Science & Mathematics

As cognitive radars evolve towards the end-to-end processing of one-dimensional complex baseband sequences, deep networks face severe adversarial threats. However, existing attacks encounter dual limitations in practical electronic warfare: low cross-architecture transferability and severe vulnerability to physical channel distortions, which degrades their tactical reliability. To overcome these bottlenecks, we propose a physical prior-driven Segmented Spatio-Temporal Attack (SSTA). First, a global-local feature decoupling segmentation mechanism interrupts the adversarial gradients' dependence on long-range sequence coherence, bridging the cross-architecture feature gap. Second, moving beyond static norm constraints devoid of physical semantics, we abstract channel distortions into differentiable spatio-temporal operators, integrating them into momentum iterations via an Expectation over Transformation (EoT) strategy. Comprehensive cross-evaluations across 9 heterogeneous models spanning CNNs, RNNs, and Transformers demonstrate that SSTA outperforms the state-of-the-art baseline by 10.36% in Average Black-Box Attack Success Rate. Furthermore, baseband equivalent simulations confirm that the generated waveforms survive extreme physical distortions and, after matched filtering, achieve zero main-lobe attenuation (0 dB) with noise floor lift strictly within Constant False Alarm Rate tolerances. SSTA successfully unifies digital-domain deception and physical-domain fidelity, providing crucial support for CEW security assessment.

Online adaptation of the cornering stiffness keeps a model-based sideslip estimator valid as tires change, but competes with learned model correction for the same filter innovation. A corrector with enough parameters can absorb the innovation pattern that a stiffness change produces, and adaptation is suppressed while the fit improves. We propagate the stiffness sensitivities of the predicted measurements through the vehicle states and construct a corrector orthogonal to them. A null-space parameterization enforces the constraint without a penalty coefficient and preserves the static least-squares stiffness estimate on each identification segment. In full-vehicle simulation, the stiffness response of the unconstrained corrector declines as its parameter count grows, whereas the orthogonal corrector responds at least as fully as the uncorrected filter at all sizes and lowers sideslip error by 12.7% to 22.0%. In a simulated drive with a stiffness step, the orthogonal corrector adapts as quickly as the uncorrected filter and lowers sideslip error during and after the transient. On public real-vehicle data, the 430-parameter unconstrained corrector loses most of its response to deliberate offsets of the filter's nominal stiffness, whereas the orthogonal corrector of the same size retains most of it, with a sideslip error slightly above the uncorrected filter's.

LLM agents have become capable kernel engineers on mainstream GPU stacks, but they struggle on emerging accelerators such as Ascend NPUs, whose programming model is barely represented in pretraining data. Recent NPU agents address this gap largely through experience: they accumulate memory from their own generation and optimization trials and reuse it on later tasks. We argue that experience alone is not enough for kernel generation. An agent can only remember what it has tried, and it rarely tries a mechanism it does not know. As a result, such memory offers little help when a new operator calls for a different mechanism, and even familiar operators raise unseen situations as optimization proceeds. We present ASCENDEVOLVE, which grounds every step of an evolutionary kernel search in a large external knowledge base built from platform documentation, toolkit headers, and operator repositories. Because this corpus far exceeds any context window, ASCENDEVOLVE indexes it and routes each agent to a small, task-specific slice of evidence instead of the corpus itself. The retrieved knowledge seeds diverse implementation strategies, guides repair when a candidate fails, and constrains how strong candidates are recombined. On 53 Ascend C operators from CANN-Bench spanning four difficulty levels, ASCENDEVOLVE achieves an overall score of 71.39, improving over Reflexion and OpenEvolve by 11.6% and 17.2%.

When unique pretraining data is scarce, models see the same tokens many times and are thought to memorize. Random-token replacement, an input-corruption augmentation, is one remedy reported to lower validation loss, but a lower loss alone does not reveal which source of error it reduces. On a controlled source whose entropy rate is known in closed form, we show that replacement shrinks predictions toward the corpus average. We also introduce a decomposition that separates validation loss into approximation, estimation, and memorization terms. This shrinkage view predicts that replacement's bias cost needs no memorization but its benefit does. Memorization raises validation loss after its minimum, so we report the effect at two points, the minimum validation loss and the end of a fixed budget. Where replacement helps, it reduces this rise by about 60%. At the end of the budget, it turns from harmful to helpful as the controlled source becomes less predictable; at the minimum, it helps at no predictability level under the fixed recipe. On Korean and Japanese web text, replacement removes about a third of the loss rise after the minimum by the end of the budget, but its effect at the minimum is much smaller. Across ten real corpora, replacement lowers the final loss on nine. It harms only the census corpus, program-generated JSON that is the most redundant of the ten and much more redundant than any of 64 further prose and code corpora we measure.

