Kola Tubosun, Anuoluwapo Aremu, Tolulope Ogunremi, Iroro Orife, David Ifeoluwa Adelani
ÌròyìnSpeech is a 42-hour, 80-speaker Yorùbá read-speech corpus whose audio has been distributed by ELRA since 2024. This paper describes the release of its text component: 24,905 unique, hand-verified, tone-marked Yorùbá sentences (275,897 tokens; 15,687 types), curated in 2022 as recording prompts. Roughly 11,000 sentences were adapted from openly licensed news material; the remainder were written in-house to broaden coverage beyond the religious translation that dominates existing Yorùbá corpora. Every sentence was checked by hand for tone-mark accuracy, edited for read-aloud clarity and a neutral register, and localised so that non-Yorùbá personal and place names appear in Yorùbá form. Preparing the text for release surfaced systematic Unicode normalisation failures affecting more than 60% of lines (with precomposed and decomposed forms of the same letter co-occurring within single sentences) which we document and correct. The corpus supports diacritic restoration, grapheme-to-phoneme conversion, TTS front-end development and orthographic research, and serves as a validated prompt set for new recording.
The Nash-Williams--Tutte theorem characterizes the existence of $k$ edge-disjoint spanning trees by a condition on every vertex partition. We prove that, for simple graphs, the same condition guarantees $k$ edge-disjoint spanning trees, each of diameter $O(n/δ)$ and with $O((n/δ)\log(δ+1))$ internal vertices, where $n$ is the number of vertices and $δ$ is the minimum degree. Both bounds hold simultaneously for every tree, with absolute implicit constants independent of $k$, and each is asymptotically optimal in general. Our proof is constructive and yields a randomized algorithm with expected running time $\tilde{O}(n^5)$. We derive applications to short edge-disjoint routes and weak linkages, small Steiner trees, and survivable networks with short paths. The joint bounds also yield low-diameter spanning Eulerian subgraphs and short tours for postman and general routing problems.
Direct photons escape heavy-ion collisions with little rescattering, carrying information from the full emission history. Yet describing the measured direct-photon yield and the sizable elliptic flow $v_2$ together remains a long-standing challenge. Here we explore how correlations between emitting partons may affect both observables. The local $2\to2$ photon rate depends on the joint distribution of incoming partons, so a connected correlation between them can change photon emission without changing the one-particle distribution of medium particles. Once folded over the evolving medium in Au+Au and Pb+Pb collisions, the correlation raises the photon yield toward the fitted PHENIX and ALICE data and increases $v_2$ mainly at intermediate $p_T$. The fitted temperature dependence accounts for most of the net flow increase in this region, suggesting that the correlation changes the relative contributions between hotter and cooler regions.
Equivariant neural networks incorporate known symmetries of the data, such as permutations, rotations, or translations, directly into their architecture, often improving sample efficiency and generalization. However, strict equivariance can make optimization difficult, for example, when the data only approximately satisfy the assumed symmetry, or when the equivariance constraints induce a challenging loss landscape. Recent studies have shown that relaxing equivariance during training by introducing non-equivariant dense linear layers can ease optimization in such cases and improve the performance of the resulting strictly equivariant model, after removing the relaxation layers at test time. While effective, this approach incurs a significant computational overhead, limiting its applicability in scalable architectures. In this work, we propose a more efficient constraint-relaxation method based on positional encoding (PE). Our framework injects a positional encoding with learnable scale that breaks the model's original symmetry. This positional signal is gradually annealed to zero, recovering the original equivariant model by the end of training. Empirically, we demonstrate significant improvements for translational and rotational equivariant models with only marginal compute and memory overhead.
