arXiv:2605.17723v1 Announce Type: new Abstract: Residential batteries increasingly serve two roles: they can earn money by arbitraging wholesale prices and providing grid services, and they provide backup power during outages. This dual use creates a basic tradeoff between earning market value and preserving outage readiness. Coordination across many batteries can help, but a provider cannot treat the fleet as a single virtual battery when each household is promised its own backup protection. We compare standalone control, in which each home is dispatched independently, with pooling, in which homes are coordinated while each battery retains its own state of charge and household-specific backup requirement. Both regimes are implemented as model predictive control problems with 15-minute decision intervals and evaluated using household telemetry together with ERCOT market inputs. The empirical design focuses on the 543 homes in our sample that can support at least one backup product in standalone operation and studies backup caps ranging from 2 to 24 hours. Lower caps relax backup obligations, while the 24-hour cap coincides with assigning each home its own longest feasible backup tier. Pooling remains beneficial in this service-constrained setting, but its value declines smoothly as backup obligations tighten. Standalone firm margin ranges from \$11.06 per home per week at the 2-hour cap to \$10.79 at the 24-hour cap, while pooling benefit falls from \$1.49 to \$1.27 per home per week. Relative to standalone firm margin, pooling is worth about 13.5% at the 2-hour cap and about 11.8% at the 24-hour cap. Coordination therefore still helps after preserving household-level backup guarantees, but its value declines as backup obligations tighten.
Science Journals
arXiv:2605.17727v1 Announce Type: new Abstract: Frozen vision-language embeddings contain signals at multiple semantic resolutions, from object identity to attributes, relations, and full-caption meaning, but they expose these signals through a fixed-length vector interface. We study whether embedding length can be turned into a controllable semantic access interface. We propose \textbf{GraSP-VL}, which learns a shared near-orthogonal prefix transform over frozen VLM embeddings. GraSP-VL instantiates a \textbf{Semantic Matryoshka} interface: short prefixes are assigned coarse semantic roles, while longer prefixes progressively expose finer language-grounded distinctions. Because the transform is shared across image and text embeddings and preserves full-dimensional geometry, prefix behavior changes without rewriting the original VLM space. On a 20,147-example COCO/Flickr30K annotation pool, GraSP-VL reaches a staircase score of 53.01 and hard-negative selectivity of 89.76, while keeping full-space drift below $10^{-6}$. It also transfers to SugarCrepe-clean with 86.03 object accuracy and 11.96 mean external emergence, and preserves full-dimensional zero-shot CIFAR-100 accuracy. These results show that frozen VLM embeddings can be reorganized into a truncatable semantic prefix interface rather than merely compressed.
arXiv:2604.26793v2 Announce Type: replace Abstract: Motivated by sensing modalities in modern autonomous systems that involve hardware-constrained spatial sampling over large arrays with limited coherence time, we develop a novel framework for rapid super-resolution multi-signal direction-of-arrival (DoA) estimation based on Hankel-structured sensing and data matrix decomposition of arbitrary rank, under both the $L_2$ and $L_1$-norm formulation. The resulting $L_2$-norm estimator is shown to be maximum-likelihood optimal in white Gaussian noise. The $L_1$-norm estimator is shown to be maximum-likelihood optimal in independent, identically distributed (i.i.d.) isotropic Laplace noise, offering broad robustness to impulsive interference and corrupted measurements commonly encountered in practice. Extensive simulations demonstrate that the proposed methods exhibit powerful super-resolution capabilities, requiring significantly lower SNR and achieving substantially higher resolution probability than recent competing approaches.
