Papers

Soft and continuum robots enable manipulation through distributed body deformation and contact, yet translating language and visual context into executable whole-body actuation remains a fundamental challenge. We present SWIM, a framework that maps an initial RGB observation and a language instruction to a complete actuation-command sequence. Its vision-language-action (VLA) policy, SWIM-VLA, combines a diffusion action head with Visual Soft Proprioception (VSP) through a shared representation of RGB observations, language instructions, and tendon states. The diffusion head models conditional distributions of expert command chunks, while VSP supervises ordered body-anchor predictions using simulation ground truth, encouraging the representation to retain body geometry when learning from limited demonstrations. Embodied mechanical intelligence supports physical execution of command sequences generated through iterative virtual rollout from evolving simulated observations, with intrinsic compliance providing local contact adaptation without online policy queries. We evaluate SWIM on packing, reaching, and grasping on a planar tendon-driven soft robot, with grasping targets anchored. In simulation, SWIM-VLA achieves success rates of 100%, 96%, and 88%, respectively, outperforming an adapted OpenVLA-OFT baseline and controlled ablations. On hardware, SWIM achieves success rates of 100%, 80%, and 75%, compared with 75%, 40%, and 25% for direct online deployment of the same policy checkpoint.

Traditional energy forecasting solutions rely on task-specific supervision and energy asset representations, limiting transferability and the ability to capture general temporal dynamics across heterogeneous assets. We address this by proposing a distributed Joint Embedding Predictive Architecture (JEPA) for self-supervised learning from heterogeneous energy time-series. The framework predicts latent representations of masked temporal segments while integrating temporal observations and contextual information within a shared embedding space. To prevent representation collapse, training combines a latent-space predictive objective with covariance and temporal variance regularization. The evaluation was conducted on energy consumption and generation datasets under data-degradation scenarios and compared with a Transformer forecasting baseline. The learned representations remained stable (cosine similarity $\approx 0.98$; effective rank 185-235). JEPA achieved performance comparable to a Transformer on building energy data, higher $R^2$ in 3/5 consumer clusters, and outperformed the baseline on 9/10 unseen PVs ($R^2$=0.73-0.88 vs. <0.45), while showing greater robustness to missing data.

Continual learning must balance the learning of new knowledge with the retention of previously learned knowledge to incrementally learn tasks from a data stream without catastrophic forgetting. While leveraging pretrained models has significantly advanced continual learning, existing methods exhibit a scalability bottleneck when trained sequentially on many tasks, suffering from performance degradation due to inter-task interference and loss of plasticity. Inspired by evidence that sparse fine-tuning achieves performance comparable to full fine-tuning, this paper presents a novel sparsity-driven continual learning framework. Our continual learning method, termed CLARE, operates in two stages: it first identifies a sparse, task-critical parameter mask via a sparsity-inducing objective, then performs mask-constrained fine-tuning by only optimizing parameters selected by the mask. This two-stage sparse adapter mechanism enables all tasks to be accumulated within a shared adapter space while reducing destructive interference across tasks. Extensive experiments demonstrate the scalability of CLARE. On the long task-sequence benchmark Omnibenchmark-1k, CLARE outperforms strong baselines in final accuracy by a large margin, e.g, improving EASE by 4.64% and 13.34% after learning 100 tasks, respectively.

Autonomous wheel-loader control requires joint reasoning over task semantics, egocentric vision, proprioception, and 3D scene geometry. We present sensVLA, a Vision-Language-Action (VLA) architecture that combines a Qwen3-2B Vision-Language Model (VLM) with a fully trainable transformer action expert trained by flow-matching velocity regression. sensVLA routes Bird's-Eye-View (BEV) features, extracted from fused front and rear lidar, directly to the action expert through a dedicated cross-attention pathway, while the VLM consumes front and rear RGB views to provide task-conditioned semantic context. This design decouples spatial grounding from linguistic reasoning while preserving interaction between both streams at decision time. The expert predicts six action dimensions: longitudinal velocity, steering, body-frame displacement, arm rate, and bucket rate. On a real-world dataset from a wheel loader, sensVLA reaches aggregate per-step parity with a strong camera-only baseline and reduces longitudinal velocity RMSE by 28% and displacement error by 9% on loading centric scenarios. It also degrades 29% less when the camera stream is corrupted or removed, evidencing that explicit spatial grounding improves accuracy and fault-tolerance for heavy equipment autonomy.