Nivya Talokar, Ayush K Tarun, Murari Mandal, Maksym Andriushchenko, Antoine Bosselut
LLM-based agents execute real-world workflows via tools and memory. These affordances enable ill-intended adversaries to also use these agents to carry out complex misuse scenarios. Existing agent misuse benchmarks largely test single-prompt instructions, leaving a gap in measuring how agents end up helping with harmful or illegal tasks over multiple turns. We introduce STING (Sequential Testing of Illicit N-step Goal execution), an automated red-teaming framework that constructs a step-by-step illicit plan grounded in a benign persona and iteratively probes a target agent with adaptive follow-ups, using judge agents to track phase completion. We further introduce an analysis framework that models multi-turn red-teaming as a time-to-first-jailbreak random variable, enabling analysis tools like discovery curves, hazard-ratio attribution by attack language, and a new metric: Restricted Mean Jailbreak Discovery. Across AgentHarm scenarios, STING yields substantially higher illicit-task completion than single-turn prompting and chat-oriented multi-turn baselines adapted to tool-using agents. In multilingual evaluations across six non-English settings, we find that attack success and illicit-task completion do not consistently increase in lower-resource languages, diverging from common chatbot findings. Overall, STING provides a practical way to evaluate and stress-test agent misuse in realistic deployment settings, where interactions are inherently multi-turn and often multilingual.
Aboubaker Seddiq Benterki, Jüri Vain, Gert Kanter, Leelo Aino Jürgenstein
We introduce ALBI (Agent for Learning By Induction), a neuro-symbolic ILP framework that replaces the ASP-based hypothesis generator in the Learning from Failures (LFF) paradigm with a Large Language Model (LLM), while retaining SWI-Prolog as a formal verifier. ALBI implements an iterative generate-test-constrain loop: the LLM proposes candidate hypotheses from structured prompts; Prolog tests each candidate; and diagnostic feedback drives refinement. We further introduce semantic anonymization, a metamorphic testing methodology, to distinguish structural symbolic induction from surface-level pattern matching on predicate names. Experiments on 30 standard ILP benchmarks show that ALBI achieves 100% success across three frontier LLMs (Gemini 3.1 Pro, GPT 5.4 Pro, Claude Opus 4.6), matching Popper while requiring only 1.4-1.7 iterations on average. Under anonymization, all models maintain 100% success with a moderate iteration increase (1.36-1.67 times), providing evidence of robust symbolic reasoning.
We study (non-induced) subgraph counting under interactive local edge differential privacy (LEDP). Given a fixed pattern graph $H$ with $k$ vertices, $\ell\ge1$ edges, and $q$ connected components, our goal is to approximately count its copies in an arbitrary $n$-vertex undirected graph while preserving edge privacy. We give two complementary accuracy guarantees. First, for every $H$, we give Linear Noise Cancellation (LNC), a two-round $\varepsilon$-LEDP algorithm with additive error and root mean square error both $O(n^{k-3/2}/\varepsilon^\ell)$ on every $n$-vertex graph. For fixed sufficiently small $\varepsilon$, this improves the optimal noninteractive additive error for triangles by a factor of $\sqrt n$ and gives the same improvement in worst-case root mean square error for all cliques on at least three vertices. To our knowledge, this is the first separation between interactive and noninteractive LEDP subgraph counting, showing that a single additional round can improve worst-case accuracy polynomially. Second, we determine how accuracy improves when the graph has maximum degree at most a public bound $d$. Our Predict and Correct (PC) framework gives an $(\ell+2)$-round $\varepsilon$-LEDP algorithm with additive error $O(n^{q-1/2}d^{k-q-1}\log^{3\ell-2}n/\varepsilon^\ell)$. For connected patterns, its polynomial factor is $\sqrt n\,d^{k-2}$, giving sublinear error on constant-degree graphs at fixed privacy. We prove matching lower bounds in $n$ and $d$, up to logarithmic factors at fixed privacy, even under arbitrary interaction and approximate privacy with sufficiently small $δ$. At $d=Θ(n)$, the lower bound also establishes the optimality of LNC's dependence on $n$.
Assigning applicants to posts in the presence of applicant preferences and quotas associated with posts is extensively investigated. For a post, a lower quota guarantees, and an upper quota limits the number of applicants assigned to it. Typically, quotas are assumed to be fixed, which need not be the case in practice. We address this by introducing a soft quota setting, in which every post is associated with two values - lower target and upper target - which together denote a range for the intended number of applicants in any assignment. Unlike the fixed quota setting, we allow the number of applicants assigned to a post to fall outside the range. This leads to assignments with deviation. Here, we study the problem of computing an assignment that has two orthogonal optimization objectives - minimizing the deviation (maximum or total) with respect to soft quotas and ensuring optimality with respect to preferences of applicants (rank-maximality or fairness). The order in which these objectives are considered, the different possibilities to optimize deviation combined with the well-studied notions of optimality with respect to preferences open up a range of optimization problems of practical importance. We present efficient algorithms based on flow networks to solve these optimization problems. We also consider a generalization of the soft quota setting, where every deviation is associated with a cost. We show extensions of our algorithms for solving the problems in this setting.
