arXiv:2607.17766v1 Announce Type: new
Abstract: Extra context is valuable for simultaneous speech translation of technical talks, but injecting the entire document context into every streaming segment is often too coarse. Through diagnostic experiments, we find that context gains mainly come from paper-specific terminology recovery rather than uniform semantic enhancement. We therefore propose EGTA, an Evidence-Grounded Terminology Adaptation framework that builds a document terminology memory, selects compact candidate terms conditioned on the current streaming state, and adapts ASR/speech-side and decoder-side decision spaces using only the selected terms. EGTA can be instantiated in cascaded, end-to-end, and generation-only SimulST settings without full-model fine-tuning. We evaluate EGTA on an ACL technical-talk SimulST evaluation suite consisting of MCIF-dev and ACL60/60-dev. On MCIF-dev, EGTA-RG improves BLEU by +1.05/+0.59, XCOMET-XL by +0.019/+0.006, named-entity recall by +79\%/+73\% relative, and acronym recall by +0.099/+0.171 on En$\rightarrow$Zh and En$\rightarrow$De. Across MCIF-dev latency settings, EGTA consistently improves XCOMET-XL, named-entity recall, and acronym recall. External validation on ACL60/60-dev further shows consistent terminology-recall gains without additional fine-tuning. Shuffled-memory controls and activation audits provide evidence that the improvements are tied to paper-specific evidence alignment rather than generic context prompting.
Science Journals
arXiv:2607.16619v1 Announce Type: new
Abstract: Safe and socially compliant navigation in open human-robot environments requires robots to reason about heterogeneous participants with different dynamics, autonomy levels, and social roles. Existing trajectory prediction and planning methods often rely on homogeneous interaction assumptions or enforce only geometric collision constraints, making it difficult to jointly model asymmetric interactions, coupled prediction-planning, and soft social norms. This paper proposes SAGE, a socially-aware generative engine for heterogeneous multi-agent navigation. SAGE represents robots and surrounding entities as a directed heterogeneous graph and employs a Heterogeneous Graph Transformer (HGT) to encode type-specific asymmetric interactions. Conditioned on the resulting context, a diffusion-based generative module jointly models future entity trajectories and robot trajectory plans. During inference, a training-free safety-social energy guidance mechanism refines sampled robot trajectories using differentiable collision, kinematic, task-progress, and role-conditioned social-compliance terms. Extensive experiments on real-world (ETH/UCY and SDD) and synthetic datasets verify the effectiveness of SAGE in improving safety and social compliance while maintaining task performance. The proposed guidance mechanism consistently reduces collision and social-violation rates, scales to teams of up to 20 robots, and enables explicit control of the safety-accuracy-task trade-off without retraining. These findings demonstrate the potential of SAGE as a scalable framework for socially-aware multi-agent navigation in complex environments.
arXiv:2607.16438v1 Announce Type: new
Abstract: Stochastic Mckean-Vlasov models have a substantial importance in different fields such as finance, biology and control. This paper puts the light on stochastic proportional delay Mckean-Vlasov model with L\'evy jump where the non-jump coefficients are granted the permission to grow beyond linearity. The truncated Euler-Maruyama algorithm is then applied to our addressed model where the convergence rate and almost sure exponential stability of the aforementioned numerical algorithm are being investigated. Finally, numerical examples are presented to foster the theoretical analysis done throughout the paper
arXiv:2607.17419v1 Announce Type: new
Abstract: Linear attention promises constant-time recurrent inference but degrades sharply on associative recall. We formulate attention recall as a spherical-packing problem and introduce Kernelized Linear Attention Activations (KATA), a framework whose feature maps are derived from first principles by certifying nonnegative attention weights through a self-dual homogeneous cone. Building on this observation, we show that rank-one positive semi-definite (PSD) features offer a favorable capacity--interference tradeoff. KATA recovers a parameter-free convex output gate and characterizes associative capacity through the Welch interference floor. For tolerances above this floor, KATA enlarges the state without adding parameters and admits spherical codes with exponentially many keys in the projection dimension. We implement KATA as fused Triton kernels at two operating points: a flash-attention-style forward up to ${\sim}1.6\times$ FlashAttention-2 throughput, and an exact $O(T)$ chunked-state form that reaches ${\sim}11\times$ FlashAttention-2 forward throughput at $131$k tokens. An associative scan of the first-order feature lowers the inter-chunk recurrence depth to $O(\log(T/C))$ for chunk size $C$ and averages ${\sim}2.4\times$ the throughput of a matched sequential linear-attention baseline. On long-range MQAR and repeated-key overwrite, several KATA variants outperform Gated DeltaNet, with parameter counts and state sizes reported alongside accuracy. Induction preserves near-perfect recall, while kernel benchmarks show that the maps can be implemented efficiently. KATA retains $0.985$ MQAR at a $16\times$ out-of-distribution length, approaching the softmax with roughly one quarter of the KV-cache entries. Experiments on 340M-parameter LLMs reveal a feature-dependent fluency trade-off and clarify how positional embeddings, delta rules, and decay gates interact with feature geometry.
