated self-application evidence. The unattended-loop engine passed 10 of 10 scenarios with zero false-DONE, and local-key receipt bundles rejected 18 tamper classes with zero false accepts. In a 9,240-cell ablation, the pre-registered A4 versus A2-prime comparison reduced visible-pass/hidden-fail amplification from 31 of 1,800 injected cells under a compute-budgeted naive loop to 2 of 1,800 under the gated loop, a 1.6 percentage-point improvement in not-amplified rate with a 95 percent confidence interval of [0.8, 2.5]. A near-compute A3 versus A4 comparison, 14 of 1,800 versus 2 of 1,800, indicates that the gain is associated with enforcing review as a lifecycle gate rather than merely adding a reviewer. The self-application corpus contains 565 stories and 1,007 review findings, with 94.8 percent resolved, plus a 68-row high/critical cross-vendor exhibit. These results support Proof-or-Stop as a model-agnostic, host-neutral control layer for deciding which autonomous-agent claims a lifecycle may act on. The evaluation is limited to one model family, 24 ablation tasks, and a self-hosted corpus.
arXiv:2509.24566v2 Announce Type: replace
Abstract: Large vision-language models (LVLMs) have achieved impressive performance across a wide range of vision-language tasks, while they remain vulnerable to backdoor attacks. Existing backdoor attacks on LVLMs aim to force the victim model to generate a predefined target pattern, which is either inserted into or replaces the original content. We find that these fixed-pattern attacks are relatively easy to detect, because the attacked LVLM tends to memorize such frequent patterns in the training dataset, thereby exhibiting overconfidence on these targets given poisoned inputs. To address these limitations, we introduce TokenSwap, a more evasive and stealthy backdoor attack that focuses on the compositional understanding capabilities of LVLMs. Instead of enforcing a fixed targeted content, TokenSwap subtly disrupts the understanding of object relationships in text. Specifically, it causes the backdoored model to generate outputs that mention the correct objects in the image but misrepresent their relationships (i.e., bags-of-words behavior). During training, TokenSwap injects a visual trigger into selected samples and simultaneously swaps the grammatical roles of key tokens in the corresponding textual answers. However, the poisoned samples exhibit only subtle differences from the original ones, making it challenging for the model to learn the backdoor behavior. To address this, TokenSwap employs an adaptive token-weighted loss that explicitly emphasizes the learning of swapped tokens, such that the visual triggers and bags-of-words behavior are associated. Extensive experiments demonstrate that TokenSwap achieves high attack success rates while maintaining superior evasiveness and stealthiness across multiple benchmarks and various LVLM architectures.
arXiv:2509.25667v3 Announce Type: replace
Abstract: This paper presents an Artificial Intelligence (AI) integrated approach to Brain-Computer Interface (BCI)-based wheelchair development, utilizing a motor imagery right-left-hand movement mechanism for control. The system is designed to simulate wheelchair navigation based on motor imagery right and left-hand movements using electroencephalogram (EEG) data. A pre-filtered dataset, obtained from an open-source EEG repository, was segmented into arrays of 19x200 to capture the onset of hand movements. The data was acquired at a sampling frequency of 200Hz. The system integrates a Tkinter-based interface for simulating wheelchair movements, offering users a functional and intuitive control system. We propose TFormerEEG, a Transformer-driven deep learning architecture, for motor imagery EEG classification. The model achieves a test accuracy of 93.04% compared with various machine learning baseline models, including XGBoost, EEGNet, and an EEG-Deformer model. The TFormerEEG achieved a mean accuracy of 91.18% through stratified cross-validation, showcasing the effectiveness of this model.
arXiv:2607.14288v1 Announce Type: new
Abstract: We study majority correctness when voting is preceded by sustained social interaction on a social network. Motivated by the Condorcet Jury Theorem, we consider a binary choice with an objectively correct alternative, where uninformed voters revise their vote intentions through repeated interaction in the presence of competing committed leaders (zealots). In this zealot--contrarian voter model, voters may either imitate or oppose the views they encounter. For fully mixed electorates, we characterize the long-run distribution of votes and the correlation structure induced among voters, and we show that Erd\H{o}s--R\'enyi networks exhibit the same majority-correctness behavior after an appropriate rescaling of leader influence. Building on these results, we establish a finite-electorate Condorcet-type guarantee: when post-deliberation individual correctness exceeds random choice, a strict majority is more likely to select the correct alternative than a randomly chosen voter. At the same time, we identify an aggregation failure: social interaction can reduce majority accuracy relative to a no-deliberation benchmark in which voters respond only to zealots. As the electorate size tends to infinity, this finite-electorate advantage disappears unless social updating is purely conformist, revealing a tipping point at full conformity: any persistent contrarian updating drives both individual and majority correctness to the random choice level of one half. Simulations on scale-free, ring, and small-world networks further show that topology matters because it shapes the vote correlations generated by social influence: hub-dominated structures generate stronger positive correlations and lower majority accuracy, whereas spatially structured networks generate weaker correlations, preserve a larger effective number of independent judgments, and improve majority accuracy.