arXiv:2508.14422v4 Announce Type: replace Abstract: This paper introduces a dimension-decomposed geometric learning framework called Sliced Learning for disturbance identification in quadrotor geometric attitude control. Instead of conventional learning-from-states, this framework adopts a learning-from-error strategy by using the Lie-algebraic error representation as the input feature, enabling axis-wise space decomposition (``slicing") while preserving the SO(3) structure. This is highly consistent with the geometric mechanism of cognitive control observed in neuroscience, where neural systems organize adaptive representations within structured subspaces to enable cognitive flexibility and efficiency. Based on this framework, we develop a lightweight and structurally interpretable Sliced Adaptive-Neuro Mapping (SANM) module. The high-dimensional mapping for online identification is axially ``sliced" into multiple low-dimensional submappings (``slices"), implemented by shallow neural networks and adaptive laws. These neural networks and adaptive laws are updated online via Lyapunov-based adaptation within their respective shared subspaces. To enhance interpretability, we prove exponential convergence despite time-varying disturbances and inertia uncertainties. To our knowledge, Sliced Learning is among the first frameworks to demonstrate lightweight online neural adaptation at 400 Hz on resource-constrained microcontroller units (MCUs), such as STM32, with real-world experimental validation.
arXiv:2508.14769v2 Announce Type: replace Abstract: Federated distillation has emerged as a promising collaborative machine learning approach, offering enhanced privacy protection and reduced communication compared to traditional federated learning by exchanging model outputs (soft logits) rather than full model parameters. However, existing methods employ complex selective knowledge-sharing strategies that require clients to identify in-distribution proxy data through computationally expensive statistical density ratio estimators. Additionally, server-side filtering of ambiguous knowledge introduces latency to the process. To address these challenges, we propose a robust, resource-efficient EdgeFD method that reduces the complexity of the client-side density ratio estimation and removes the need for server-side filtering. EdgeFD introduces an efficient KMeans-based density ratio estimator for effectively filtering both in-distribution and out-of-distribution proxy data on clients, significantly improving the quality of knowledge sharing. We evaluate EdgeFD across diverse practical scenarios, including strong non-IID, weak non-IID, and IID data distributions on clients, without requiring a pre-trained teacher model on the server for knowledge distillation. Experimental results demonstrate that EdgeFD outperforms state-of-the-art methods, consistently achieving accuracy levels close to IID scenarios even under heterogeneous and challenging conditions. The significantly reduced computational overhead of the KMeans-based estimator is suitable for deployment on resource-constrained edge devices, thereby enhancing the scalability and real-world applicability of federated distillation. The code is available online for reproducibility.
arXiv:2605.17734v1 Announce Type: new Abstract: Equipping LLM agents with reusable skills derived from past experience has become a popular and successful approach for tackling complex and long-horizon tasks. However, such lessons are often encoded as textual guidance that remains largely advisory, lacking explicit mechanisms for when and how to intervene in the agent loop. To bridge the gap, we introduce HASP(Harnessing LLM Agents with Skill Programs), a new framework that upgrades skills into executable Program Functions (PFs). Rather than offering passive advice, PFs act as executable guardrails that activate on failure-prone states and modify the next action or inject corrective context. HASP is highly modular: it can be applied at inference time for direct agent-loop intervention, during post-training to provide structured supervision, or for self-improvement by evolving validated, teacher-reviewed PFs. Empirically, HASP drives substantial gains compared to both training-free and training-based methods on web-search, math reasoning, and coding tasks. For example, on web-search reasoning, inference-time PFs alone improve the average performance by 25% compared to (multi-loop) ReAct Agent, while post-training and controlled evolution achieve a 30.4% gain over Search-R1. To provide deeper insights into HASP, our mechanism analysis reveals how PFs trigger and intervene, how skills are internalized, and the requirement for stable skill library evolution.