arXiv:2607.17112v1 Announce Type: new
Abstract: This paper presents a unified dataset and modeling framework for financial alternative dispute resolution (ADR) cases collected from multiple Japanese ADR organizations. Each case consists of paired claims from the complainant and the respondent with a binary settlement outcome.
We introduce a functional tagging scheme to represent dispute structures and propose a multi-task model that jointly performs dispute classification and settlement prediction. Experimental results show that incorporating dispute structure improves prediction performance, and large language models achieve comparable or superior performance in several domains. These findings suggest that dispute structures are partially shared across ADR domains.
arXiv:2607.17395v1 Announce Type: new
Abstract: Leprosy (Mycobacterium leprae) has been confirmed in wild western chimpanzees (Pan troglodytes verus) in West Africa, presenting as clear and progressive visual symptoms. Manual review of camera-trap footage at landscape scale is infeasible, motivating the need for automated screening. We present the first deep learning pipeline for wildlife leprosy detection and contribute the PanLep300 dataset of 125,670 annotated bounding-box crops across 953 tracks from 303 camera-trap videos with ecologically-motivated splits that withhold whole individuals and camera installations. We benchmark spatial (2D), temporally aggregated (2.5D), and video-based (3D) classification approaches to investigate which approach is best suited to automated leprosy detection in wild apes. We find that simple aggregation of crop-level predictions consistently matches or outperforms both learned temporal models and end-to-end video architectures -- consistent with leprosy's static cutaneous presentation. We further find that performance is suppressed when tracklets contain frames of partially visible individuals -- as commonly occurs at the start and end of a track -- and demonstrate that this can be addressed through targeted construction and aggregation strategies.
arXiv:2607.17050v1 Announce Type: new
Abstract: GUI agents must reason about how actions transform interface states, but end-to-end success rates entangle this ability with perception, grounding, planning, and recovery. We introduce EvoGUI, a diagnostic framework that converts normalized GUI trajectories into three complementary visual question answering probes: temporal ordering, inverse action/value prediction, and contrastive one-step successor discrimination. Their labels are derived from trajectory order and logged actions, requiring no additional task-label annotation after trajectory normalization. We instantiate EvoGUI-Bench from Mind2Web and WebLINX, yielding 3,000 instances across 120 domains, and evaluate 28 vision-language model configurations zero-shot. The strongest model reaches only 60.4 EvoGain, while model scale and GUI specialization do not reliably predict performance. These results establish EvoGUI-Bench as a scalable diagnostic complement to end-to-end GUI-agent evaluation while exposing substantial headroom in state-transition understanding. The source code is publicly available at https://github.com/Yyhhh6/EvoGUI.
arXiv:2410.18936v2 Announce Type: replace
Abstract: We consider the foundational problem of maintaining a $(1-\varepsilon)$-approximate maximum weight matching (MWM) in an $n$-node dynamic graph undergoing edge insertions and deletions. We provide a general reduction that reduces the problem on graphs with a weight range of $\mathrm{poly}(n)$ to $\mathrm{poly}(1/\varepsilon)$ at the cost of just an additive $\mathrm{poly}(1/\varepsilon)$ in update time. This improves upon the prior reduction of Gupta-Peng (FOCS 2013) which reduces the problem to a weight range of $\varepsilon^{-O(1/\varepsilon)}$ with a multiplicative cost of $O(\log n)$.