We give new bounds for list sizes of random linear codes at capacity, max loads of linear hash functions, and Furstenberg sets, over every finite field $\mathbb{F}_q$. 1. Random linear codes over $\mathbb{F}_q$ with rate $1 - H_q(p) - \epsilon$ are $(p, O(q H_q(p)/\epsilon))$-list decodable with high probability for all values of $p, q, \epsilon$, including the high error regime. This nearly matches the list size lower bound of $H_q(p)/\epsilon$ due to Guruswami, Li, Mosheiff, Resch, Silas, and Wootters [IEEE Trans. Inf. Theory 2022]. Our bound is the first uniform improvement for $q > 2$ since Guruswami, Håstad, and Kopparty [STOC 2010]. 2. Linear hash functions over $\mathbb{F}_q$ hashing $n$ balls to $n$ bins achieve maximum load $O(q \ln \ln q / {\ln q}) \cdot \ln n / {\ln \ln n}$, both in expectation and with probability $1-o(1)$. This nearly matches the lower bound of $\ln n / {\ln \ln n}$. Previously, only a polylogarithmic upper bound was known for $q > 2$, due to Alon, Dietzfelbinger, Miltersen, Petrank, and Tardos [J. ACM 1999]. We reduce list decodability and linear hashing to strong Furstenberg set lower bounds, which we prove using a new polynomial method of multiplicity gaps. While previous polynomial methods analyze a set $S$ by studying polynomials that vanish on it, we consider polynomials that vanish everywhere, but with higher multiplicity inside $S$ than outside.

While Chain-of-Thought (CoT) reasoning has been proven to be effective, it often leads to overthinking, resulting in computational overhead, inference latency, and even degraded performance in large language models (LLMs). Existing concise reasoning frameworks significantly compromise accuracy while compressing the length of output. In this paper, we propose SKIP, a self-knowledge-guided step-wise preference learning framework. Starting with lightweight fine-tuning to adjust the model's output style, SKIP introduces a carefully designed knowledge probing mechanism to guide model to output an answer at each reasoning step. Based on the correctness of intermediate steps, we construct preference data that guide the model toward more efficient and correct reasoning by leveraging DPO. Experimental results demonstrate that our method effectively improves reasoning compression while mitigating performance degradation after fine-tuning. Besides, SKIP shows strong generalization ability on out-of-distribution datasets. We further conducted ablation studies on the component parameters of our framework.

We present GANADI, a systematic approach for identifying C/C++ OSS reuse genealogies to enhance software supply chain security. Understanding OSS reuse genealogy is crucial for improving SBOM completeness and prioritizing security remediation across supply chains. Although existing approaches can identify reused compo- nents and vulnerabilities within a project, they fail to trace OSS reuse paths through intermediate projects, limiting their effectiveness in securing supply chain ecosystems. To address this limitation, GANADI constructs reuse genealogies by clustering downstream projects based on shared characteristics of origin-derived code (called pivotal functions), and then inferring reuse direction among the projects within each cluster. When applied to 20 widely reused OSS projects with over 1,500 propagation paths, GANADI achieved 84.85% precision and 95.76% recall in identifying reuse genealogies, outperforming existing approaches that achieved at most 23.21% recall. Leveraging OSS reuse genealogy for vulnerability detection, we identified 48 unpatched vulnerabilities in real-world popular C/C++ projects. Among them, 23 were patched following our responsible disclosure (including one CVE ID assigned), demonstrating the practical impact of genealogy-based vulnerability management.

