arXiv:2607.01388v1 Announce Type: new Abstract: Multi-step symbolic reasoning is essential for robust financial analysis, yet most benchmarks neglect intermediate reasoning steps. FINCHAIN introduced verifiable Chain-of-Thought (CoT) evaluation but is limited to English. FINESSE-Bench includes a Russian block but relies on multiple-choice questions without step-level supervision. We present RusFinChain, the first Russian-language symbolic benchmark for verifiable CoT reasoning in finance. It spans 17 domains, 172 topics, and comprises 5,280 parameterized examples from executable Python templates, ensuring contamination-free evaluation. Each example includes a gold-standard reasoning chain with intermediate numeric values for automatic verification. We also introduce enhanced metrics: Fuzzy Numeric Alignment and Soft-Attention Alignment. We evaluate 8 open-weight LLMs on a stratified sample, generating 8,100 responses. Results reveal a substantial reasoning gap: models achieve Hard F1 of ~0.65 for step alignment, but only ~29% of final answers are correct. Our fuzzy and soft metrics show stronger correlation with final-answer correctness (Spearman rho approx 0.48) than the original ChainEval (rho approx 0.38-0.46), demonstrating superior diagnostic power. We release dataset, code, and evaluation framework to foster verifiable financial AI for the Russian-speaking community.
Science Journals
arXiv:2607.01533v1 Announce Type: new Abstract: We study hydrodynamic spin coupling in a two-rotor corral using DNS of 2D incompressible viscous fluid flow. An active rotor is driven at angular velocity W, and a nearby torque-free passive rotor selects an angular velocity w through hydrodynamic torque balance. The signed gear ratio Gamma=w/W distinguishes corotation from counterrotation, with Reynolds number Re=|\Omega|r^2/\nu. Motivated by a recent quasi-two-dimensional experiment, we use a DLM/FD method to compute planar phase diagrams of $\Gamma(G,Re)$ at corral sizes C=3, 4.5, and 6. The planar model recovers the benchmark gap route at Re=20: an intermediate counterrotation band, a wide-gap transition to corotation, gear-ratio magnitudes of order 10^{-2}, and the observed sequence of vortex attachment, detachment, and merger. It also produces a reentrant-like gap structure with a small-gap corotation region whose relation to the experimental close-range geometric state remains unresolved. The main discrepancy is the high-Re boundary. At the experimental mid-gap transect G about 0.3, the planar gear ratio approaches zero from the counterrotating side but does not cross through Re=400; at the narrower gap G=0.22, by contrast, the planar terminal spin reverses near Re=44. Wall-traction diagnostics show that this crossing is not the experimental shear-competition mechanism: the gap-facing counterrotating arc narrows but does not collapse or deflect as in the experiment, and the reversal at G=0.22 occurs by redistribution of the integrated planar torque. The strictly planar model therefore captures the broad gap-route architecture and the existence of a Reynolds-driven spin boundary, but displaces that boundary in gap and alters its surface-stress mechanism. The remaining mismatch points to finite-depth secondary motion, end-wall stresses, and apparatus geometry as plausible contributors to the experimental shear balance.
arXiv:2607.01535v1 Announce Type: new Abstract: Despite the intense engagement surrounding low-level vision generalist models, their effectiveness in zero/few-shot scenarios beyond learned tasks remains unverified. The primary challenge of developing an ideal generalist lies in achieving the ability to generalize from new unseen tasks, which also can be assessed by matched quantitative criteria. Existing methods have made some progress in prompt engineering but have not systematically explored this gap across a wide range of low-level visual tasks. Stimulated by the problem, we propose Hidden-Shot, an implicit prompt mechanism aimed at exploring low-level task adaptation in a vision generalist model. Specifically, the method extracts implicit visual task-based information, utilizes a global task-aware textural prompt, and selectively merges implicit information with in-task processing information to enhance one-shot capabilities in new tasks. The overall design performs direct injection in a cost-effective manner, while minimally altering the architecture of the original generalist model. Additionally, we introduce a data-driven evaluation framework termed C/U assessment to cover two basic scenarios, 3C4U (3 conventional and 4 unconventional tasks) for retraining existing models and 3C7U (3 conventional and 7 unconventional tasks) for training from scratch, as a comprehensive assessment to systematically test the generalization ability of low-level generalist models. Experiments on seven and ten datasets outperform the state-of-the-art vision generalist model, respectively verified by 3C4U and 3C7U framework. Our presented Hidden-Shot approach demonstrates superior performance on one-shot new tasks while maintaining consistent performance on existing tasks.