When combined with a reduction of Bernstein-Dudeja-Langley (STOC 2021) this yields a reduction from dynamic $(1-\varepsilon)$-approximate MWM in bipartite graphs with a weight range of $\mathrm{poly}(n)$ to dynamic $(1-\varepsilon)$-approximate maximum cardinality matching in bipartite graphs at the cost of a multiplicative $\mathrm{poly}(1/\varepsilon)$ in update time, thereby resolving an open problem in [GP'13; BDL'21]. Additionally, we show that our approach is amenable to MWM problems in streaming, shared-memory work-depth, and massively parallel computation models. We also apply our techniques to obtain an efficient dynamic algorithm for rounding weighted fractional matchings in general graphs. Underlying our framework is a new structural result about MWM that we call the "matching composition lemma" and new dynamic matching subroutines that may be of independent interest.
arXiv:2410.19280v2 Announce Type: replace
Abstract: In integrated power and gas energy system optimization models (ESOMs), pipeline gas transmission with linepack is a particularly complex problem due to its non-linear and non-convex character. For ESOMs based on mixed-integer linear programing, piecewise linearization is a well-established convexification approach for this problem, which, however, requires binary variables to model feasible combinations of linear gas flow and pressure segments and thus can quickly become computationally challenging. In order to improve computational performance, this paper proposes a piecewise linearization method specifically designed to be tight, resulting in a reduced problem space a solver can explore faster. We provide numerical results comparing the proposed formulation against two piecewise linearizations from the literature, both from a theoretical point of view and in terms of practical computational performance, with results showing an average speed-up of 2.57 times for our case study. Test cases are carried out on a modified 24-bus IEEE Reliability Test System and a 12-node gas system, considering discrete unit commitment decisions.
arXiv:2411.10921v2 Announce Type: replace
Abstract: Accurate forecasts of distributed solar generation are necessary to maintain grid stability amid the increased uptake of distributed solar photovoltaic (PV) systems. However, the high variability of solar generation over short time intervals (seconds to minutes) caused by cloud movement makes this forecasting task difficult. To address this, using cloud images, which capture the second-to-second changes in cloud cover affecting solar generation, has shown promise. Recently, deep neural networks with attention that focus on important regions of an image have been applied with success in many computer vision applications. However, whether such methods provide meaningful benefits for cloud movement forecasting, and how such improvements propagate through to downstream solar generation forecasting accuracy, remains under-explored. In this study, we conduct a large-scale empirical investigation of the impact of attention-based cloud forecasting on solar generation forecasting, addressing a gap that has been overlooked in the literature. To this end, we develop a pipeline that incorporates an attention-enhanced convolutional long short-term memory network and an existing self-attention-based video prediction method to forecast cloud movement using satellite imagery. The effectiveness of the resulting cloud forecasts is evaluated through their downstream impact on solar forecasting across 50 PV sites in Australia. We further provide insights into the cloud conditions under which attention-based cloud forecasting methods yield the most significant improvements in downstream solar forecasting accuracy. We find that for clouds at high altitudes, the cloud predictions obtained using attention-based methods result in solar forecast skill score improvements of 5.86% or more compared to non-attention-based methods.
arXiv:2607.16354v1 Announce Type: new
Abstract: Retail demand forecasting remains difficult when demand shifts faster than static forecasting models can be retrained, especially in early demand cycles where newly observed labels are sparse. To address this, this study aims to improve adaptive retail forecasting by proposing a predict-then-correct (PtC) framework that retains a first-stage machine learning (ML) forecast and applies a few-shot continuous contextual bandit correction policy with similar-SKUs augmentation and top-p masked updating. Across Walmart retail data and an exclusive beverage dataset, PtC delivers statistically significant reductions in MAPE, MAE, and RMSE across stable & high volume, stable & low volume, and erratic & intermittent demand patterns, improves average RMSE by 9.52% over the ML-only baseline in the ablation study, and yields lower inventory costs than base-stock, proximal policy optimization, and soft actor-critic policies under the tested lead-time settings. These findings show that online forecast correction can bridge offline demand learning and real-time retail decision-making by adapting to sparse feedback without fully retraining the base forecasting model.