During social movements, protesters need to gather with limited communication means and limited knowledge other than what they observe in their direct surroundings. We propose BeWater, a fully distributed walking protocol that achieves gathering thanks to city information like street length, number of restaurants, number of lanes, or street names. Even though using only one of these observables performs poorly, we show that combining them in more advanced tactics rapidly leads to groups of significant sizes. To do so, our work leverages OpenStreetMap data to perform experiments on several real-world cities.

Machine learning (ML) has become the dominant approach for network traffic classification, achieving very high predictive performance. However, a model is only valuable if it learns semantically meaningful and trustworthy patterns rather than exploiting spurious correlations. Conventional evaluation practices predominantly assess predictive performance. Consequently, whether the model relies on semantically meaningful patterns remains unknown. To address these challenges, we adapt the knowledge generation framework for network traffic classification. The adapted framework combines data, ML models, explainability, visualization, and expert reasoning to support the iterative exploration, verification, and refinement of model behavior and data preprocessing. The framework is grounded in findings from the literature, benchmark dataset analyses, practical experience with XAI-based traffic classification, and expert feedback, providing practical guidance for semantic model validation. By complementing predictive performance with semantic validation and human expertise, the proposed framework supports the development of network traffic classification models that are not only accurate but also robust and trustworthy.

Retrieval-Augmented Generation (RAG) pipelines typically rely on a fixed indexing and retrieval configuration determined at preprocessing time. This one-size-fits-all design is ill-suited to domain-expert settings, where heterogeneous queries require different chunking granularities, metadata constraints, and source-selection strategies. As a result, configurations that are effective for one family of queries often perform poorly for others. In this paper, we introduce ORDER (Optimal Routing for Dynamic Evidence Retrieval), a query-conditioned RAG framework that jointly adapts indexing and retrieval to the incoming query. Our approach first discovers semantic clusters over a given set of questions associated to a corpus and learns, for each cluster, a chunking strategy together with a suited metadata filtering and reranking configuration. At inference time, queries are routed to the appropriate pre-built index through nearest-centroid assignment. To further improve retrieval, we propose a supervised query router (QRe) that predicts which collections are most likely to contain relevant evidence, coupled with a Uniform Multi-source Sampler (UMS) that allocates the retrieval budget evenly across the selected sources. We evaluate our framework on large-scale, heterogeneous historical archives and show that conditioning both indexing and retrieval on the query consistently outperforms both naive baselines and strong state-of-the-art RAG systems in complex expert-domain environments.

Social networks in which algorithms actively influence humans through personal recommendations are ubiquitous. While opinion dynamics is an established tool to analyze these systems, existing models typically do not capture how individual agents process personal recommendations. In this work, we introduce a model for personal recommendations that is analytically tractable and consistent with the confirmation bias phenomenon from behavioral psychology. We describe how individuals process recommendations based on prior beliefs and a sensitivity parameter using a Gaussian influence function. Using this model, we analyze the effect of different recommendation policies. For broadcast policies, where recommendations are homogeneous across the agents, a bifurcation analysis shows that the system exhibits bistability, which may result in unintended consequences. For personally targeted policies, we first derive optimal personal recommendations and then extend to robust convergence when the agents' sensitivity to personal recommendations is uncertain. The collective behavior of the proposed model and the derived policies are illustrated and evaluated through numerical simulations.

Lifelong conversational agents rely on memory systems to maintain deep, context-aware interactions with users. However, existing explicit textual memory pipelines suffer from a severe information bottleneck, often losing subtle behavioral patterns and emotional shifts. Furthermore, being typically static post-deployment, they cannot autonomously adapt to personal habits and preferences without manual feedback. Cognitive science, however, suggests that humans maintain mental models purely in a latent space and continuously refine them through predictive coding. Inspired by this, we propose ThinkFlow, a novel end-to-end latent memory framework for lifelong conversational agents. ThinkFlow bypasses the text bottleneck by dynamically compressing conversational flows into probabilistic latent memory skills, autonomously consolidating complex user states into disentangled, continuous vectors without semantic interference. To break this barrier, we introduce a test-time evolution paradigm. By coupling teacher-guided latent alignment to bootstrap the initial state with a self-supervised next-user-utterance prediction task for continuous refinement, the framework successfully overcomes cold-start challenges and achieves label-free lifelong personalization. Extensive experiments on long-term conversation benchmarks demonstrate that ThinkFlow significantly outperforms prevailing memory systems, providing highly personalized and contextually accurate responses over extended multi-session interactions.