arXiv:2508.15878v2 Announce Type: replace Abstract: Formal theorem proving (FTP) has emerged as a critical foundation for evaluating the reasoning capabilities of large language models, enabling automated verification of mathematical proofs at scale. However, progress has been constrained by limited datasets due to the high cost of manual curation and the scarcity of challenging problems with verified formal-informal correspondences. We propose leveraging theoretical computer science (TCS) as a scalable source of rigorous proof problems, where algorithmic definitions enable automated generation of arbitrarily many challenging theorem-proof pairs. We demonstrate this approach on two TCS domains: Busy Beaver problems, which involve proving bounds on Turing machine halting behavior, and Mixed Boolean Arithmetic problems, which combine logical and arithmetic reasoning. Our framework automatically synthesizes problems with parallel formal (Lean4) and informal (Markdown) specifications, creating a scalable pipeline for generating verified proof challenges. Evaluation on frontier models reveals substantial gaps in automated theorem proving: while DeepSeekProver-V2-671B achieves 57.5\% success on Busy Beaver problems, it manages only 12\% on Mixed Boolean Arithmetic problems. These results highlight the difficulty of long-form proof generation even for problems that are computationally easy to verify, demonstrating the value of TCS domains for advancing automated reasoning research.
arXiv:2508.16438v4 Announce Type: replace Abstract: Recent advances in large language models (LLMs) and dense retrievers have driven significant progress in retrieval-augmented generation (RAG). However, existing approaches face significant challenges in complex reasoning-oriented multi-hop retrieval tasks: 1) Ineffective reasoning-oriented planning: Prior methods struggle to generate robust multi-step plans for complex queries, as rule-based decomposers perform poorly on out-of-template questions. 2) Suboptimal reasoning-driven retrieval: Related methods employ limited query reformulation, leading to iterative retrieval loops that often fail to locate golden documents. 3) Insufficient reasoning-guided filtering: Prevailing methods lack the fine-grained reasoning to effectively filter salient information from noisy results, hindering utilization of retrieved knowledge. Fundamentally, these limitations all stem from the weak coupling between retrieval and reasoning in current RAG architectures. We introduce the Orchestrated Planner-Executor Reasoning Architecture (OPERA), a novel reasoning-driven retrieval framework. OPERA's Goal Planning Module (GPM) decomposes questions into sub-goals, which are executed by a Reason-Execute Module (REM) with specialized components for precise reasoning and effective retrieval. To train OPERA, we propose Multi-Agents Progressive Group Relative Policy Optimization (MAPGRPO), a novel variant of GRPO. Experiments on complex multi-hop benchmarks show OPERA's superior performance, validating both the MAPGRPO method and OPERA's design.
arXiv:2509.18103v3 Announce Type: replace Abstract: Research on the distribution of prime numbers has revealed a dual character: deterministic in definition yet exhibiting statistical behavior reminiscent of random processes. In this paper we show that it is possible to use an image-focused machine learning model to measure the comparative regularity of prime number fields at specific regions of an Ulam spiral. Specifically, we demonstrate that in pure accuracy terms, models trained on blocks extracted from regions of the spiral in the vicinity of 500m outperform models trained on blocks extracted from the region representing integers lower than 25m. This implies existence of more easily learnable order in the former region than in the latter. Moreover, a detailed breakdown of precision and recall scores seem to imply that the model is favouring a different approach to classification in different regions of the spiral, focusing more on identifying prime patterns at lower numbers and more on eliminating composites at higher numbers. This aligns with number theory conjectures suggesting that at higher orders of magnitude we should see diminishing noise in prime number distributions, with averages (density, AP equidistribution) coming to dominate, while local randomness regularises after scaling by log x. Taken together, these findings point toward an interesting possibility: that machine learning can serve as a new experimental instrument for number theory. Notably, the method shows potential 1 for investigating the patterns in strong and weak primes for cryptographic purposes.