arXiv:2607.16355v1 Announce Type: new
Abstract: Recent advances in physics-grounded video generation leverage physics simulation as a physical prior to guide video synthesis toward physically plausible outcomes. The simulation process is controlled by physical specifications, which are typically generated by a vision-language model in a single pass. Such one-shot prediction often fails to accurately translate user intent into executable simulations, particularly for fine-grained object dynamics, complex motion trajectories, and temporally structured interactions. In this paper, we propose PhysAgent, a reflective agentic framework that closes the loop among physical program generation, physics simulation, stage-specific verification, and targeted program repair. Beyond improving the control of coupled physical parameters, our framework enables the agent to progressively realize complex trajectories, multi-stage interactions, and precise event outcomes by treating each physical program as an executable hypothesis. In addition, we design a set of physics-control APIs to support more stable and complex motion behaviors. Extensive experiments demonstrate that PhysAgent produces more physically plausible videos, achieves better prompt alignment, and generalizes more effectively across diverse physical scenarios.
arXiv:2607.16251v1 Announce Type: new
Abstract: Spatio-Temporal Foundation Models (STFMs) aim to learn generalizable representations of complex dynamical systems across space and time. However, existing approaches suffer from distributional bias in real-world pre-training data, structural bottlenecks of autoregressive or diffusion-based paradigms, and objectives that overemphasize point-wise reconstruction in noisy observation space.We propose \textbf{NeoST}, the first spatio-temporal foundation model pre-trained solely on procedurally generated synthetic systems. NeoST introduces a scalable synthetic pre-training corpus to mitigate real-world bias, a latent-space reasoning architecture that generates and iteratively refines multiple future trajectories without sequential error accumulation, and latent-space objectives that emphasize structural dynamics and enable inference-time correction under distribution shifts.Extensive experiments across diverse real-world benchmarks show that NeoST consistently outperforms existing STFMs in diverse real-world spatio-temporal systems, achieves superior long-horizon stability and inference efficiency.
arXiv:2607.16768v1 Announce Type: new
Abstract: Learning with noisy labels is a fundamental problem in training reliable deep neural networks. Robust loss functions provide a direct and effective way to mitigate the adverse effects of label noise. However, most existing robust losses are designed directly at the level of the final multiclass objective, which makes it difficult to systematically characterize and extend their robustness properties. In this paper, we propose a general framework that constructs robust multiclass losses from univariate base functions. By defining mapping operators from base functions to multiclass losses, the robustness of the induced losses can be characterized through simple properties of the base functions. We develop two complementary construction schemes, Target Separation and Binary Reduction, corresponding to inter-class independent and inter-class dependent formulations, respectively. For both schemes, we analyze their symmetry and asymmetry properties and derive corresponding sufficient conditions, which provide theoretical criteria for noise-robust loss design. The proposed framework also provides a new route to constructing symmetric losses, serving as a complement to normalization-based symmetric loss designs. Extensive experiments on synthetic and real-world noisy-label benchmarks demonstrate that the proposed losses achieve competitive or superior performance under various noise settings.
arXiv:2607.18161v1 Announce Type: new
Abstract: Coding agents are increasingly used to accelerate code generation in many downstream tasks, such as fixing bugs, building applications, and prototyping. However, despite their value as coding assistants, agent-generated code tends to be larger and more verbose than the corresponding human-written implementation. In this work, we show that the cause lies in the agent's own search process: while iterating toward a passing solution, an agent accumulates speculative edits, abandoned hypotheses, and temporary changes that persist into the final patch. This may seem harmless for a single patch, but the problem compounds as agents take responsibility for ever-larger portions of a codebase-a codebase that was once minimal and well-maintained slowly accumulates redundancy faster than it can be cleaned up, drifting to a state that is harder to maintain. Given the magnitude of this problem, we take a step towards alleviating this issue. First, we formally define this phenomenon as CodeSlop-the residual and functionally unnecessary edits commonly seen in AI-generated code. We then introduce our algorithm TRIM (Trajectory-guided Redundancy Identification and Minimization). Rather than minimizing CodeSlop directly, TRIM instead minimizes agent trajectories. As we show empirically, this indirect technique of minimizing CodeSlop is highly effective: TRIM cuts CodeSlop by 17.9%-32.9% across agentic scaffolds, with negligible performance regression. TRIM is also highly efficient, requiring roughly half the validation cost of algorithmic baselines such as Delta Debugging.