Large language model (LLM) inference is often constrained by both computation and memory, especially in offloading-based deployments where model weights are transferred across memory hierarchies during autoregressive decoding. In this setting, reducing the number of executed layers can lower per-token latency while also avoiding costly weight movement. Motivated by this observation, we present FlexEE, an early exiting framework for resource-constrained and offloading-based LLM inference. FlexEE makes early exiting practical for LLM decoding through layer-wise exit supervision for reliable intermediate-layer prediction, self-speculative decoding over a Top-K local vocabulary for low-cost exit decisions, and dynamic hidden state management for KV-cache-correct and memory-aware execution. Across generative and downstream tasks, FlexEE enables efficient early exit with minimal accuracy degradation, delivering up to 1.27$\times$/3.16$\times$ and 1.25$\times$/2.83$\times$ end-to-end speedups on Llama2-7B and Llama3-8B under 0%/50% weight offloading, respectively.

Our industry partner focuses on quality assurance for industrial systems across multiple domains, including maritime systems, such as overwater vessels and autonomous underwater robots (AURs). Despite the strong performance of vision-language models (VLMs) in scene understanding, image captioning, and object recognition, their use in AUR software operating in underwater environments is underexplored. Therefore, in this context, it is important to evaluate the quality of VLMs for integration into AUR software and, so, automated software testing tools are needed to assess their suitability and improve their dependability. To this end, we propose a search-based metamorphic testing approach (MetaVLM) that identifies a minimal set of transformations on underwater images to induce incorrect model predictions, thereby revealing VLM failures. We employ NSGA-II as a multi-objective search algorithm and evaluate it over open-source VLMs, BLIP and CLIP, against a random search baseline. Results demonstrate the strengths and limitations of each VLM in the context of AUR software systems. Based on the results, we derive lessons for software engineering practitioners and researchers working on quality assurance of VLM-based software systems.

Frozen vision-language models (VLMs) remain unreliable on fine-grained left-right claims, and raw claim likelihoods need not reliably rank verification errors. After a horizontal-reflection intervention is fixed, how should its induced likelihood measurements be combined into a selective verification signal? We introduce Relation-Orbit, a closed-form contrast with no learned fusion parameters that assigns eight normalized likelihoods to query-supporting and counterfactual roles determined by reflection, inverse relation, and entity exchange. A claim is asserted only when the signed contrast exceeds a threshold selected on held-out data using pointwise Clopper-Pearson upper confidence bounds. On VSR and GQA across four frozen VLMs, Relation-Orbit yields higher mean test coverage at a 10% selective-risk calibration target than an all-eight Orbit-Max baseline in all eight dataset-backbone settings; gains over a nearly abstain-all one-sided intervention score are reported separately. A separate LLaVA-1.5/COCO evaluation, reduced-orbit controls, and a two-sided partition diagnostic further characterize the structural advantage.

Particle swarm optimization (PSO) is a widely used algorithm featured in many state-of-the-art optimization tool-kits. However, rigorous performance guarantees are still lacking. The standard PSO dynamics do not admit a natural mean-field description, which would provide an avenue for theoretical analysis. By modifying the PSO formulation, one can recover the consensus-based optimization (CBO) algorithm with memory, which admits a mean-field limit and facilitates rigorous convergence analysis. These theoretical guarantees rely heavily on the fact that for CBO, the drift and noise strengths can be chosen independently, whereas they are coupled for PSO. We analyze how the PSO parameter coupling affects existing convergence guarantees for CBO and its variant with memory effect. We show, by an explicit construction, that the coupling still leaves a non-empty set of admissible parameters for these convergence guarantees to hold. However, the admissible parameter ranges shrink in the limits used to recover PSO. The resulting convergence guarantees from CBO therefore do not directly extend to the classical PSO model. We provide numerical simulations illustrating the parameter tradeoffs shown in the theoretical analysis.