arXiv:2510.01171v4 Announce Type: replace
Abstract: Post-training alignment often reduces LLM diversity, leading to a phenomenon known as mode collapse. Unlike prior work that attributes this effect to algorithmic limitations, we identify a fundamental, pervasive data-level driver: typicality bias in preference data, whereby annotators systematically favor familiar text as a result of well-established findings in cognitive psychology. We formalize this bias theoretically, verify it on preference datasets empirically, and show that it plays a central role in mode collapse. Motivated by this analysis, we introduce Verbalized Sampling, a simple, training-free prompting strategy to circumvent mode collapse. VS prompts the model to verbalize a probability distribution over a set of responses (e.g., "Generate 5 jokes about coffee and their corresponding probabilities"). Comprehensive experiments show that VS significantly improves performance across creative writing (poems, stories, jokes), dialogue simulation, open-ended QA, and synthetic data generation, without sacrificing factual accuracy and safety. For instance, in creative writing, VS increases diversity by 1.6-2.1x over direct prompting. We further observe an emergent trend that more capable models benefit more from VS. In sum, our work provides a new data-centric perspective on mode collapse and a practical inference-time remedy that helps unlock pre-trained generative diversity.
arXiv:2510.09416v4 Announce Type: replace
Abstract: Learning on temporal graphs has become a central topic in graph representation learning, with numerous benchmarks indicating the strong performance of state-of-the-art models. However, recent work has raised concerns about the reliability of benchmark results, noting issues with commonly used evaluation protocols and the surprising competitiveness of simple heuristics. This contrast raises the question of which characteristics of the underlying graphs temporal graph learning models actually use to form their predictions. We address this by systematically evaluating eight models on their ability to capture eight fundamental characteristics related to the link structure of temporal graphs. These include structural characteristics such as density, temporal patterns such as recency, and edge formation mechanisms such as homophily. Using both synthetic and real-world datasets, we analyze how well models learn these characteristics. Our findings reveal a mixed picture: models capture some characteristics well but fail to reproduce others. With this, we expose important limitations. Overall, we believe that our results provide practical insights for the application of temporal graph learning models and motivate more interpretability-driven evaluations in graph learning research.
arXiv:2607.14394v1 Announce Type: new
Abstract: Fourier Neural Operators (FNOs) learn solution operators for partial differential equations and offer orders of magnitude speedup over traditional numerical solvers at inference time, which makes them attractive surrogates for high-resolution computational physics. Scaling FNOs to high-resolution spatial grids requires distributing the data across GPUs, but the distributed FFT at the core of each spectral layer requires multiple dense all-to-all collectives that communicate the full spatial tensor, only for most coefficients to be discarded immediately. We introduce the Distributed Truncated Spectral Transform (DTST), which reverses this order. Each GPU computes only a small subset of frequency modes used by the spectral convolution locally via a partial DFT, and two collectives combine the results with a payload that depends only on this mode count, not the spatial resolution. DTST produces spectral coefficients identical to the standard distributed FFT with truncation, while providing both spatial data parallelism and spectral weight model parallelism. We present DRIFT, a GPU implementation of DTST for distributed Fourier Neural Operators, using separable per-dimension basis matrices and efficient GPU-to-GPU communication. On a 3D+time FNO across 4--32 GPUs, on up to 8 nodes (4 GPUs/node), DRIFT achieves a forward-pass speedup of 38--64$\times$ and a 37$\times$ training speedup over the distributed FNO baseline, reducing communication time from 97\% to under 6\% of the forward-pass time, with growing speedups at higher resolution.