arXiv:2607.16266v1 Announce Type: new
Abstract: Existing approaches for reasoning about action and change provide expressive semantics for modeling dynamic systems, in most cases built on top of logic programming systems. We introduce a modular framework for transition and trajectory verification based on Tiles and implemented in Soda, which is an efficient functional programming language. The framework operationalizes action language semantics through executable verification pipelines that process states, actions, transitions, and rules as compositional functional components. Verification procedures are represented as typed functional pipelines, enabling modular specifications, reusable reasoning components, and transparent execution workflows with guaranteed pipeline termination. The framework includes an executable specification layer that allows users to define domain descriptions in YAML, which are operationalized into the underlying verification model and executable pipeline structure. We provide an open-source implementation and illustrate the framework through examples that involve misinformation and emotional reasoning.
arXiv:2607.17065v1 Announce Type: new
Abstract: The Subspace-based Model Identification algorithm using a modified Iterative Principal Component Analysis (SMI-IPCA) is a theoretically rigorous method for identifying a linear state-space model of a multi-input multi-output (MIMO) process, in an errors-in-variables (EIV) setting. The method can simultaneously estimate unknown heteroskedastic noise variances corrupting the input and output measurements, along with the state space model. This work proposes a recursive formulation of SMI-IPCA (RSMI-IPCA) enabling online identification and adaptive model updates as and when new data arrive. By maintaining a fixed length lag window rather than storing the complete historical data, RSMI-IPCA estimates measurement noise variances, process order, while simultaneously identifying the state-space matrices, making it suitable to monitor time-varying systems, whether the induced changes are slow or abrupt. The algorithm gradually adapts to slow sensor degradation (time-varying noise variances), changes in process operating conditions (time-varying model parameters), and structural modifications (varying model order). Simulation studies are presented to demonstrate the efficacy and practical applicability of the proposed algorithm.
arXiv:2607.17420v1 Announce Type: new
Abstract: Biographical personas are widely used in system prompts, but their effects on code generation are rarely evaluated under controlled, pre-registered conditions. We tested four prompt conditions (no persona, two engineer personas, and a research-librarian persona), 12 code-generation tasks, two frontier models, and five runs per cell (480 completions). Persona effects differed between the two tested models. Under the pre-registered mixed-effects analysis, the condition-by-model interaction was significant for provider-reported output tokens; a post-hoc visible-character measure showed the same qualitative pattern. Six GPT-5.5 completions were length-capped and are reported separately. On Claude Opus, the minimalist engineer persona reduced visible output by 30% (33% in provider tokens) without improving correctness, while the thorough engineer persona increased output without a correctness gain. In an exploratory post-hoc analysis, the librarian persona elicited in-character disclaimers in 55 of 60 Opus responses and 12 genuine no-code responses, lowering mean correctness from 0.92 to 0.67. GPT-5.5 produced neither behavior in its 59 non-truncated responses. These results are consistent with personas acting as Model-Dependent behavioral-policy biases rather than universal quality interventions. We release raw completions, derived scores, analysis artifacts, a pre-registration document, and an execution gate log; end-to-end test-based rescoring requires an unreleased task harness.