Crisis sentiment analysis is especially challenging for low-resource languages such as Bangla, where language, context, and public reaction shift rapidly. We introduce UNRESTSENT200K, a Bangla crisis sentiment dataset with approximately 200K Facebook and YouTube comments from the July-August 2024 Bangladesh uprising. The dataset covers five event-aligned phases, from early escalation and internet blackout to regime transition and a later flood crisis. Each comment is linked to its parent post, enabling evaluation with and without discourse context. All comments are annotated through a fully human process involving 14 native Bangla-speaking annotators and senior validation, achieving substantial agreement (kappa = 0.73, alpha = 0.71) and 94.2% blind-audit agreement. We benchmark fine-tuned encoders, prompted LLMs, and LoRA-tuned LLMs. Results show that parent-post context consistently improves performance, while temporal shift across phases causes large performance drops. Strong LLMs perform well, but still struggle with sarcasm, implicit political references, and phase-dependent meaning. UNRESTSENT200K provides a benchmark for studying context-aware and temporally robust sentiment analysis in low-resource crisis discourse. UNRESTSENT200K is available at https://sami0055.github.io/UNRESTSENT200K/

Many publications on robotic systems in healthcare describe early-stage work on low technology readiness levels. This paper describes how a mobile service robot approved as a medical device reaches higher technology readiness levels by adding peripheral functions and smaller improvements, which are pivotal for user acceptance in clinical environments and which often cannot be elicited by questioning users ex-ante as certain aspects only come in mind from testing the systems in clinical settings or operational environments. Especially developers of service robots in healthcare are advised to plan with such downstream developments, which can take significant implementation time, to obtain user acceptance and achieve widespread adoption of their robotic systems.

Autoresearch agents are reshaping the research ecosystem, but they can also let flawed claims enter the literature at scale. Human advisors catch such issues in drafts through careful, traceable feedback, yet advisor-style assessment requires extensive manual effort and does not scale. To shift automated paper assessment from a judge to a diagnostician, we introduce PaperDoctor, an agent framework for pre-submission feedback with three key innovations. First, a holistic hierarchical framework evaluates writing, layout, references, code, theory, prior work, and experiments through three layers: L1 surface screening, L2 typed verifiers that route each claim to the appropriate evidence, and L3 reproducers that rerun experiments by priority. Second, each finding contains an observation, a pointer to specific evidence such as a sentence, equation, or code line, and a revision suggestion, making critiques auditable and actionable. Third, PaperDoctor selectively rebuilds and reruns experiments based on claim importance and compute budget, surfacing reproducibility gaps and quantitative limitations that are invisible from the manuscript alone. We evaluate PaperDoctor on 30 in-progress papers, yielding 70.6% agreement and all positive holistic scores, and on 40 manuscripts across machine learning, natural science, and social science, covering human- and AI-authored papers with code. Overall, PaperDoctor produces more auditable feedback than human and other agentic reviewers, pairs critiques with concrete suggestions by design, and complements dimensions often overlooked by human reviewers. We also develop an interactive interface that lets authors browse findings grounded in their paper. PaperDoctor reframes automated paper assessment as diagnosis rather than verdict, taking a concrete step toward AI advisors for more rigorous AI-assisted scientific discovery.