arXiv:2607.01488v1 Announce Type: new Abstract: A specially shielded CdTe detector based hard X-ray (HXR) monitoring system equipped with a lead collimator has been developed and installed on the Aditya-U tokamak to investigate the dynamics of fast electrons (~20-200 keV) generated during sawtooth activity. The pre-existing HXR monitor in Aditya-U is exposed to the entire HXR bremsstrahlung emission from the plasma volume, peripheral limiters, and other structural components, which limits its ability to separately study the dynamics of lost and confined runaway electrons (REs). In contrast, the newly developed diagnostic has successfully measured the chord-averaged thin-target HXR bremsstrahlung emission encompassing the core plasma region, particularly within and around the sawtooth inversion radius. The measured HXR spectra are validated through forward modelling code that incorporates plasma parameters, confined RE characteristics, and the geometric configuration of the diagnostic system. The results confirm the capability of the developed HXR monitor to probe the fast-electron dynamics during internal plasma instabilities.
arXiv:2607.01494v1 Announce Type: new Abstract: Matter seeks to resolve longstanding interoperability problems in the Internet of Things (IoT), yet little is known about how developers experience the standard in day to day work. This paper examines over 13,000 issues from the official Project CHIP GitHub repository to understand the kinds of problems contributors report when implementing and integrating Matter. Using topic modeling and qualitative analysis, we identify four recurring areas of concern, Testing, Interoperability, Development, and Platform and Network, and describe how they manifest in the evolution of the codebase and tooling. The findings reveal systematic technical and integration challenges and point to concrete opportunities to refine Matter's test infrastructure, cross vendor guidance, and documentation as the standard continues to mature.
arXiv:2607.01496v1 Announce Type: new Abstract: High Energy Physics experiments at flagship colliders produce and process some of the biggest datasets on Earth, with the current generation of flagship experiments at the Large Hadron Collider producing more than a tenth of the world's total internet traffic every second. Moreover the quantities of data produced have increased exponentially over the past decades and this trend shows no sign of slowing down. In parallel, the use of picosecond timing is becoming more common in HEP detectors, enabling qualitatively new approaches to real-time processing and selections. I review the planned introduction of precision timing information into the upcoming upgrades of the CMS, ATLAS, and LHCb experiments. I discuss the ways in which the combination of timing and networking technology may enable future detectors to be designed as triggereless from the ground up, and reflect on the physics benefits of such a paradigm shift for the field.
arXiv:2607.01516v1 Announce Type: new Abstract: The "Trading Prophet" problem challenges an online trader to maximize its profit by buying and selling assets under stochastic prices and capacity constraints, competing against an offline prophet with full foresight. In previous work, each arriving asset was assumed to have a single price $p_t$, and the trader was allowed to either buy a copy at this price (subject to having available capacity), or sell a copy (if it already held at least one copy in hand). However, this abstraction can fail to capture the structural asymmetry of decentralized dealer-based markets, where buying and selling opportunities could be distinct, and driven by individual preferences. To address this, we introduce the Asymmetric Trading Prophets problem, where at each timestep the trader observes a price tuple $(b_t, s_t)$ -- representing the cost to buy, and the revenue from selling at this timestep. Importantly, the $(b_t,s_t)$ tuple could be potentially arbitrarily correlated. We provide the first competitive analysis for this asymmetric trading prophets problem, characterizing the achievable profit based on the trader's capacity $B$ and initial inventory $B_0$. For the unit-capacity case of $B=1$, we design online algorithms that achieve constant competitive ratios for both i.i.d. and non-i.i.d. distributions on the price tuples, when the trader has one initial copy ($B_0=1$). For the general capacity case where $B$ can be large, we give algorithms for i.i.d. distributions that achieve a competitive ratio of $1 - \Theta(\log B_0/\sqrt{B_0})$. Finally, for the symmetric case (where the price tuple satisfies $b_t=s_t$), we improve this to get a competitive ratio of $1 - O(\log B/\sqrt{B})$, demonstrating that the performance approaches optimality as the capacity increases. We show that both ratios are tight up to a logarithmic factor.