arXiv:2607.17962v1 Announce Type: new
Abstract: TabPFN is a transformer-based foundation model for tabular prediction that performs inference without task-specific training by conditioning on a support set and query inputs. Despite its strong empirical performance, its internal behavior on structurally difficult tabular geometries remains poorly understood. We study this behavior using zigzag persistent homology, treating TabPFN layer representations as evolving point clouds. We construct a controlled benchmark of synthetic tabular tasks with known true probabilities and varied intrinsic topology, including warped circles, tori, spheres, Hopf links, trefoil knots, and Swiss rolls. Across these tasks, we find that the topology of TabPFN's internal representation geometry is strongly associated with dataset-level reliability; for example, the zeroth homology group $H_0$ fragmentation count correlates positively with mean absolute residual across controlled tasks, and this association strengthens in a high-resolution warped circle case study at large sample size. Harder geometries induce a dual topological signature: increased $H_1$ loop activity and increased $H_0$ fragmentation, while the $H_1$ persistence becomes shorter-lived. These descriptors correlate with Bayes error, mean absolute residuals, and overconfidence. Our results suggest that zigzag persistence diagnoses the reliability of the inferred in-context task geometry and provides a context-level view of when TabPFN operates in topologically stressed regimes.
arXiv:2412.03771v4 Announce Type: replace
Abstract: Zero-shot learning enables models to generalise to unseen classes using semantic information, bridging the gap between training classes and previously unseen test classes. While widely studied in computer vision, its application to environmental audio remains underexplored, and generative approaches have received little attention.
This work presents the first benchmark of generative methods for zero-shot environmental sound classification. Four approaches spanning variational, adversarial, diffusion-based, and denoising paradigms are evaluated. The benchmark includes CADA-VAE and LisGAN, adapted from computer vision, together with two embedding-generation methods introduced in this work: one based on a denoising diffusion probabilistic model (DDPM) and the other on a conditional generative denoising network (CGDN).
Experiments on five environmental audio datasets (ESC-50, ARCA23K-FSD, FSC22, UrbanSound8K, and TAU Urban Acoustic Scenes 2019) and one music dataset (GTZAN) show that generative methods are competitive with established compatibility-based approaches. Among the evaluated generative methods, CGDN achieves the highest average accuracy and is the only one to significantly outperform both the DDPM- and GAN-based methods, while remaining statistically indistinguishable from the strong ALE baseline. These findings suggest that optimisation stability is an important factor in generative zero-shot learning for environmental audio.
arXiv:2412.04704v2 Announce Type: replace
Abstract: Traceability remains a critical capability to ensure system reliability, maintainability, and compliance in modern software development. Although unsupervised Information Retrieval (IR) and Machine Learning (ML) techniques are widely adopted for automated trace link recovery, their effectiveness is often limited by the quality and structure of the underlying artifacts. In practice, these approaches assume that meaningful traceability signals are embedded in textual data, an assumption that rarely holds in industrial settings with sparse, inconsistent, or unbalanced documentation. Furthermore, conventional evaluation metrics (e.g., precision, recall, F1) can misrepresent performance when data characteristics are not explicitly considered. We introduce TraceXplainer, an information-theoretic framework for evaluating the reliability and limits of unsupervised traceability. Our approach leverages self-information and mutual information (MI) to quantify the informativeness and alignment of source and target artifacts. Through a comprehensive empirical analysis of industry datasets, we show that typical traceability corpora exhibit significant information imbalances, where the source code contains on average more information than the corresponding documentation. In addition, the observed levels of mutual information, loss, and noise reveal inherent constraints on the ability of unsupervised techniques to recover accurate trace links. These findings suggest that improving traceability in practice requires a shift to data-centric engineering, focusing on artifact quality, consistency, and information alignment; rather than solely advancing model sophistication (or complexity). Our results provide insights for practitioners to better assess traceability readiness and guide improvements in documentation and development workflows.
arXiv:2607.18177v1 Announce Type: new
Abstract: Covalent virtual screening requires ranking compounds according to both noncovalent recognition and their ability to adopt a reaction-competent geometry with an appropriately reactive warhead. Here, we introduce BCover, a reaction-aware scoring suite that combines pre-reactive docking with quantum-chemistry-derived ligand reactivity descriptors, the electrostatic properties of the protein pocket. Quantum-chemical descriptors are aggregated using a nonlinear tree-based scoring model. BCover was evaluated retrospectively on the COValid benchmark, comprising nine targets and ten reactive sites, and compared with AutoDock, DOCK6, DOCKovalent, AlphaFold3 with Rosetta rescoring, and AlphaFold3 confidence-based ranking. BCover achieved an average adjusted LogAUC of 31% (57% max), an average ROC-AUC of 0.88 (0.96 max), an average EF1 of 18 (33 max). Its average LogAUC exceeded those of the classical docking methods and AlphaFold3-Rosetta, although AlphaFold3-mPAE provided the strongest overall enrichment. At an average runtime of about 10~s per ligand, BCover was approximately 25-fold faster than the evaluated AlphaFold3 workflows and achieved the highest average time-adjusted virtual-screening productivity index. Redocking experiments further showed that the method recovered near-native ligand conformations. These results demonstrate that combining docking-derived geometry with ligand local electronic reactivity and pocket electrostatics provides an efficient and interpretable strategy for covalent ligand prioritization. BCover is intended as a high-throughput screening method that complements more computationally demanding QM/MM and free-energy calculations during subsequent lead optimization.