arXiv:2605.17915v1 Announce Type: new Abstract: Surgical Video Question Answering (VideoQA) provides a promising paradigm for dynamic intraoperative interpretation, enabling real-time decision support and context-aware retrieval in clinical environments. Nevertheless, existing approaches are predominantly restricted to images or short clips, limiting their ability to model long-range procedural dynamics and causal dependencies across extended surgical workflows. To address this challenge, we propose SurgLQA, a unified long-horizon VideoQA framework for scalable surgical reasoning. This framework incorporates Faithful Temporal Consolidation (FTC), which leverages intrinsic temporal cues to construct compact long-range representations while preserving fine-grained temporal fidelity. Further, we develop Temporally-Grounded Multi-Policy Scaling (TMS), an adaptive test-time inference paradigm that strategically adjusts policy-level reasoning capacity within temporally grounded contexts. To facilitate systematic evaluation, we restructured a long-duration colonoscopy VideoQA benchmark, Colon-LQA, and conducted extensive experiments on Colon-LQA and REAL-Colon-VQA. Experimental results demonstrate that our approach achieves consistent performance gains in long-range reasoning with temporally grounded inference. Code link: https://github.com/RascalGdd/SurgLQA.
arXiv:2508.06670v2 Announce Type: replace-cross Abstract: By applying interpretable machine learning methods such as decision trees, we study how simple models can classify the Galois groups of Galois extensions over $\mathbb{Q}$ of degrees 4, 6, 8, 9, and 10, using Dedekind zeta coefficients. Our interpretation of the machine learning results allows us to understand how the distribution of zeta coefficients depends on the Galois group, and to prove new criteria for classifying the Galois groups of these extensions. Combined with previous results, this work provides another example of a new paradigm in mathematical research driven by machine learning.
arXiv:2605.00793v2 Announce Type: replace-cross Abstract: With the development of deep learning, medical image processing has been widely used to assist clinical research. This paper focuses on the denoising problem of low-dose computed tomography using deep learning. Although low-dose computed tomography reduces radiation exposure to patients, it also introduces more noise, which may interfere with visual interpretation by physicians and affect diagnostic results. To address this problem, inspired by Cycle-GAN for unsupervised learning, this paper proposes an end-to-end unsupervised low-dose computed tomography denoising framework. The proposed framework combines a U-Net structure for multi-scale feature extraction, an attention mechanism for feature fusion, and a residual network for feature transformation. It also introduces perceptual loss to improve the network for the characteristics of medical images. In addition, we construct a real low-dose computed tomography dataset and design a large number of comparative experiments to validate the proposed method, using both image-based evaluation metrics and medical evaluation criteria. Compared with classical methods, the main advantage of this paper is that it addresses the limitation that real clinical data cannot be directly used for supervised learning, while still achieving excellent performance. The experimental results are also professionally evaluated by imaging physicians and meet clinical needs.
arXiv:2605.17902v1 Announce Type: new Abstract: Stochastic-process-based degradation modeling is a core approach for estimating the distribution of remaining useful life (RUL); however, the selection of an appropriate stochastic process has not been sufficiently addressed. Existing model selection methods mainly rely on the statistical fit of the observed health indicator (HI) trajectory, but this approach may select a model that is inconsistent with the underlying degradation mechanism when the observation window is short or the signal is highly noisy. To address this issue, this paper proposes Literature-Anchored Stochastic Trajectory Retrieval-Augmented Generation (LAST-RAG). The proposed method uses both the observed HI trajectory and domain-specific context, and hierarchically conditions the candidate degradation model space based on theoretical and mechanical evidence retrieved from a local evidence bank. In addition, Rule-based Confidence Reasoning with Uncertain State (RCRUS) is introduced to prevent candidate models from being prematurely eliminated when hierarchical decisions are uncertain. Simulation-based experiments demonstrate that the proposed method outperforms statistical, prognostic, and uncertainty-aware baselines in both Wiener/gamma family classification and detailed degradation model classification. Ultimately, this study reframes degradation model selection from a purely statistical goodness-of-fit problem into a knowledge-conditioned decision-making problem that integrates observed data with domain knowledge.