arXiv:2607.01663v1 Announce Type: new Abstract: 4D scene synthesis from monocular videos has made significant progress in recent years. However, existing methods are typically constrained by view interpolation. As a result, they struggle to infer unseen regions beyond the observed views. In this paper, we reformulate the task as 4D scene synthesis with unseen regions, which extends beyond traditional interpolation settings. Camera-conditioned video generation enables unseen region synthesis by guiding generation along specified cameras. However, these methods lack explicit 3D priors and are optimized with random camera trajectories. This design leads to severe inconsistencies under large trajectory deviations. To address this limitation, we build a unified training and inference framework with panoramic trajectory guidance. While this design improves cross-view consistency, the panoramic representation alone fails to model dynamic content effectively. Object motion in panoramic space introduces scale and shape distortions. To address this, we propose PanoGaussian, a unified Panoramic-Gaussian representation that distills the panoramic representation into an explicit dynamic Gaussian representation to capture dynamic physical priors of the 4D scene. Experiments demonstrate that PanoGaussian achieves consistent 4D scene synthesis even under large viewpoint variations.
arXiv:2607.02347v1 Announce Type: cross Abstract: Variations in solar radius (hereafter R_Sun) is a key reference for solar magnetic activity in time. The sunlight amount may have varied with R_Sun and had an effect on the Earth's climate in the past. Eclipse observations offer a unique opportunity to measure the absolute R_Sun value before modern direct observations. The scientific community has discussed a possible long-term R_Sun variability from 1715 onward. Prior to their coverage, Clavius' eclipse reports had been subjected to qualitative debates regarding the local eclipse visibility and a possible secular R_Sun trend. This study leverages the recent dramatic developments of lunar topography data and ephemeris data to provide an effective resolution of this debate. Clavius' eclipse reports described an explicit totality in 1560 at Coimbra and a "slender circle" around the eclipsing Moon in 1567 at Rome. Our study revised the {\Delta}T constraints of -492 s =< {\Delta}T =< 200 s in 1560 and 140 s =< {\Delta}T =< 151 s in 1567 to satisfy Clavius' descriptions, considering the lunar limb profile and assuming Auwers' canonical R_Sun. This study constrains the R_Sun margin of 1567, utilising three scenarios to interpret Clavius' account. The local totality requires an upper R_Sun limit of 1567 as R_Sun =< 696200 km in absolute size (959.92" in angular size), indicating no linear secular R_Sun shrinkage but possible R_Sun oscillations on a centennial timescale. Conversely, the annularity scenario is considered unlikely because it requires an R_Sun decrease of 7.5" within 3 centuries, even beyond the capacity of extreme shrinking-Sun hypotheses.
arXiv:2607.01548v1 Announce Type: new Abstract: Large language models are increasingly used as open-ended search operators in evolutionary optimization. We introduce Evolutionary Feature Engineering (EFE), a framework for using LLM-based evolution to discover preprocessing transformations for structured data. EFE represents transformations as Python programs with a standardized fit/transform interface, allowing them to be inserted directly into existing machine learning pipelines. During evolution, candidate programs are refined using dataset context, summary statistics, and downstream performance feedback on validation set. We instantiate EFE in two settings. For time-series forecasting, EFE-Time learns invertible, dataset-specific normalizations that improve off-the-shelf time-series foundation models. It reduces forecasting errors (MASE, WQL, MAE) 3% or more when averaged across datasets and improvements are as much as 19% on the COVID-Deaths dataset. Notably, these improvements occur with recent TSFMs such as Chronos-2. For tabular prediction, EFE-Tab evolves compact feature programs that add useful interpretable features and remove redundant ones, improving or matching existing LLM-based feature-engineering methods. We found EFE-Tab to be particularly effective on classical decision trees, where small sets of evolved features yield competitive accuracy while preserving interpretability. Overall, EFE demonstrates that LLM-based evolution can improve both accuracy and interpretability when automatically tackling structured data.