Aiming to modify textual content while preserving the original style, Scene Text Editing (STE) has significant practical value in many applications. STE typically requires paired images before and after editing for training. However, recent approaches rely heavily on synthetic paired data and complex disentanglement strategies. They struggle to faithfully capture the diversity and complexity of natural scenes, often producing artifacts or hallucinations. In this work, we challenge the common practice and investigate whether STE can be driven by turning each real sample into its own paired supervision. Concretely, we explore multiple ways to disrupt the original image (e.g., Crop, Shuffle, Mask) to construct self-paired training data, and build a strong baseline (TextRIRO}) upon a conditional diffusion architecture. Our experiments show that combining character-column shuffling with image cropping (Shuffle&Crop) effectively destroys text semantics while preserving key style cues, enabling the model to learn editing behaviors directly from the real text image. With this concise yet real-oriented design, TextRIRO achieves promising performance in both accuracy and visual realism across real-world benchmarks, substantially mitigating the synthetic-to-real domain gap. Furthermore, we leverage TextRIRO to build TextRIRO-3M, a large-scale realistic dataset for long-text recognition by concatenating edited and original images. Experimental results show that training recognition models with TextRIRO-3M significantly improves recognition accuracy, demonstrating that TextRIRO provides highly useful training resources for downstream tasks. Overall, TextRIRO lifts STE to realistic, reliable, and widely applicable new levels. Code is available at https://github.com/YesianRohn/TextRIRO.

We study adaptive prefix-length selection for reliability-ordered coded transmission over $N$ coordinates, using only the $K$ most reliable, to balance age of information (AoI) against throughput. An additive-increase/decrease (AID) prefix-walk controller updates the prefix length from the last decoding outcome alone, at $O(1)$ per-slot cost with no channel estimation, inducing an irreducible birth--death chain whose mean drift fixes a unique balance point $K^\dagger$ (largest $K$ with success probability $\ge\tfrac12$), around which the stationary distribution concentrates geometrically. We derive this distribution in closed form via detailed balance and obtain exact steady-state AoI and goodput via renewal-reward analysis. Simulations on a $64$-coordinate polar code over a binary symmetric channel (BSC) confirm these predictions to within $0.3\%$. Relative to a genie-aided upper bound with perfect channel knowledge, we further quantify the goodput cost of adapting from a single feedback bit alone.

While feed-forward models excel in static 3D geometry estimation, extending them to dynamic 4D scenes requires modeling visual geometry as a causally evolving state. Current methods typically rely on unordered temporal aggregation, which lacks the directional structure of physical time. Furthermore, existing supervision often treats geometry and motion as disjoint objectives, failing to exploit their inherent physical coupling. Consequently, they lack a unified constraint to effectively supervise temporal state transitions, leading to inconsistent 4D scene representations. To address this, we propose a feed-forward framework for causal 4D visual geometry learning from monocular videos. At its core, Causal Spatiotemporal Mamba augments temporal aggregation with directional state propagation. Through complementary Temporal-Spatial and Spatial-Temporal Scans, CSM continuously propagates geometry-aware states across frames to model spatiotemporal evolution. To align this causal state evolution with observable dynamics, we introduce Unified Motion Supervision. Rather than treating motion as an independent objective, UMS leverages geometry-aware predictions from the camera and depth heads to construct a unified forward motion field that is consistent with the underlying 3D structure. This geometry-grounded supervision explicitly constrains inter-frame state transitions, enabling stable states propagation across frames. Extensive evaluations on dynamic benchmarks demonstrate state-of-the-art performance across video depth, camera pose, and optical flow estimation. These results validate that the synergy between the directional state propagation of Causal Spatiotemporal Mamba and Unified Motion Supervision effectively captures continuous scene evolution, significantly reducing temporal drift and reinforcing spatial-temporal consistency in 4D representation learning.