arXiv:2510.14854v4 Announce Type: replace
Abstract: Magnetic induction (MI) communication (MIC) has emerged as a promising candidate for underground communication networks due to its excellent penetration capabilities. Integration with Space-Air-Ground-Underground (SAGUI) networks in next-generation mobile communication systems requires a well-defined network architecture. A recent discovery in MIC research, MI fast fading, remains in its early stages and presents unique challenges. This paper provides a comprehensive survey on through-the-earth (TTE) MIC, covering MI applications, channel modeling, point-to-point MIC design, relay techniques, network frameworks, and emerging technologies. We compare various MIC applications to highlight TTE-specific challenges and review the principles of channel modeling, addressing both MI slow fading and MI fast fading, along with its potential impact on existing MIC theories. We conduct a fine-grained decomposition of MI channel power gain into four distinct physical parameters, and propose a novel geometric model to analyze MI fast fading. We also summarize MI relay techniques, examine crosstalk effects in relay and high-density networks, and explore key research tasks within the OSI framework for a holistic MI network protocol in SAGUI. To bridge the gaps identified, we propose a MIC framework that supports TCP/IP and Linux, enabling full implementation of existing and emerging MIC solutions. This framework empowers researchers to leverage Linux resources and deep learning platforms for accelerated development of MIC in SAGUI networks. Remaining research challenges, open issues, and promising novel techniques are further identified to advance MIC research.
arXiv:2510.17815v2 Announce Type: replace
Abstract: Semiconductors and their downstream applications sustain the electronic, information, energy and industrial systems underpinning modern society. Improving their sustainability is therefore an urgent global priority, particularly as global electricity generation is projected to increase more than 2.5 fold by 2050. Yet, since the invention of the transistor in 1947, a unified, global view of circuit elements as media for charge redistribution and transfer one that reveals switching inertia and the dynamical nature of switching while connecting microscopic and macroscopic domains across the semiconductor value chain through a common theoretical language has remained absent. Switching consequently lacks a unified mechanistic account of its physical origins and spatiotemporal evolution, with fundamental disconnects between charge- and energy-conservation frameworks, among carrier dynamic mechanisms and across equivalent-circuit formalisms. These limitations fragment research domains and impede sustainability gains, particularly those requiring cross-domain causal information. Here, we present Charge-Unified Semiconductor Switching Theory (CUSST), a general theory that unifies circuit elements through a charge-mediated view, reveals switching inertia and the dynamical nature of switching, bridges these long-standing disconnects and establishes a unified conceptual, mechanistic, formal and analytical framework. Through these unifications, CUSST provides an unusually simple representation of otherwise fragmented switching phenomena. It establishes a unified micro-macro spatiotemporal view of switching, generalizes circuit theory, extends the application of conservation laws and provides a foundation for developing new theoretical systems.
arXiv:2510.21324v2 Announce Type: replace
Abstract: Chest X-ray (CXR) plays a pivotal role in clinical diagnosis, and a variety of task-specific and foundation models have been developed for automatic CXR interpretation. However, these models often struggle to adapt to new diagnostic tasks and complex reasoning scenarios. Recently, LLM-based agent models have emerged as a promising paradigm for CXR analysis, enhancing model's capability through tool coordination, multi-step reasoning, and team collaboration, etc. However, existing agents often rely on a single diagnostic pipeline and lack mechanisms for assessing tools' reliability, limiting their adaptability and credibility. To this end, we propose CXRAgent, a director-orchestrated, multi-stage agent for CXR interpretation, where a central director coordinates the following stages: (1) Tool Invocation: The agent strategically orchestrates a set of CXR-analysis tools, with outputs normalized and verified by the Evidence-driven Validator (EDV), which grounds diagnostic outputs with visual evidence to support reliable downstream diagnosis; (2) Diagnostic Planning: Guided by task requirements and intermediate findings, the agent formulates a targeted diagnostic plan. It then assembles an expert team accordingly, defining member roles and coordinating their interactions to enable adaptive and collaborative reasoning; (3) Collaborative Decision-making: The agent integrates insights from the expert team with accumulated contextual memories, synthesizing them into an evidence-backed diagnostic conclusion. Experiments on various CXR interpretation tasks show that CXRAgent delivers strong performance, providing visual evidence and generalizes well to clinical tasks of different complexity. Code and data are valuable at this \href{https://github.com/laojiahuo2003/CXRAgent/}{link}.