arXiv:2401.14278v3 Announce Type: replace Abstract: Blockchain performance has historically faced challenges posed by the throughput limitations of consensus algorithms. Recent breakthroughs in research have successfully alleviated these constraints by introducing a modular architecture that decouples consensus from execution. The move toward independent optimization of the consensus layer has shifted attention to the execution layer. While concurrent transaction execution is a promising solution for increasing throughput, practical challenges persist. Its effectiveness varies based on the workloads, and the associated increased hardware requirements raise concerns about undesirable centralization. This increased requirement results in full nodes and stragglers synchronizing from signed checkpoints, decreasing the trustless nature of blockchain systems. In response to these challenges, this paper introduces Chiron, a system designed to extract execution hints for the acceleration of straggling and full nodes. Notably, Chiron achieves this without compromising the security of the system or introducing overhead on the critical path of consensus. Evaluation results demonstrate a notable speedup of up to 30%, effectively addressing the gap between theoretical research and practical deployment. The quantification of this speedup is achieved through realistic blockchain benchmarks derived from a comprehensive analysis of Ethereum and Solana workloads, constituting an independent contribution.
arXiv:2509.18150v2 Announce Type: replace Abstract: Multimodal Large Language Models (MLLMs) have demonstrated outstanding performance across a variety of domains. However, training MLLMs is often inefficient, as much of the computation is redundant due to the long input sequences from multimodal data and underutilized inter-layer operations. Notably, such redundancy is not static but varies across different stages of training. Building on this observation, we shift the focus to the training process itself and propose a training-efficient framework based on sparse representations, termed the Sparse Training Scheme (STS). Instead of applying a uniform sparsity strategy, STS adopts a stage-aware design that adapts to different sources of redundancy during training. Specifically, the framework consists of two complementary components: the Visual Token Compressor, which reduces the information load by compressing visual tokens during modality alignment, and the Layer Dynamic Skipper, which mitigates computational overhead by dynamically skipping unnecessary layers during instruction tuning. Our approach is broadly applicable to diverse MLLM architectures and has been extensively evaluated on multiple benchmarks, demonstrating its effectiveness and efficiency.
arXiv:2605.17900v1 Announce Type: new Abstract: Accurate Point of Interest (POI) attribute acquisition is essential for location-based services, yet traditional modular Interactive Voice Response (IVR) systems suffer from error accumulation and high maintenance overhead. We present DuIVRS-2, a large language model (LLM)-based end-to-end framework designed for large-scale POI attribute acquisition at Baidu Maps. To address the long-tail distribution of real-world interactions, our methodology first employs a finite state machine (FSM)-guided data augmentation strategy to synthesize a balanced and diverse training dataset. We then streamline dialogue management via a selective generation scheme combined with a Chain-of-Thought (CoT) mechanism, which ensures output stability and effectively eliminates hallucinations in industrial settings. To facilitate continuous policy refinement with minimal manual effort, we design a cooperative iterative learning framework that leverages a dual-evaluator voting system. Deployed in production for two months, DuIVRS-2 processed 0.4 million calls daily and achieved a 83.9\% Task Success Rate (TSR), outperforming its predecessor by 4 percentage points while maintaining a low reaction time of 130ms. This work provides a production-proven reference for developing robust, cost-effective LLM agents for large-scale industrial dialogue applications.
arXiv:2605.17759v1 Announce Type: new Abstract: To circumvent the inherent fidelity bottlenecks and optimization misalignment of VAE-based latent diffusion, pixel-space diffusion models have emerged as a compelling end-to-end paradigm. However, existing pixel diffusion models often struggle to balance computational efficiency with the preservation of high-frequency details. They frequently resort to patch-based compression or restricted local decoding, leading to a "spectral compromise" where high-frequency and fine-grained pixel information are suppressed. To address these challenges, we propose \textbf{FrequencyBooster}, a novel framework designed to empower pixel diffusion with full-frequency modeling capabilities without prohibitive overhead. The core of our method is a high-capacity decoder that specializes in extracting exhaustive high-frequency details and low-frequency semantics, the latter of which is derived from a Diffusion Transformer (DiT) backbone. Unlike prior works that sacrifice global context for local refinement, FrequencyBooster leverages high-dimensional feature representations to maintain global structural integrity while achieving superior pixel-level precision. Extensive experiments on ImageNet demonstrate the effectiveness of our approach: our model achieves a state-of-the-art FID of \textbf{1.60} at $256 \times 256$ resolution within only 320 epochs. Furthermore, at $512 \times 512$ resolution, FrequencyBooster attains an FID of \textbf{1.69}, significantly outperforming existing pixel-space and latent-space generative models.