Large language models are deployed as long-horizon agents that compose diverse tools across MCP services into executable workflows. Existing MCP environment-scaling methods are data-centric: they first synthesize a database and scenario, then derive tools and tasks from them. As a result, tool interfaces may not match real ones, tool compositions are not grounded in execution, and tasks rarely span more than one environment. We propose ToolSpace, a tool-centric framework that reverses this order. ToolSpace mines data, state, and retry dependencies from adjacent calls in execution traces of real MCP services and open agent corpora, using deterministic rules rather than LLM judgment, and clusters the resulting weighted tool-composition graph into environments. Databases are synthesized only for state-mutating environments, while query and stateless tools replay recorded returns. ToolSpace then performs state-aware random walks with rollback and decompiles each chain into a natural-language task with assertion-based checks, keeping only samples that replay successfully from the initial state. Applied to AutomationBench and tau3-Bench Banking, the pipeline produces harder Pro versions on which 7 frontier models drop by up to 38.2 points. Across seven long-horizon tool-use benchmarks, ToolSpace raises Qwen3.6-35B-A3B from 23.0 to 41.0 average score (43.2 with RL) and GLM-5.2 from 44.6 to 56.6, on par with Claude Opus 5. Ablations show that execution-witnessed edges clearly outperform LLM-judged ones, and performance keeps improving with data and environment scale.
Lingguang Wang, Ömer Şahin Taş, Marlon Steiner, Christoph Stiller
Learning-based planners are sensitive to the long-tailed distribution of driving data. Common maneuvers dominate datasets, while dangerous or rare scenarios are sparse. This imbalance can bias models toward the frequent cases and degrade performance on critical scenarios. To tackle this problem, we compare balancing strategies for sampling training data and find reweighting by trajectory pattern an effective approach. We then present FlowDrive, a flow-matching trajectory planner that learns a conditional rectified flow to map noise directly to trajectory distributions with few flow-matching steps. We further introduce moderated, in-the-loop guidance that injects small perturbation between flow steps to systematically increase trajectory diversity while remaining scene-consistent. On nuPlan and the interaction-focused interPlan benchmarks, FlowDrive achieves state-of-the-art results among learning-based planners and approaches methods with rule-based refinements. After adding moderated guidance and light post-processing (FlowDrive*), it achieves overall state-of-the-art performance across nearly all benchmark splits. Our code is available at https://github.com/einsteinguang/flow_drive_planner.
Alexandre G. Leclercq, Sébastien Bougleux, Aurélien Corroyer-Dulmont, Romain Hérault
Deep learning in medical imaging is constrained by data scarcity and by privacy regulations that make centralizing patient data across institutions impractical. Federated Learning (FL) addresses these constraints by keeping data local, but its distributed nature exposes training to strong statistical heterogeneity. Multicentric medical data is particularly affected, exhibiting a mixed skew that combines feature, label, concept, and quantity shifts across centers. Personalized FL mitigates heterogeneity by tailoring a model to each client, yet most methods assume training from scratch, which is unrealistic given the high dimensionality of medical features relative to the limited data available. We propose the Personalized Aligner Federated Pretrained (PAFP) framework, a personalized FL approach built on a pre-trained backbone. PAFP inserts client-specific Feature Alignment modules before the fine-tuned blocks to realign hidden feature distributions toward a server-aggregated target. On the FedISIC benchmark, PAFP attains the highest unweighted balanced accuracy while reducing inter-client performance variance roughly six-fold relative to the strongest baseline, yielding accuracy and cross-client equity jointly. Our code is publicly available at https://github.com/Alexandre-Leclercq/PAFP.