Existing reasoning evaluations typically provide task-relevant information to models as available premises, rarely examining concurrently how models discover evidence autonomously and how information presentation within narratives guides or obscures judgment. This paper proposes the WORTH Benchmark: models read original mystery narratives without clue annotations, autonomously select key clue sentences, identify case participants, and explain their reasoning process. The narrative materials are designed by professional authors such that evidence facilitating reasoning coexists with narrative arrangements that delay the revelation of truth. We report a pilot experiment under full-story conditions across two episodes, conducting a total of 70 formal runs on models, of which 67 runs are content-scorable. Scoring separately records hits on author-designated key clue sentences and participant selections; natural language explanations are used for case diagnosis and are not scored independently. The results show that clue hits and participant judgments are not synchronized; across 37 content-scorable runs in Episode 02, 31 runs simultaneously selected the same set of incorrect participants, while adjacent suspicion-oriented and exoneration-oriented sentences were selected 25 times and 0 times, respectively. These phenomena illustrate the diagnostic value of component-wise analysis and suggest that not-fully-cooperative informational relationships may influence evidence selection and judgment. This study only implements full-story conditions for two episodes, and does not establish stable model rankings or infer general mechanisms on this basis; human player records have not yet been cleaned, and this version does not report human-model comparisons.

As model parameters scale up, sparsely activated Mixture-of-Experts (MoE) approaches have become essential for model scaling. However, mainstream models currently adopt hierarchical architectures, where experts in different layers, although topologically independent, exhibit substantial similarity and redundancy in their stored content. Compared to the hierarchically arranged \textbf{Local Expert} in existing mainstream models, we hypothesize that inter-layer shared \textbf{Meta Expert} hold greater potential. To this end, we conduct a multi-dimensional empirical comparison between Local and Meta Experts, and find that models incorporating Meta Experts exhibit lower parameter redundancy, together with lower cross-entropy loss and higher downstream task accuracy. With the activated quantity and the expert granularity held fixed, \textbf{our model matches the performance of Vanilla MoE using only 70--80\% of the experts}, substantially improving the model's scaling potential. Beyond removing inter-layer redundancy among experts and improving information storage efficiency, our theoretical analysis further shows that, compared with Local Experts, Meta Experts provide hidden states with more flexible residual pathways, thereby improving information retrieval efficiency.

The open-loop minimum-energy control (MEC) problem asks for control inputs that minimize the control energy while ensuring the terminal state reaches a desired value. In this paper, we study the open-loop MEC problem for stochastic linear time-invariant systems. We consider a variety of stochastic constraints that enforce the terminal error to be \emph{small}, and show that Stochastic MEC (SMEC) problem can be formulated as a QCQP. We obtain the optimal solution for SMEC and show that it generalizes the well-known Deterministic MEC problem by introducing novel stochastic variants of controllability and Gramian matrices and show that there exists a fundamental lower bound on the optimal control energy which cannot be overcome by increasing the time horizon of the problem. We then extend the formulation to systems with unknown dynamics using maximum-likelihood estimation and conformal calibration, and compare these approaches with direct sample-based estimation that do not incorporate structural information of SMEC problem into account. Further, with the help of bias-variance analysis, we show when incorporating structural information proves to be better than direct sample based approach. Finally, we establish finite-sample high-probability upper bounds on optimal-cost sub-optimality and original constraint-violation probability under the data-driven controller, quantifying their dependence on the number of experiments, number of samples per experiment, system dimension, input sequence dimension, and noise-to-signal ratio. Using simulations, we validate the theoretical results numerically.

Diffusion language models (DLMs) are emerging as a promising paradigm for code generation, offering the potential for fast, parallel decoding. However, generating complex programs remains challenging, as their interdependent components must maintain consistent interfaces, data flows, and shared assumptions. Aggressive parallel decoding can compromise these dependencies and undermine program correctness, while conservative decoding sacrifices efficiency. To address this trade-off, we propose planning program decomposition before implementation to coordinate interdependent units during parallel generation. We introduce Self-Decomposing Diffusion for Code (SDDC), a novel framework that decomposes complex programs and implements their units in parallel, entirely through diffusion. SDDC first generates a contract specifying the program's decomposition and inter-unit dependencies, then uses it to guide coordinated parallel implementation. Across five benchmarks and two 7B diffusion backbones, SDDC substantially improves the accuracy--latency trade-off, raising pass@1 by up to 31.1 percentage points while decoding 7.5--13.7$\times$ faster than the base models, and outperforming a fine-tuning baseline by up to 23.5 points with lower latency.