arXiv:2605.17760v1 Announce Type: new Abstract: We give tolerant testers with sublinear query complexity in the adjacency-list model for Unique Games. Prior tolerant testers required structural assumptions such as expansion or clusterability. For Unique Games, the tester distinguishes instances whose optimum fraction of violated constraints is at most $\varepsilon$ from those whose optimum is at least $\rho$, for $0<\varepsilon<\rho<1$, assuming $\varepsilon\log n\lesssim\rho^4$. On instances with $n$ vertices and $m$ constraints, it uses $\widetilde O(\sqrt m\,\rho^{-13/2}+n\rho^{-2}/\sqrt m)$ queries. We also give a specialized tester for bipartiteness, the $Q=2$ transposition case of Unique Games. Exploiting its signed structure, the tester achieves substantially better tolerance and query-complexity guarantees than the generic Unique Games tester. Writing $\lambda=\rho/(1+\log(1/\rho))$, the bipartiteness tester distinguishes graphs that can be made bipartite by deleting at most an $\varepsilon$ fraction of edges from graphs in which every bipartition has at least a $\rho$ fraction of edges with both endpoints on the same side, assuming $\varepsilon\log n\lesssim\lambda^2$, using $\widetilde O(\sqrt m/\lambda^2+n/(\sqrt m\,\lambda))$ queries.
arXiv:2605.17761v1 Announce Type: new Abstract: Insider threats often reveal early anomalies through disruptions in behavioral statistics-such as altered recurrence patterns or short-versus long-term frequency shifts-rather than changes in event semantics. Yet, as the field has shifted from statistical modeling to log tokenization and deep sequential encoders, these statistical cues are weakened or lost, leaving current models insensitive to gradual and low-visibility insider behaviors.We propose MV-Gate, a multi-view behavior modeling framework that explicitly integrates statistical regularities with sequence semantics. MV-Gate constructs three aligned behavioral sequences: activity tokens, multi-scale status signals capturing recurrence patterns, and frequency-deviation signals describing short- vs long-term intensity differences. An anomaly-aware gating mechanism injects these statistical views into the attention computation, guiding the encoder to emphasize statistically irregular events. Experiments on CERT r4.2, CERT r5.2, and ADFA-LD show that MV-Gate achieves notable gains over classical, deep-learning, and domain-specific baselines, particularly for progressive, weak-signal threats. These results highlight the necessity of jointly modeling statistical and sequential evidence for robust insider-threat detection.
arXiv:2603.14942v3 Announce Type: replace Abstract: The Hawkes process models self-exciting event streams, requiring a strictly non-negative and stable stochastic intensity. Standard identification methods enforce these properties using non-negative causal bases, yielding conservative parameter constraints and severely ill-conditioned least-squares Gram matrices at higher model orders. To overcome this, we introduce a system-theoretic identification framework utilizing the sign-indefinite orthonormal Laguerre basis, which guarantees a well-conditioned asymptotic Gram matrix independent of model order. We formulate a constrained least-squares problem enforcing the necessary and sufficient conditions for positivity and stability. By constructing the empirical Gram matrix via a Lyapunov equation and representing the constraints through a sum-of-squares trace equivalence, the proposed estimator is efficiently computed via semidefinite programming.