Christian Scherer, Joe Watson, Theo Gruner, Daniel Palenicek, Ingmar Posner, Jan Peters
Distilling expert demonstration data into large generative models using behavioral cloning is a scalable approach to learning capable policies for robotic control, particularly for dexterous manipulation. Reinforcement learning (RL) can be used as a means to finetune these policies further using additional experience. An open question is whether RL is more sample-efficient than collecting more expert demonstrations. Prior work has finetuned large pretrained policies in a scalable fashion by applying RL to a smaller residual policy that corrects the pretrained model. However, for typical sparse reward tasks, RL algorithms can struggle to optimize the behavior in a sample-efficient manner. We explore inverse reinforcement learning, where a dense reward function is learned from expert demonstrations, potentially reducing the challenge of RL finetuning. We specifically consider coherent imitation learning, an IRL method that facilitates improvement of the BC policy by using a specific learned reward formulation with theoretical guarantees for imitation learning. We show that our IRL method maintains or improves the performance of pi-0.5 on all six sparse manipulation tasks and achieves a $\geq 90\%$ success rate on five out of six complex manipulation tasks, outperforming RL-based baselines using sparse rewards. We also demonstrate real-world learning on a robot manipulation task, finetuning pi-0.5 to success with less than 30 minutes of environment interaction time. By ensuring our initial pretrained finetuning policy is optimal for our initial reward and critic, our method circumvents the initial drop commonly seen in RL finetuning and enables faster improvement.
A \emph{rainbow cycle} in a list-edge-colored graph is a cycle where no color appears more than once. We give a short and simple proof of a result of [ABSZZ] showing that a properly edge-colored $n$-vertex graph with average degree $Ω(\log n\log\log n)$ always contains a rainbow cycle, and generalize it to weighted graphs with edges list colored with list size at most $\ell$ and where the total weight of all edges containing a given color $i$ incident to a vertex is at most $Δ$, showing that $Ω_\ell(Δ\log n\log\log n)$ average degree guarantees a rainbow cycle. Using the reduction of [AG26] and the new generalized rainbow cycle theorem, we prove that for $r\geq 3$, every binary linear $r$-query locally correctable code $E:\mathbb{F}_2^k\rightarrow \mathbb{F}_2^n$ satisfies $k\leq \tilde{O}(n^{1-2/(r-1)})$ by showing a rainbow analogue of the odd $r$-LDC lower bounds of [BHKL25,JM25], closing the gap between the best known lower bounds for odd- and even-query binary linear $r$-LCCs.
Interpretability often locates concepts by copying part of a language model's state from one input into another (activation patching). A larger output change counts as stronger evidence that this part carries the concept. Methods that learn which part to copy often change the output more than the whole state does. By that reading, learned parts isolate the concept more cleanly. Yet the whole contains the part. So whose effect is this excess, the network's or the method's? Copying the whole state learns nothing, so it shows what the network produces. We prove that, to first order, the effects of orthogonal parts add up to that of the whole. A part therefore exceeds the whole exactly when the rest moves the output back, which does not require isolating the concept more cleanly. Objectives that reward a larger effect select such parts. Distributed alignment search with cross-entropy, for example, exceeds the whole-state copy just before the output on almost all tasks, and inside the network at most sites. In both, changing only its objective to target what the network produces removes most of the excess. It therefore comes largely from the objective, so a larger learned effect alone is not stronger evidence.
Pranith Kumar, Prasun Gera, Hyojong Kim, Chulhyung Park, Hyesoon Kim
Weak-memory processors rely on ordering instructions for correctness, yet conventional implementations often enforce them more conservatively than the memory model requires. This over-enforcement manifests as drain-induced retirement stalls at ordering instructions and conservative squash/replay of speculative loads, suppressing legal executions and reducing throughput. We present TEMPO, a tag-based framework for precise micro-architectural implementation of ordering instructions. TEMPO assigns lightweight ordering tags to instructions and decomposes enforcement across retirement-time predicates and completion-time store ordering, allowing the core to enforce required ordering without conservative retirement serialization. TEMPO eliminates unnecessary retirement serialization at ordering instructions and speculative-load squash/replay. In our evaluation, TEMPO reduces geometric-mean normalized execution cycles by 7.9% on native four-thread workloads and improves geometric-mean IPC by 15.9% on an instrumented SPEC2017 dynamic binary translation (DBT) proxy for cross- ISA execution (e.g., x86-on-Arm), while adding only 262 bytes per core.