arXiv:2607.01667v1 Announce Type: new Abstract: While Multimodal Large Language Models (MLLMs) have advanced video understanding, achieving precise temporal and cross-modal alignment in audiovisual video captioning remains a formidable challenge. Most existing approaches suffer from modality detachment and temporal incoherence, failing to accurately bind auditory events to visual entities or capture complex causal dynamics. To address these deficiencies, we propose TCA-Captioner, a framework specifically engineered to enhance Temporal and Cross-Modal Alignment for audiovisual video captioning. We first introduce the Observer-Checker-Corrector (OCC) framework, an iterative refinement strategy that generates high-fidelity, meticulously grounded training data. Leveraging a curated high-density human interaction dataset, TCA-Captioner is optimized to model sophisticated audiovisual interactions. Furthermore, we present TCA-Bench, a diagnostic benchmark utilizing a Decoupled Evaluation Protocol to isolate and quantify model proficiency in audiovisual binding and temporal relational reasoning. Extensive experiments demonstrate that TCA-Captioner sets a new standard for temporally-coherent and synchronized audiovisual narratives.
arXiv:2607.01688v1 Announce Type: new Abstract: Although the electromagnetic transient (EMT) framework can capture subsynchronous oscillations (SSOs), it faces scalability issues for large-scale systems. Thus motivated, we propose a generalized dynamic phasor (DP) framework to analyze SSOs in multi-machine systems with inverter-based resources (IBRs) and large loads such as artificial intelligence data centers (AI DCs) under balanced and unbalanced conditions. The grid-following (GFL) and grid-forming (GFM) IBRs are modeled in their respective $dq$-frame DPs. In contrast, the detailed model of multi-mass turbine driven synchronous generators (SGs) along with dynamic transmission network models and loads are represented in $pnz$-frame DPs. The linearizability and time-invariance of the framework enable us to perform eigen decomposition, which is a powerful tool for root-cause analysis of SSO modes and the design of damping controllers. In addition, the DP modeling approach facilitates faster simulation of large-scale systems. The generalized framework is validated with EMTDC/PSCAD simulations using the IEEE first benchmark model for subsynchronous resonance and the modified IEEE 4-machine system. Several use cases are presented on the modified IEEE 68-bus system with two GFL IBRs to show the applicability of the framework. First, time- and frequency-domain analyses of the IBR-induced SSO mode are presented. Then, two solutions are proposed to damp the poorly damped SSO mode: (a) a decentralized controller is designed using particle swarm optimization, and (b) the control of one GFL IBR is replaced by GFM control. Finally, the impact of AI DC load on primary frequency response of the system and the multi-mass turbines of the SGs are studied.
arXiv:2607.01592v1 Announce Type: new Abstract: Objective. Gold-standard depth-of-interaction (DOI) calibration using collimated gamma-ray irradiation is time-consuming and impractical for system-level calibration of detector arrays. This work investigates an efficient DOI and energy calibration method for detector panels using uncollimated irradiation, with gamma rays incident nearly parallel to the crystal depth direction. Approach. The 511-keV photopeak location in a dual-ended readout PET detector block was evaluated as a function of crystal depth using collimated and uncollimated $^{22}$Na irradiation. A $4\times4$ dual-ended readout PET detector panel was then assembled. Three detector blocks were calibrated using the gold-standard method, and two uncollimated-irradiation DOI calibration approaches--a physics-informed model and a multilayer perceptron (MLP)--were compared against it. Finally, the full panel was calibrated for DOI and energy using the MLP-based approach. Main Results. The median relative RMSE between second-order polynomial fits from collimated and uncollimated irradiation was 1%, showing that uncollimated irradiation can provide reliable estimates when accurate DOI calibration parameters are available. Compared with gold-standard DOI calibration, the physics-informed and MLP-based approaches achieved RMSEs of 0.38-0.58 mm and 0.36-0.61 mm, respectively. The MLP-based approach provided better DOI resolution estimates and was therefore used for full-panel calibration. After saturation correction, the panel achieved a mean energy resolution of 15.6% and a DOI resolution of 2.0 mm. Significance. The proposed MLP-based calibration requires only a single uniform 511-keV irradiation, making it simple to implement and suitable for in situ calibration of DOI-capable PET detector arrays.