arXiv:2412.10733v3 Announce Type: replace
Abstract: We study the computational power that oblivious robots operating in the plane have under sequential schedulers. We show that this power is much stronger than the obvious capacity these schedulers offer of breaking symmetry, and thus to create a leader. In fact, we prove that under any sequential scheduler, robots are capable of solving problems that are unsolvable even with a leader under the fully synchronous scheduler FSYNC. More precisely, we consider the class of pattern formation problems, and focus on the most general problem in this class, Universal Pattern Formation (UPF), which requires the robots to form every pattern given in input, starting from any initial configuration (where some robots may occupy the same point, hence forming a multiplicity). We first show that UPF is unsolvable under FSYNC, even if the robots are endowed with additional strong capabilities (multiplicity detection, rigid movement, agreement on coordinate systems, presence of a unique leader). On the other hand, we prove that, except for point formation (Gathering), UPF is solvable under any sequential scheduler without any additional assumptions. We then turn our attention to the Gathering problem, and prove that weak multiplicity detection (the ability to detect a multiplicity but not the exact number of robots forming it) is necessary and sufficient for solvability under sequential schedulers. The results obtained show that the computational power of the robots under FSYNC (where Gathering is solvable without any multiplicity detection) and that under sequential schedulers are orthogonal.
arXiv:2501.02373v3 Announce Type: replace
Abstract: Task arithmetic in large-scale pre-trained models enables agile adaptation to diverse downstream tasks without extensive retraining. By leveraging task vectors (TVs), users can perform modular updates through simple arithmetic operations like addition and subtraction. Yet, this flexibility presents new security challenges. In this paper, we investigate how TVs are vulnerable to backdoor attacks, revealing how malicious actors can exploit them to compromise model integrity. By creating composite backdoors that are designed asymmetrically, we introduce BadTV, a backdoor attack specifically crafted to remain effective simultaneously under task learning, forgetting, and analogy operations. Extensive experiments show that BadTV achieves near-perfect attack success rates across diverse scenarios, posing a serious threat to models relying on task arithmetic. We also evaluate current defenses, finding they fail to detect or mitigate BadTV. Our results highlight the urgent need for robust countermeasures to secure TVs in real-world deployments.
arXiv:2501.06620v3 Announce Type: replace
Abstract: The cumulative distribution function (CDF) is fundamental for characterizing random variables, making it essential in applications that require privacy-preserving data analysis. This paper introduces a novel framework for constructing differentially private CDFs inspired by functional analysis and the functional mechanism. We develop two variants: a polynomial projection method, which projects the empirical CDF into a polynomial space, and a sparse approximation method via matching pursuit, which projects it into arbitrary function spaces constructed from dictionaries. In both cases, the empirical CDF is approximated within the chosen space, and the corresponding coefficients are privatized to guarantee differential privacy. Compared with existing approaches such as histogram queries, tree-based methods, and adaptive quantiles, our approach achieves comparable or superior performance. Our methods are particularly well-suited to decentralized settings and scenarios where CDFs must be efficiently updated with newly collected or streaming data. They are also readily extensible to multivariate distributions while remaining effective. In addition, we investigate the influence of parameters such as dictionary size and systematically evaluate different dictionary constructions, including Legendre polynomials, B-splines, and distribution-based functions. Overall, our contributions advance the development of practical and reliable methods for privacy-preserving CDF estimation.