The rapid proliferation of Generative Artificial Intelligence (GenAI) is reshaping pedagogical practices and assessment models in higher education. While institutional and educator perspectives on GenAI integration are increasingly documented, the student perspective remains comparatively underexplored. This study examines how students perceive, use, and evaluate GenAI within their academic practices, focusing on usage patterns, perceived benefits, and expectations for institutional support. Data were collected through a questionnaire administered to 436 postgraduate Computer Science students at the University of Hertfordshire and analysed using descriptive methods. The findings reveal a Confidence-Competence Paradox: although more than 60% of students report high familiarity with tools such as ChatGPT, daily academic use remains limited and confidence in effective application is only moderate. Students primarily employ GenAI for cognitive scaffolding tasks, including concept clarification and brainstorming, rather than fully automated content generation. At the same time, respondents express concerns regarding data privacy, reliability of AI-generated information, and the potential erosion of critical thinking skills. The results also indicate strong student support for integrating AI literacy into curricula and programme Knowledge, Skills, and Behaviours (KSBs). Overall, the study suggests that universities should move beyond a policing approach to GenAI and adopt a pedagogical framework that emphasises AI literacy, ethical guidance, and equitable access to AI tools.
Port-Hamiltonian models describe physical systems by separating stored energy, dissipation and external inputs. Learning such models from data requires a choice of representation and fitting method. We compare using neural networks, analytic expressions and combinations of the two for representing the different components of the port-Hamiltonian system, and compare fitting the models with gradient-based optimisation or sparse regression. Testing on simulations of mechanical and electrical systems, with and without added noise, we present prediction accuracy and computational cost of the different approaches.
Continual learning in physical AI differs from conventional continual learning because small per-step policy errors can accumulate over a trajectory. Each deviation may move the agent outside the training distribution, increase subsequent prediction errors, and ultimately cause closed-loop task failure. This work introduces Dynamics-Risk Adaptive Plasticity (DRAP), a replay-free method that estimates the historical importance of adaptable model tensors from sample-level action gradients weighted by local trajectory-amplification risk. A ridge-regularized local linear model is fitted to expert state-action transitions, and the largest singular value of its state-transition matrix provides a policy-independent, Lyapunov-inspired estimate of one-step perturbation amplification. After each task, risk-weighted squared gradients are accumulated in a tensor-level importance memory. During subsequent tasks, DRAP uses normalized cumulative importance to scale the effective AdamW learning rate of each tensor, immediately reducing the plasticity of components that supported previous behavior at dynamically sensitive trajectory points. We instantiate DRAP on a fixed KappaTune-selected subnetwork of OpenVLA and evaluate replay-free sequential adaptation across the LIBERO Spatial, Object, and Goal suites. Compared with standard AdamW fine-tuning and EWC, the results show substantially improved retention of previously learned behaviors while preserving strong new-suite acquisition.
Yan Lin, Jilin Hu, N. M. Anoop Krishnan, Morten M. Smedskjaer
Amorphous (disordered) materials require simulation cells with at least hundreds to thousands of atoms to accurately capture their diverse local atomic environments, compared to crystalline materials that can be described by unit cells containing a few to hundreds of atoms. To advance the design of amorphous materials with desired properties and facilitate the exploration of their vast design space, generative inverse design has emerged as a promising approach. It aims to directly output materials with properties closely aligned with the desired ones using probabilistic generative models conditioned on desired properties, which can be more resource efficient than the traditional trial-and-error approach. However, due to the inherent stochasticity of probabilistic generative models, when element assignments are unconstrained, a large portion of generated materials may be charge unbalanced, and existing methods either fix the composition in advance or discard charge unbalanced samples after generation. In this work, we propose AMGenC, a new generative inverse design method for amorphous materials that can guarantee the generation of formally charge balanced samples, with minimal additional computational overhead and without sacrificing inverse design accuracy. AMGenC achieves this through an element noise that gives the generation process a starting point centered around charge balance, and the combination of a per-step soft projection and a final discrete projection for steering the elements toward exact charge balance throughout the generation. We perform extensive experiments on two amorphous materials datasets. Experimental results provide evidence that AMGenC achieves its design goal.