arXiv:2607.01601v1 Announce Type: new Abstract: Large scale document deduplication must preserve semantic equivalence while remaining efficient over massive corpora. We present SemHash LLM, a multi granularity framework that unifies semantic projection hashing, attention weighted MinHash, contrastive boundary learning, and selective LLM based adjudication. The method combines character, token, and document level signals through gated fusion, then applies a cascaded filtering pipeline for efficient candidate reduction. Semantic projection hashing learns compact binary codes in distilled LLM embedding space, while attention weighted Min- Hash suppresses boilerplate and emphasizes informative content. Adaptive decision boundaries and uncertainty estimation further improve robustness across template pollution, short text perturbation, containment, and viral fragments. Experiments show that SemHash LLM achieves strong duplicate detection quality with less than one percent neural verification cost.
arXiv:2607.01689v1 Announce Type: new Abstract: Model merging aims to combine existing single-task solutions into a multi-task solution without additional data-driven fine-tuning.~Most existing approaches achieve this using geometric properties of local solution spaces. However, such geometric views provide limited guidance for scoring how statistically useful each task-specific update direction is across tasks during merging. To address this, we formulate model merging from a new perspective of probabilistic inference under a product-of-experts (PoE) scenario where each single-task solution defines an energy-based expert model (EBM) over the merged parameters. We show that several existing model merging methods arise as special cases of our framework under energy designs that impose implicit Gaussian assumptions on directional residuals between merged and task-specific models. Empirically, we find that these residuals are often heavy-tailed which exposes a mismatch with the imposed light-tailed Gaussian structures. We address this with a heavy-tailed PoE design based on Cauchy experts, which better captures the observed residual behavior while admitting a provably convergent inference procedure. Experiments across multiple tasks and architectures show significant improvements over state-of-the-arts baselines. Our code is available at https://github.com/MinhLong210/PoE-EBM-Merging.git.
arXiv:2607.01639v1 Announce Type: new Abstract: Universal traffic laws describe recurrent patterns in congestion, mobility and driving behavior across cities, providing a scientific basis for transportation planning, management and control. Their discovery, however, remains expert-driven, requiring candidate regularities to be identified from heterogeneous observational evidence or validated through intervention experiments. Although autonomous artificial intelligence (AI) systems have advanced scientific discovery in controlled laboratory settings, extending them to complex transportation domains remains a challenge. Here we present TrafficSci, an agentic AI system that formulates traffic-law discovery as an iterative, auditable workflow integrating evidence scoping, critic-judge hypothesis induction, and observational-interventional validation. Across four case studies spanning population, network, control and trajectory scales, TrafficSci autonomously rediscovers three established traffic laws and identifies an unreported intrinsic temporal memory scale in urban driving behavior, statistically consistent across eight cities and two trajectory datasets. TrafficSci provides a route for extending AI-driven scientific discovery from controlled domains to complex urban systems.
arXiv:2607.01696v1 Announce Type: new Abstract: Parametrized PDEs with density-valued solutions are often difficult to approximate with classical linear reduced-order models, especially in transport-dominated regimes. We introduce an optimal-transport-based reduced-order modeling that represents each density by the Kantorovich potential transporting a fixed reference density to the target density, and then maps these potentials to transport signatures using a weighted Laplacian associated with the reference measure. This embeds the density-valued solution map in a Hilbert space while preserving control of the induced transport maps and Wasserstein error. We treat the signature map as a continuous matrix indexed by parameters and space, construct a low-rank skeleton decomposition using a maximal-volume criterion, and learn the parameter-to-coefficient map with a neural network for efficient non-intrusive online evaluation. The reconstructed solution is obtained by pushing forward the reference density, so mass preservation is built into the method. We prove a mean-squared Wasserstein error bound separating low-rank approximation, discretization, sampling, and learning errors, and demonstrate the method on a two-dimensional continuity equation, where transport signatures yield substantially lower-rank structure than the original density snapshots.