Large Language Models are now common in student assessment, but we know little about how student demographics affect their use. Sometimes, considering student demographics may be necessary – for example, to improve readability for users with lower educational levels. However, it also risks being a cause of discrimination, e.g., when assigning lower scores to students from lower socioeconomic backgrounds. We set up controlled prompts to test 1) explicit demographic effects, where we mention demographic details directly, and 2) implicit effects, where we use conversation history as a demographic signal. We test these settings in three tasks: Automated Essay Scoring, Formative Feedback, and Metalinguistic Question Answering. We test six state-of-the-art LLMs on these tasks. In both explicit and implicit cases, the models pick up on demographic cues and can change their scoring, feedback, and answers accordingly. We find that LLMs frequently adjust the readability of feedback to education levels when these are explicitly mentioned. On the other hand, implicit conditions produce unpredictable biases, such as in question answering, where responses from lower-education levels receive lower sentiment scores. Our results provide clear evidence of demographic sensitivity in LLMs for educational assessment tasks.

Natural language arguments are compelling before they are formally explicit. A premise supports a claim through defeasible warrants, background commitments, and exception conditions that the text leaves implicit. However, formal verification requires the opposite. Making such arguments machine-checkable requires constructing the missing commitments, not only translating given sentences into logic. Construction, however, carries a risk that translation does not: a system free to add premises can make any claim provable, and a formally valid proof may assert the claim outright, prove it without the original premise, or establish more than the claim itself. We address this problem by formulating autoformalization for argumentative material inference as guard completion, in which non-monotonic material support is turned into monotonic formal inference relative to an explicitly constructed guard set. A completion is accepted only when its proof both passes the theorem prover and survives contrastive tests of premise dependence and claim selectivity. We implement this formulation in GUARD, a neuro-symbolic framework in which LLMs construct and formalize candidate guards, Isabelle/HOL verifies the resulting theories and returns step-level feedback for iterative refinement, and the system abstains when no faithful completion can be reached. Our empirical results on Debatepedia and ARCT using different LLMs demonstrate that GUARD yields significant improvements in verified-faithful (+35.3, +32.9 points) and substantial reductions in leakage (-25.9, -21.9 points) over the state-of-the-art LLM-driven theorem proving approach. Moreover, we show that the symbolic soft critique and the explicit assumption layer account for most of these gains, with the soft critique also improving the initial validity of the elicited context and reducing the number of iterations required for successful verification.

Long-form text-to-speech (TTS) enables multi-turn conversations with consistent prosody and higher quality voice cloning from longer reference audio. Recent open-weights autoregressive TTS models such as Qwen3-TTS and VoxCPM2 attain state-of-the-art word error rate (WER) and speaker similarity (SIM) on short-form prompts but significantly deteriorate when used with long-form prompts. We propose Localized Attention-Constrained Inference (LACI), an inference-only method to detect TTS errors in near real-time, roll back to the error onset and regenerate with temporary guardrails, adding negligible computational overhead. Using LACI, we improve worst-of-N WER across 10 RNG seeds for Qwen3-TTS-0.6B from 35.2% to 3.4% on prompts longer than 1500 words, even surpassing its short-form reliability of 5.4% on prompts with fewer than 500 words. To demonstrate the efficacy of LACI on voice cloning reliability, we propose a sliding-window version of the SIM metric that we call wSIM. wSIM exposes several novel failure patterns that are not captured by SIM. LACI improves worst-of-N wSIM from 0.01 to 0.47 on 120 seconds of reference audio while reducing the rate of catastrophic generations with WER above 30% from 26% to below 1%

The Open Network (TON), with a peak market capitalization exceeding $20 billion and over 175 million activated on-chain addresses, relies on the TVM (TON Virtual Machine) to execute smart contracts. TVM uses first-class continuations with savelists to manage control flow and register state across continuation invocations. Since savelist-captured registers allow data to flow across continuation boundaries without passing through the operand stack, bytecode-level analyses cannot construct complete data flow tracking without explicitly modeling savelist semantics. We present TasmScan, the first bytecode-level static analysis framework for TVM that enables cross-continuation data flow reasoning without requiring source code. TasmScan models savelist semantics via forward register analysis with a formal over-approximation guarantee for exact-resolved save sites and locally tracked register definitions, then lifts bytecode into TASIR, a typed intermediate representation, and performs path-sensitive taint analysis with context-aware sources to detect defects. We evaluate TasmScan on 2,921 contracts from the TON verifier registry and a labeled benchmark of 208 contracts with human-confirmed ground truth. On the full corpus, TasmScan resolves 294,546 dynamic continuation targets with 100% precision; ablation confirms that savelist propagation is essential for resolving indirect register calls that depend on cross-continuation register passing. On the benchmark, TasmScan detects 95.3% of defects across five classes with 96.8% precision. A 366-pair stratified sample from the full corpus estimates 85.8% overall precision. TasmScan offers a 17x median speedup over the state-of-the-art symbolic-execution baseline, and in the path-analysis comparison completes 100% of analyses with zero crashes or timeouts.