arXiv:2605.17664v1 Announce Type: new Abstract: In this work, we extend a modified Anderson acceleration proposed in [Y. He, arXiv:2603.25983, 2026] to accelerate the Picard iteration for the Navier-Stokes equations. In this variant of Anderson acceleration, named AAg, the nonlinear residual--rather than the standard fixed-point iteration residual--is used to define the associated least-squares problem. We establish a convergence analysis for this method with any depth that shows how AAg accelerates convergence through the gain of the optimization problem, and obtain a sharp prediction of its linear convergence rate (a feature that is not part of the known theory for classical Anderson acceleration). Additionally, motivated by this sharp convergence prediction, we introduce an adaptive strategy that automatically selects the depth parameter. Results of several numerical experiments are given that illustrate the new theory and also demonstrate the effectiveness of the proposed adaptive approach. Comparisons of AAg to usual AA and nonlinear GMRES are also provided.
arXiv:2605.06506v2 Announce Type: replace Abstract: Language-model (LM) surprisal is widely used as a proxy for contextual predictability and has been reported to correlate with metaphor novelty judgments. However, surprisal is tightly intertwined with lexical frequency. We explore this interaction on metaphor novelty ratings using two different word frequency measures. We analyse surprisal estimates from eight Pythia model sizes and 154 training checkpoints. Across settings, word frequency is a stronger predictor of metaphor novelty than surprisal. Across training stages, the surprisal--novelty association peaks at an early stage and then falls again, mirroring a similarly timed increase in the surprisal--frequency association. These results suggest that the often-reported optimal LM surprisal settings may incorrectly associate contextual predictability with metaphor novelty and processing difficulty, whereas lexical frequency may be the major underlying factor.
arXiv:2605.17666v1 Announce Type: new Abstract: This work proposes an automatic real time lighting technique for procedurally generated isometric maps. The scenario is generated from a string seed and the proposed lighting system estimates the geometrical shape of the 2D objects as if they were 3D for further light interaction, therefore producing a 2.5D effect. We employ opacity maps to overcome an issue generated by the geometrical shape estimation. The solution is a coupled approach between the CPU and GPU. The produced visuals, gameplay and performance were evaluated by gamers, programmers and designers. Furthermore, the performance, in terms of frames per second, was evaluated over distinct graphics cards and processors and was satisfactory.
arXiv:2605.18689v1 Announce Type: cross Abstract: Virtually all aspects of many-body atomic physics are challenging: experiments are technically demanding, datasets have become enormous, and the memory and CPU requirements for classical simulation of generic quantum systems often scale exponentially with system size. Machine learning (ML) methods are already assisting in each of these areas and are poised to become transformative. Here, we focus on two specific applications of ML to cold-atom-based quantum simulators. These devices generally generate data in the form of images; we first showcase denoising of raw images and then identify solitonic waves in Bose-Einstein condensates. In both of these examples, we comment on the interplay between performance, model complexity, and interpretability.
arXiv:2605.17887v1 Announce Type: new Abstract: We propose OASIS, an outlier- and sink-aware technique built on inter-layer null signaling. As AttnResidual architectures introduce an additional depth-wise normalization channel, they improve inter-layer routing flexibility but also exacerbate attention sinks, activation outliers, and the resulting degradation in inference stability and quantization robustness. OASIS addresses this issue by introducing a Softmax1-based null space and coupling token-level null evidence to depth routing through an inter-layer null signal, thereby reducing sink-dominated routing and improving structural robustness. Theoretically, we show that the dual-normalization design of AttnResidual intensifies sink formation and quantization brittleness. Experimentally, we compare OASIS against five baselines on three real-world datasets and observe consistent improvements in both attention sink and post-quantization performance. Notably, OASIS achieves an average reduction of 9.26% in maximum infinity norm and 2.60% in average kurtosis across the evaluated settings, while lowering perplexity by 75.85% under W8A8 and improving GSM8K Pass@1 by 12.42% under W4A4.