Gautam Chandrasekaran, Jason Gaitonde, Ankur Moitra, Arsen Vasilyan
The low-degree algorithm is a cornerstone in computational learning theory. For product or Gaussian distributions, it shows that efficiently learnability follows from Fourier concentration. However, a longstanding obstacle towards building such a theory over nonproduct distributions is that we can no longer rely on having closed-form expressions for a good basis of orthogonal functions. This hints that the analysis of the low-degree algorithm might be brittle to the underlying distributional assumptions. We refute this intuition by showing that the low-degree algorithm provably succeeds for a large class of graphical models under mild high-temperature conditions. As an application, for nearly every Ising model that is known to rapidly mix, we obtain learning algorithms for every function class for which the Fourier approach succeeds for product distributions (e.g. low-depth circuits, halfspaces, intersections, monotone, among others) with no significant loss. Our framework is based on a strikingly clean connection with the coordinate-by-coordinate localization scheme of Chen and Eldan introduced for establishing rapid mixing in high-temperature models, as well as other analytical transference principles to product distributions.
Multi-agent systems offer significant advantages in terms of flexibility and redundancy, enabling the efficient distribution of complex tasks among multiple robots. However, their deployment requires advanced control strategies to ensure optimal cooperation between autonomous agents and human operators. We propose a modification of the global connectivity maintenance algorithm to incorporate measurements taken in agent's local frame, using sensors with limited fields of view. This algorithm, responsible for the autonomous behavior of the multi-robot system, is combined with different adaptive supervision strategies, allowing the user to exert control at varying scales over the entire group. (i) Single Agent Control (S): The operator directly controls a single robot, (ii) Pinning Control (P): The operator imposes constraints on multiple robots to influence the group, (iii) Centroid Control (C): The operator acts on the system's center of mass to steer the entire fleet. In conjunction with the connectivity maintenance algorithm, these methods ensure compliance with inter-agent constraints while providing haptic feedback to the user regarding the system's connectivity state. The effectiveness of these approaches was evaluated through a user study, comparing performance with and without haptic feedback across multiple scenarios tailored to the different control modes.
Adrian Cosma, Stefan Ruseti, Emilian Radoi, Mihai Dascalu
Subword tokenization introduces a computational layer in language models, where many distinct token sequences decode to the same surface form while preserving meaning, yet induce different internal computations. Despite this non-uniqueness, language models are typically trained using a single canonical deterministic tokenization. In this work, we use non-canonical subword variants as a strictly meaning-preserving form of data augmentation. We introduce a lightweight training architecture that conditions canonical next-token prediction on sampled subword variants via an auxiliary causal encoder and block-causal cross-attention, without modifying the training objective or token interface. In data-constrained pretraining, augmentations with subword variants consistently delay overfitting under repeated data exposure and reduce held-out next-token loss across evaluation datasets. In multilingual fine-tuning, we find that the effectiveness of training with auxiliary subwords depends on tokenizer quality: gains are strongest when canonical tokens are highly compressed and diminish when the tokenizer already over-fragments the input.
Andrey Ignatov, Georgy Perevozchikov, Radu Timofte, Dong Zhang, Zhao Ran, Yang Zhang, Xiaochen Li, Shichang Ju 等 24 位作者
On-device RGB photo enhancement is a popular task that is needed for quality improvement of photos captured with mobile devices as well as for retouching of images acquired through other sources. This creates a need for efficient deep learning models for this problem that are not only performant but can also be deployed on constrained mobile hardware. In this Mobile AI challenge, we address this problem and propose participants to design fast solutions that can perform comprehensive enhancement of RGB photos while running on popular smartphone GPUs from Qualcomm and Arm. For this, the participants were provided with a large-scale DPED dataset consisting of RGB image pairs captured with an old iPhone 3GS smartphone and a professional Canon 70D DSLR camera. The runtime of all models was evaluated on the Snapdragon 8 Elite Gen 5 and Dimensity 9500 chipsets with the Adreno and Mali GPUs, respectively. Top solutions proposed in this challenge are able to enhance Full HD resolution RGB images on both platforms under 300 milliseconds. A comprehensive description of the models developed in the challenge is provided in this paper.