Empathetic interaction involves two distinguishable capacities: representing another person's emotional state (cognitive empathy) and generating an appropriate response to that state (affective empathy). We apply this distinction to examine how emotion-related information is internally organized, selectively attended to, and carried through response generation in Llama-3.2-3B-Instruct across 10 emotion categories from the EmpatheticDialogues dataset. Layer-wise linear probing revealed a broad middle-layer region of peak emotion-category decodability, with the layer-11 L2 probe achieving 63.6% held-out accuracy against a 10% chance level and a 54.6% TF-IDF lexical baseline. During response generation, emotion-related user tokens received 1.89 times as much attention per token as other utterance tokens, concentrated across layers 10-15. Target-emotion alignment then decreased from a mean cosine similarity of 0.239 for input representations to 0.125 for generated responses, with positive drift in 77% of examples and the largest shifts for angry and furious. Emotion-category representation, attention allocation, and response-level alignment therefore emerge as distinguishable components of model processing that can be analyzed through a functional cognitive-affective empathy framework. These findings provide a foundation for monitoring emotion representations during generation and leveraging models' existing affective structure to support more naturally empathetic responses without relying on external prompting or explicit emotion conditioning.

Feed-forward Gaussian reconstruction from sparse posed monocular frames requires reasoning over observations that vary jointly in viewpoint and time. Existing methods either predict Gaussian primitives from observation-aligned features or aggregate multi-frame information through compact latent queries. However, the former tightly couples Gaussian allocation to individual frames, while the latter does not explicitly structure observed evidence according to its temporal relation to the requested timestamp. Consequently, evidence across spatial scales, viewpoints, and timestamps can be difficult to align and integrate. We present \textbf{HiQGS}, a query-based hierarchical framework for feed-forward Gaussian scene reconstruction from sparse monocular frames. HiQGS introduces a \textbf{Hierarchical Spatiotemporal Encoder} that organizes multi-resolution geometry-appearance visual features according to image location, observation time, and camera pose, thereby preserving complementary appearance and structural cues. Our \textbf{Time-Adaptive Decoder} use target timestamp queries the resulting hierarchical representation to retrieve relevant spatiotemporal evidence and predicts the corresponding Gaussian scene state. Experiments on static and dynamic scene reconstruction benchmarks demonstrate strong rendering quality and geometric accuracy, validating the effectiveness of hierarchical visual encoding and target-time-aware Gaussian querying.

Offline reinforcement learning is fundamentally limited by the coverage of the available data, while collecting additional trajectories through online exploration may be costly, unsafe, or infeasible. We study whether this limitation can be overcome without directly interacting with the underlying environment. Motivated by practical settings such as collaborator-mediated simulation, where a collaborator can provide information complementary to the offline data, we introduce query-based collaborative reinforcement learning to study how to acquire this information efficiently. The learner starts with a fixed offline dataset and adaptively queries state-time pairs; the collaborator samples an action according to a fixed, possibly suboptimal policy, and the simulator returns the corresponding reward and next state. For finite-horizon tabular problems, we derive an instance-dependent information-theoretic lower bound on the additional queries required to identify an $ε$-optimal policy and develop a local quadratic approximation. Guided by this characterization, we develop an adaptive query-allocation algorithm whose query complexity nearly matches the local benchmark under suitable conditions. Experiments on multiple synthetic and semi-synthetic environments demonstrate the empirical efficiency of the proposed method.

AI memory personalizes assistants, yet users want some disclosed information forgotten. We characterize the negative space of AI memory, where protection should take precedence over potential future personalization benefits. From 179 incidents reported by 146 users, we developed a taxonomy of 15 information categories users want excluded from memory, revealing sensitivity concerns beyond conventional taxonomies. We operationalize this taxonomy in FENCE, a policy-level memory gate that automatically applies user-selected category-based rules to subsequent conversations, preventing information from protected conversations from entering AI memory by default while allowing case-by-case overrides. In a within-subjects study (N=15), participants described FENCE as making memory governance more usable, interpretable, and trustworthy than conventional post-hoc management. Our findings demonstrate how taxonomy-based rules can potentially support user-defined memory boundaries. We call for collective efforts to establish policies governing what AI should not remember, rather than leaving protection to individual retrospective management.