arXiv:2510.24891v2 Announce Type: replace
Abstract: Large language models (LLMs) have demonstrated significant potential to accelerate scientific discovery as valuable tools for analyzing data, generating hypotheses, and supporting innovative approaches in various scientific fields. In this work, we investigate how LLMs can handle the transition from conceptual research ideas to well-structured research plans. Effective research planning not only supports scientists in advancing their research but also represents a crucial capability for the development of autonomous research agents. Despite its importance, the field lacks a systematic understanding of LLMs' research planning capability. To rigorously measure this capability, we introduce the Idea2Plan task and Idea2Plan Bench, a set of benchmarks built from ICML 2025 and Nature Mental Health papers released after major LLM training cutoffs. Each benchmark instance includes a research idea and a grading rubric capturing the key components of valid plans. We further propose Idea2Plan JudgeEval, a complementary benchmark to assess the reliability of LLM-based judges against expert annotations. Experimental results show that GPT-5 achieves the strongest performance on the benchmark, though substantial headroom remains for improvement. Our study provides new insights into LLMs' capability for research planning and lays the groundwork for future progress.
arXiv:2511.01492v3 Announce Type: replace
Abstract: In uncertainty quantification for parametric partial differential equations (PDEs), it is common to model uncertain random field inputs using countably infinite sequences of independent and identically distributed random variables. The lognormal random field is a prime example of such a model. While there have been many studies assessing the error in the PDE response that occurs when an infinite-dimensional random field input is replaced with a finite-dimensional random field, there do not seem to be any analyses in the existing literature discussing the sharpness of these bounds. This work seeks to remedy the situation. Specifically, we investigate two model problems where the existing dimension truncation error rates can be shown to be sharp.
arXiv:2607.14395v1 Announce Type: new
Abstract: The Internet of Things (IoT) was introduced almost two decades ago. In the past two decades, technology has seen huge advancements. Many devices have become powerful and have less power consumption. Many IoT architectures and environments were introduced to help make life easier, especially in wearable devices. The market for these wearable devices has constantly increased over the years and is expected to reach its maximum in the next couple of years. They also pose a threat to users' privacy and security because they constantly store and transmit personal information such as location, heart rate, and other sensitive data. Therefore, addressing the security vulnerabilities is a crucial aspect of this research. This paper presents a hardware-assisted, energy-efficient, low-overhead security solution for wearable devices. Specifically, two Physical Unclonable Function (PUF) architectures: Arbiter PUF and Hybrid Oscillator Arbiter (HOA) PUF are analyzed for integration in IoT systems. The result shows that Arbiter PUF consumes 25 $\mu$W, whereas HOA PUF consumes only 2.7 $\mu$W to generate keys for cryptographic purposes. These architectures introduce minimal power overhead while providing robust security, making them well suited for resource-constrained IoT ecosystems.
arXiv:2607.14144v1 Announce Type: new
Abstract: The Platonic Representation Hypothesis (PRH) holds that as models scale, representations of heterogeneous networks converge toward a shared model of reality. We propose its sequel and boundary, the Capability Convergence Hypothesis (CCH): under a fixed per-token inference budget, representational convergence does not entail capability convergence. Capability instead converges toward a class, the access-complete hybrid: any architecture holding both a compressive O(1)-state channel and a scalable verbatim-index channel. We anchor it on a witness task, the Newton's-apple problem in an infinite stream, and name three resource walls: a Shannon wall barring any o(Nb)-state architecture, a horizon wall barring any fixed window, and a circuit wall barring fixed-depth attention-only composition (conditional on TC0 != NC1). Under an explicit separability assumption a hybrid crosses all three by paying each wall's price, so capability is strictly super-additive under composition. We separate what we prove from what we conjecture: the access-completeness principle rests on information-theoretic lower bounds and pre-registered experiments, while the field-level convergence trend is an economics-motivated conjecture. We report the first pre-registered small-scale tests under criteria frozen before the data: the predicted scissors gap is measured (exact-retrieval error 0.994 vs. 0.000 once a 64-scalar state gains one global-attention layer), the state-tracking bifurcation lands at the registered boundary, and a conjunction witness shows an irreducibly two-channel solution; one prediction failed with its direction reversed and is reported as such. Representational convergence is given freely by scale; capability convergence must be purchased by access structure.