World Action Models (WAMs) improve robotic manipulation by jointly modeling visual dynamics and robot actions. However, most existing WAMs model dense short-horizon visual dynamics, capturing local interactions but providing limited long-range task context. Extending prediction horizons increases uncertainty and computation while entangling task-level evolution with fine-grained local dynamics, obscuring their dependencies and distinct roles in action generation. We propose HiLo-WAM, which decouples long-horizon task evolution from local visual dynamics while jointly modeling their interaction with robot actions. A sparse long-horizon visual stream captures historical task context and future evolution, while a dense local dynamics visual stream models short-horizon robot-object interactions. The two streams operate at different temporal scales within a unified dual-DiT architecture and guide actions through structured cross-stream attention. Progressive inference further reduces unnecessary computation through stream-wise partial denoising, joint denoising, and dynamic skipping. Experiments demonstrate strong long-horizon manipulation performance: HiLo-WAM achieves a 93.70% average success rate on RoboTwin 2.0 and a 17.43 progress score on RoboDojo long-horizon tasks, with robust in-domain and OOD performance on the Fourier GR-3 robot. Ablations confirm the complementary contributions of long-horizon task evolution and local interaction dynamics, while temporal-scale analyses highlight the importance of balancing temporal coverage and resolution. Progressive inference further achieves a 2.93x speedup while improving performance.
Differential privacy requires that algorithms be stable to the change of any record in their input, even to an extreme outlier. Private algorithms thus commonly introduce noise scaled to the worst-case possible influence of any single record. This work studies how to build differentially private algorithms that can effectively tailor their noise to the typical case rather than the worst case. We introduce the general \emph{propose-filter-release} (PFR) framework, which, by privately filtering its input, turns a mechanism that protects the addition or removal of a \emph{typical} record into one that is differentially private in the standard sense, on \emph{every} input. We show how to instantiate PFR with a novel filtering step to obtain a general meta-algorithm. Given only a concave friendliness score (which measures how typical a record is with respect to a dataset) and a release mechanism that is friendly-DP (that is, private conditioned on the changed record being typical of the remaining data), it guarantees differential privacy on sufficiently large datasets. The FriendlyCore [TCK+22] and Propose-Test-Release [DL09] algorithms can be viewed as instantiations of our general approach. We illustrate the generality of PFR by instantiating it for scalar statistics, principal subspace estimation with a dimension-independent sample size, the KL divergence of user histograms, the effective resistances in a resistor network, and treatment-rule selection.
Infrared and visible image fusion is a pivotal technology in low-altitude Unmanned Aerial Vehicle (UAV) reconnaissance missions, enabling robust target detection and tracking by integrating thermal saliency with environmental textures. However, the advancement of fusion algorithms is hindered by a critical evaluation bottleneck. In this paper, we identify a systematic failure in traditional no-reference metrics (specifically Statistics-based and Gradient-based metrics) within complex low-light environments, termed as ``Noise Trap''. It is mathematically proven that these metrics are positively correlated with high-frequency sensor noise, paradoxically assigning higher scores to degraded images and misguiding algorithm optimization. To resolve this dilemma, this paper proposes the Weber-inspired Local Contrast (WLC) metric. Grounded in the psychophysical principle of Weber's Law, WLC shifts the evaluation paradigm from global statistical distribution to local semantic contrast. By leveraging infrared priors, it effectively decouples target saliency from global background noise. Extensive experiments on the DroneVehicle dataset demonstrate that WLC exhibits high ``Semantic Discriminability'' in distinguishing thermal targets from background clutter. Furthermore, it achieves remarkable computational efficiency, thus, establishing itself as a reliable and real-time standard for intelligent UAV systems.