LLM-based multi-agent systems can fail even when communication succeeds because agents do not correctly track their peers' roles, knowledge, or intentions. We investigate whether such inter-agent misalignment cases, labelled FC2 in MAST-Data, can be converted into functional partner-state reasoning items. ToMAS applies four explicit convertibility criteria to diagnosed execution traces. A full conversion pass over 242 eligible non-AG2 training traces produced 39 CLEAN items. In an 18-trace reliability pilot, two annotators achieved 94.4% raw agreement and Cohen's kappa = 0.92. We then used the converted items as binary rewards in a small-scale GRPO feasibility experiment with Qwen2.5-1.5B. On a 28-item held-out Magentic GAIA diagnostic, every evaluated condition exceeded the ROUGE-L threshold on the same 2 of 28 items. Post-hoc adapter checks show why: under the learning rate used, the LoRA update remained numerically negligible (max abs Delta W about 7e-6), so all conditions decode identically to the untrained checkpoint. The experiment therefore does not show a training effect and cannot establish one; it reports an executable pipeline together with two limitations that any conclusive study must address: a provenance gap between the training and evaluation items, and lexical-overlap scoring. ToMAS provides a preliminary rubric and pipeline for converting diagnosed coordination failures into trainable partner-state reasoning items and identifies the requirements for a conclusive matched-domain evaluation.

Open-weight language models publish the strings their chat templates use to mark turns, roles and tool results, which the tokenizer maps back to the reserved identifiers the model obeys. Anyone who controls text in a prompt can therefore write a turn boundary indistinguishable from one the serving stack wrote. We audit 256 deployed chat tokenizers. All are forgeable, and the flag usually recommended as a fix leaves 56.6% forgeable because it misses the tool and reasoning markers agent systems rely on. We propose nameless tokenization, which leaves the control entries with a reserved identifier and no surface string, so the content encoder cannot emit one and message content reaches the model unaltered. Across five tokenizer families it reproduces the standard token stream exactly on attack-free data and lifts accuracy on a probe of delimiter-bearing text from 8.5% to 59.9%, where sanitizers lose it. Separating a delimiter's appearance from its identifier shows the identifier matters little against a bare task instruction, but carries most of a forged tool result and most of any forged turn once the system message tells the model to treat user content as data.

Numerical simulations of ocean flows typically require fine computational meshes to resolve the Munk scale, leading to high computational costs. Filtering-based large eddy simulation (LES) provides a way to relax the mesh size requirement by modeling the effects of the unresolved scales. For the implementation of this strategy, we propose a three-step algorithm called Evolve-Filter-Relax (EFR) that requires (i) the solution of a QGE problem, (ii) a nonlinear Helmholtz filter for the potential vorticity field leveraging an indicator function, and (iii) a final relaxation step. We show that the EFR algorithm can be interpreted as a splitting scheme for a perturbed QGE problem with additional dissipation and provide a practical choice for the relaxation parameter. For comparison, we also investigate a nonlinear Bardina regularization of the QGE. Numerical results on a classical benchmark show that both the EFR approach and the nonlinear Bardina regularization significantly improve the accuracy and stability of coarse mesh simulations with no LES model. Additionally, the EFR method with a deconvolution-based indicator function delivered the best balance between accuracy, stability, and computational efficiency in a test case involving a more realistic geometry (Mediterranean Sea).