arXiv:2607.14397v1 Announce Type: new
Abstract: This work develops a model-informed framework for predictive analysis and optimal design of hard-magnetic soft materials (hMSMs). These materials undergo contact-free, field-driven deformation, making them attractive for soft robotics, adaptive structures, and bio-inspired systems. Accurate prediction requires effective structure--property relations, while optimal design requires simultaneous control of structural density, magnetic particle distribution, and remanent magnetization direction. To address these issues, this work makes two main contributions. First, classical rigid-inclusion relations, a Hill self-consistent relation, and constrained-kinematics models are placed into a unified effective shear-modulus framework for particle-filled elastomers. With one default control relation, seven shear-modulus relations are combined with three strain-energy density functions to obtain 21 constitutive models. The results show that the strain-energy density form has a relatively small effect for the actuation problems considered, whereas the effective shear-modulus relation can significantly affect deformation when magnetic material overlaps with highly deforming regions. Experimental stress--strain data are then used to select a representative shear-modulus relation, with the Mooney relation giving the best overall agreement. Second, using the selected constitutive model, a joint material--structural optimization framework is developed for simultaneous design of structural density, magnetic particle volume fraction, and remanent magnetization direction. Rotational, translational, and restorative examples show that the framework handles different active design fields, objectives, and single- or multi-load-case formulations, producing non-intuitive hMSM designs with prescribed deformation responses. The framework is implemented in the open-source \texttt{CEADpx/top\_optim} repository.
arXiv:2607.14145v1 Announce Type: new
Abstract: Tool-augmented large language model agents excel at long-horizon tasks, yet they are typically post-trained on fixed toolsets. When tasks demand new tools, these agents struggle to incorporate them effectively, and retraining from scratch is often impractical. We identify the core obstacle in such toolset expansion problem as behavioral inertia: the tendency of agents to fall back on familiar tools and established reasoning patterns despite having access to new ones. We demonstrate that injecting counterfactual anchor contexts at critical decision points can break this inertia, recovering failed trajectories by eliciting suppressed agent capabilities. To scale this insight, we propose ToolAnchor, a framework that uses teacher models to hypothesize these counterfactual contexts, verifies them via student rollouts, and internalizes the successful interventions through agentic post-training. Extensive evaluations across general AI assistant (GAIA), textual search (BrowseComp), and visual search (VDR-Bench) tasks demonstrate that ToolAnchor consistently exhibits competitive performance under expanded toolsets. Our work bridges the gap between static post-training and dynamic adaptation, charting a new path for scalable agentic reinforcement learning.
arXiv:2511.06237v2 Announce Type: replace
Abstract: Enabling lifelong learning in LLMs demands resolving the stability-plasticity dilemma (i.e., models must incorporate new knowledge without overwriting prior representations) while maintaining scalability under bounded parameter growth. Existing PEFT methods fail to satisfy this triad; shared-parameter approaches suffer from catastrophic interference, while task-isolated expansions preclude knowledge transfer and scale linearly. We propose Mixtures of SubExperts (MoSEs), a modular and sparse framework that factorizes model capacity into reusable, compositional primitives. MoSEs augment transformer layers with lightweight SubExperts and a learned sub-routing function that dynamically selects and composes a sparse subset of modules conditioned on task inputs. This induces a structured decomposition of the parameter space where knowledge is localized yet accessible, mitigating interference while preserving reuse. Specifically, MoSEs balance the dilemma via three pillars: (i) stability by isolating knowledge within sparsely activated modules, (ii) plasticity through routing-driven recombination and selective expansion, and (iii) scalability via sublinear growth in effective capacity. Notably, the routing mechanism enables compositional generalization, allowing new tasks to be represented as combinations of previously acquired sub-functions. We empirically validate MoSEs on TRACE and SuperNI, showing reduced forgetting, improved forward transfer, and better parameter efficiency over strong PEFT baselines. MoSEs establish a new Pareto frontier, achieving state-of-the-art performance while maintaining strict parameter budgets. Our results suggest that modular sparsity and compositional routing are key inductive biases for building foundation models that continually learn without saturation.