Matrix factorization provides a simple model for studying the training dynamics of neural networks. Recent studies of gradient flow under small initialization have analyzed how trajectories escape from a neighborhood of the origin and approach their first nonzero stationary point. In this paper, we study continuous-time dynamics that applies a finite number of Newton-Schulz iterations to the normalized matrix gradient (Muon). We show that the number of Newton-Schulz steps can change the rank selected during the early stages of training and allow the resulting trajectory to bypass the first nonzero stationary point approached by gradient flow. Under an additional residual-inertia condition, we prove that bypass occurs for all sufficiently large finite Newton-Schulz depths and provide an explicit sufficient threshold. We also construct an example in which the bypass threshold is four.
We consider monotone submodular maximization subject to a matroid constraint. The seminal continuous greedy algorithm of Calinescu, Chekuri, Pál, and Vondrák~[SICOMP'11] achieves the tight approximation of $(1-1/e)$. Since then, a line of works by Badanidiyuru and Vondrák~[SODA'14], Buchbinder, Feldman, and Schwartz~[SODA'15 \& MOR'17], Kobayashi and Terao~[ICALP'24], Buchbinder and Feldman~[FOCS'24 \& SICOMP'25], and Buchbinder and Feldman~[STOC'25] has developed efficient $(1-1/e-\varepsilon)$-approximation algorithms for this problem. We present a combinatorial randomized $(1-1/e-\varepsilon)$-approximation algorithm that requires $\tilde{O}_{\varepsilon}(n)$ independence-oracle and value-oracle queries, where $n$ is the number of elements in the matroid. This is the first $(1-1/e-\varepsilon)$-approximation algorithm with both independence-oracle and value-oracle query complexities nearly-linear in $n$ and polynomial in $1/\varepsilon$. To achieve this, we develop a new local search algorithm, which we call \emph{protected local search}, based on the potential function of Buchbinder and Feldman~[FOCS'24 \& SICOMP'25].
We give an improved algorithm for weighted directed planar diameter that runs in $\widetilde{O}(n^{3/2})$ time. This improves upon the $\widetilde{O}(n^{5/3})$ time algorithm for weighted directed planar diameter of Gawrychowski, Kaplan, Mozes, Sharir, and Weimann [SIAM J. Comput. 2021] and the recent $\widetilde{O}(n^{8/5})$ time algorithm for unweighted undirected planar diameter of Fredslund-Hansen, Mozes, and Weimann [SOSA 2027]. The main new result is an improved data structure for computing the farthest vertex when given feasible planar distances to the vertices on the outer face. The critical insight is the fact that normalized distances to the vertices of a face behave like pseudolines, for which we can leverage range searching and upper envelope data structures. Using the farthest vertex data structure, we are able to compute all vertex eccentricities and diameter in $\widetilde{O}(n^{3/2})$.
For non-stationary tethered multirotor UAVs in real-world conditions, simulating the forces imposed on the drone by the aerodynamic drag of the tether becomes crucial, with online use cases placing a hard bound on the maximum solve time. In previous work, a quasi-analytical catenary tether model reached a mean solve time of 0.51 ms using a general-purpose root finder, but without any worst-case guarantees or proven convergence. In this work, we reformulate the inner solver by reducing the catenary boundary-value problem to a single transcendental equation in one well-conditioned unknown. We derive a closed-form bracket and prove monotonicity and convexity as well as existence and uniqueness of the root, which together guarantee convergence of the solver. We further propose a two-regime initial guess which approximates the true root within 3.4 % and reduces the mean iteration count by 69.2 % to 2.24 compared to the textbook initialization. Building on the hybrid root-finding method rtsafe (Newton-Raphson with bisection fallback giving bounded iteration counts), we implement a specialized variant that exploits the problem structure to omit unnecessary checks while retaining correctness, which gives up to 1.37 times speedup. With the proposed solver the full tether model achieves a nearly constant solve time of 4.0 us on average and 4.6 us at worst, a 68 times speedup over an optimized re-implementation of the previous method, while agreeing with it to a relative deviation of 8.7e-9. Because the reformulation leaves the underlying physical model untouched, the experimental validation of the previous work carries over unchanged. We further demonstrate its suitability for embedded, resource-constrained platforms with a Lua implementation running directly in ArduPilot on a drone's flight controller, where it stays well inside the scheduling budget with a mean solve time of 0.74 ms.