This paper develops a general framework for the well-posedness, regularity, and strong approximation of the stochastic reaction–diffusion equation (SRDE) with superlinear drift and diffusion coefficients. We first extend the well-posedness results in W. Liu and M. Röckner, J. Funct. Anal., 2902–2922, 2010 and W. Liu, J. Differential Equations, 572–592, 2013 to the case of superlinear diffusion in the Gelfand triple \(V \hookrightarrow H \hookrightarrow V^*\), with \(V\) equipped with the norm \(\|\cdot\|_V\), and derive a moment estimate by establishing a new Itô formula for \(\|X\|_V^p\) with general \(p \ge 2\). We then apply this abstract result to the SRDE, establish higher spatial regularity \(\dot H^{1+\gamma}\) for any \(\gamma \in [0,1]\) whenever the initial datum lies in the same Sobolev space, and obtain temporal Hölder regularity. Finally, we construct a family of tamed finite element methods (tamed-FEMs) for the SRDE under general assumptions on the tamed functions, derive their long-time unconditional stability, and establish optimal strong convergence rates. To our knowledge, this is the first strong approximation result for SPDEs with superlinear diffusion coefficients.

Federated learning lets multiple participants train a shared model without pooling raw data, by exchanging locally trained model updates instead. Federated averaging assumes that averaging local models is a reasonable way to solve one shared problem when participants' data are broadly similar. Work on non-IID federated learning has shown that this assumption can withstand differences in label and feature distributions. We ask whether it survives a different strain specific to graph neural networks, where client graphs differ not in label or feature distribution but in structure itself, requiring the same shared weights to operate over fundamentally different topologies. We call the resulting harm structural negative transfer. In a federation of real citation networks and synthetic structural proxies, a structurally atypical client lost more than half its achievable accuracy simply by joining. In an initial six-client federation, two label-free structural statistics computable before training were strongly associated with this harm. Expanding to twenty clients showed that degree divergence remained associated with harm, although more weakly, and survived removal of domain contrast. Spectral divergence did not replicate, which we trace to a confound caused by the composition of the reference pool used for leave-one-out statistics. A causal intervention isolating topology found no significant effect. A degree-normalization mechanism held across twenty-four seeds but did not explain the harm when corrected. The best of five candidate fixes beat a tuned baseline only until a matched, structurally blind control was applied, after which the gain disappeared. What survives is a modest, partially replicated, degree-specific signal that is not yet a validated predictor at scale.

In various fields, such as medicine and marketing, accurately predicting individual treatment effects holds significant promise. However, achieving reliable predictions alone is often insufficient for making informed decisions; it is equally important to understand why the treatment effect is higher for some individuals than for others. To address this two-fold challenge of prediction and interpretation, we introduce an algorithm based on decision trees and random forests for estimating individual treatment effects. Our algorithm is simple: it operates exactly like a standard random forest, but with a different splitting criterion, and requires no additional workarounds such as double machine learning or orthogonalization as used in Generalized random forests. It handles observational studies with varying treatment propensities without requiring separate estimation of the full propensity function. This is achieved by combining two splitting criteria—one targeting heterogeneity in the treatment effect, the other targeting bias correction for the average treatment effect—which together improve split point selection and automatically distinguish confounders from features responsible for heterogeneity. As a result, interpretation follows directly from the fitted tree structure itself, that is, from which features the trees split on and with which split statistics, without requiring separate post-hoc analysis. For the theoretical analysis of this algorithm, we consider a change point model with step functions for potential outcomes and treatment propensity and provide insights into the theoretical underpinnings of our approach. Simulation studies show that our simple algorithm achieves comparable, and often better, prediction accuracy than existing methods, while substantially improving interpretability.

Ensuring that multilingual language models generate coherent text in a specific target language is a major issue in multilingual language modeling. We develop an optimal control method for target-language text generation as well as a framework for evaluating the quality of generated text in terms of language adherence, linguistic coherence, and semantic coherence. We find that the proposed method performs at least as well as the prominent difference-in-means activation steering method for the majority of models tested, with substantially less hyperparameter tuning required.