arXiv:2511.06609v4 Announce Type: replace
Abstract: The accurate forecasting of complex, high-dimensional dynamical systems from observational data is a fundamental task across numerous scientific and engineering disciplines. A significant challenge arises from noise-corrupted measurements, which severely degrade the performance of data-driven models. In chaotic dynamical systems, where small initial errors amplify exponentially, it is particularly difficult to develop a model from noisy data that achieves short-term accuracy while preserving long-term invariant properties. To overcome this, we consider the weak formulation as a complementary approach to the classical $L2$-loss function for training models of dynamical systems. We empirically verify that the weak formulation, with a proper choice of test function and integration domain, effectively filters noisy data. This insight explains why a weak form loss function is analogous to fitting a model to filtered data and provides a practical way to parameterize the weak form. Subsequently, we demonstrate how this approach overcomes the instability and inaccuracy of standard Neural ODE (NODE) in modeling chaotic systems. Through numerical examples, we show that our proposed training strategy, the Weak Penalty NODE, is computationally efficient, solver-agnostic, and yields accurate and robust forecasts across benchmark chaotic systems and a real-world climate dataset.
arXiv:2607.14398v1 Announce Type: new
Abstract: Constrained generative models aim to produce samples that satisfy complex feasibility constraints while remaining faithful to the data distribution. Existing constrained generation methods typically enforce constraints either through training-time optimization or sampling-time correction. Training-time optimization approaches optimize on states induced by the training distribution, which can differ substantially from those encountered during sampling. Sampling-time correction methods instead modify the sampling process at inference, introducing distribution shift and requiring expensive tuning, particularly for few-step sampling. We propose a fine-tuning framework that incorporates constraint guidance obtained through online rollout into the training process, which aligns training with sampling by differentiating through the fixed noise schedule used to numerically integrate the denoising process. This exposes the model to violations that arise along the denoising trajectory and aligns diffusion learning with the sampling process. Experiments across multiple tasks show that our method improves constraint satisfaction while maintaining competitive sampling quality compared to prior methods.
arXiv:2607.14290v1 Announce Type: new
Abstract: We present a comprehensive study of the timing resolution achievable in plastic scintillator detectors read out through wavelength-shifting (WLS) fibers coupled to silicon photomultipliers (SiPMs), combining a semi-analytical framework, toy Monte Carlo validation, and full Geant4 optical photon simulation. The analytical model traces the complete photon detection chain: scintillation emission, WLS fiber re-emission, optical transit time dispersion, SiPM single-photon time resolution, and electronics quantization. It expresses the timing resolution $\sigt$ as a function of the detected photoelectron yield $\Npe$, scintillator decay constants ($\taur$, $\taud$), WLS re-emission time ($\tauwls$), fiber numerical aperture, detector geometry, and readout electronics parameters. The analytical predictions are validated at two levels. First, toy Monte Carlo simulations ($2\times 10^5$ events per parameter point across 80 grid points spanning 8 fiber types and $\Npe$ from 5 to 200) achieve analytical-to-MC agreement of $0.9997 \pm 0.0015$. Second, full Geant4 optical photon simulations track the entire scintillation, wavelength-shifting, and fiber transport chain in realistic detector geometries, confirming the analytical timing predictions and providing first-principles photoelectron yield calibration. A comprehensive parameter scan covering 7 scintillator materials, 8 WLS fiber types, 5 SiPM models, 5 electronics configurations, 3 readout topologies, and 3 boundary conditions produces quantitative design maps and lookup tables for detector optimization.
arXiv:2607.14406v1 Announce Type: new
Abstract: Pujol and Desfontaines asked whether a private histogram can allow more error on larger counts and use that slack to protect members of larger groups more strongly. We study this question for fixed disjoint groups under add-or-remove-one adjacency. The privacy budget $v(n)$ depends on the affected count, is nonincreasing, and must bound both R\'enyi-divergence directions at every order. This is the count-dependent form of zero-concentrated differential privacy (zCDP) studied here. The original strict relative-error condition is impossible at count zero. We therefore make the boundary tolerance explicit by requiring $\mathbb{E}\lvert\widehat{x}_i-x_i\rvert < r\max\{x_i,1\}$, without changing the requirement at any positive count. Our main result determines the best dependence on group size. For the upper bound, we directly specialize an existing shifted-transformation framework. The resulting shifted-log Gaussian mechanism has a certified budget $v(n)=O_r(n^{-2})$. Conversely, for every fixed $0<r<1$, any mechanism satisfying the same positive-count utility requirement and count-dependent zCDP must have $v(n)=\Omega_r(n^{-2})$. Thus the inverse-square rate is optimal under the repaired formulation. A many-count information argument further places the leading coefficient in the large-count-then-small-error limit between $\pi/(4e^2)$ and $1/\pi$, a factor below three. At $r=1$, a data-independent release meets the repaired criterion with zero privacy loss.