arXiv:2607.01236v1 Announce Type: new Abstract: As LLM agents gain increasing access to powerful tools, ensuring that their actions are aligned with the user's intent becomes critical. When an agent's proposed tool invocation deviates from the user's intent -- a phenomenon called misalignment -- it may lead to harmful consequences that are difficult to undo. Existing runtime guardrails rely on an LLM-as-a-judge paradigm that lacks a systematic framework for reasoning about alignment, often producing judgments that are inconsistent or difficult to audit. Motivated by provenance analysis, we propose a provenance-based conceptual framework that formalizes misalignment detection as determining whether a proposed tool call is supported by traceable evidence in the agent's context. Building on this framework, we propose ProvenanceGuard, a multi-stage pipeline that analyzes the agent's action for three types of misalignment before the selected tool is executed and only allows the action to take place when it is considered aligned with the user's input query. We evaluated our proposed approach on two different benchmarks, Agent-SafetyBench and WorkBench, across 10 backbone LLMs. Compared to the LLM-as-a-judge baseline, ProvenanceGuard reduces error rate on misaligned traces from 42.9% to 1.8% on Agent-SafetyBench and from 32.1% to 17.3% on WorkBench, while reducing intervention burden on task-successful traces from 30.5% to 12.8% and introducing no statistically significant increase in unnecessary interventions on aligned traces. These results demonstrate that structured, provenance-based reasoning provides an effective and practical foundation for safeguarding LLM agents from misalignment.
arXiv:2607.01675v1 Announce Type: new Abstract: Segmentation of biomarkers in medical images is frequently viewed as a first step towards medical image analysis in any bioinformatics or biomedical application. Despite progress, existing methods still struggle to capture information at multiple scales and to perform upsampling effectively across different datasets. These shortcomings often result in suboptimal generalization capabilities. Recently, architectures belonging to the Nested-UNet family excel in capturing multiscale contextual information and upsample them effectively. In this work, We propose a novel Nested-UNet architecture that effectively captures multi-scale contextual information. It includes inner and outer attention units to enhance focus during upsampling, along with channel-wise feature recalibration using squeeze-and-excitation modules, leading to improved segmentation performance. Additionally, the architecture integrates an edge-aware loss to emphasize boundary accuracy by assigning greater importance to edge regions. Tested extensively on three publicly available benchmark datasets. Our method demonstrates a generalization performance superior to existing Nested-UNet methods. Code: https://github.com/saadwazir/histosegplusplus
arXiv:2607.01581v1 Announce Type: new Abstract: The capacity of Large Language Models (LLMs) to reason about pedagogical intent within instructional communication remains underexplored, particularly in educational domains such as translation pedagogy. To address this, we propose the \textbf{Adaptive Pedagogical Vigilance (APV)} framework, a novel computational formalism that reframes communicative vigilance as an adaptive mechanism for optimizing learning through intent inference. APV formalizes the problem via a Bayesian Pedagogical Intent Inference Engine (PIIE), which models how instructors select content to maximize pedagogical utility and how vigilant learners should inversely reason about latent instructional configurations -- encompassing genre, stance, and incentives. We evaluate APV through a three-tier hierarchy: distinguishing instructional genre, reasoning about structured pedagogical setups, and generalizing to authentic educational discourse. Experiments on leading LLMs (e.g., GPT-4o, Claude 3.5) show that APV substantially improves model vigilance. It achieves the strongest discrimination between pedagogical and exposure-based content, correlates highly with human judgments ($r=0.958$), and maintains robust performance on naturalistic data where baseline methods degrade. This work establishes a unified framework for assessing and enhancing LLMs' understanding of pedagogical motives, advancing the development of more reliable AI-assisted learning systems.
arXiv:2607.01588v1 Announce Type: new Abstract: Extended Reality (XR) has become an important interaction paradigm in Human-Computer Interaction (HCI). XR studies are used to investigate interaction, perception, and user behavior in immersive environments, and typically involve experimental tasks, 3D scenes, and interactive logic. However, turning an initial XR study idea into a runnable prototype remains fragmented across study design, scene construction, and interaction implementation. We present OrchestrXR, a multi-agent human-AI workflow for early-stage idea-to-prototype XR study authoring. Rather than treating XR study creation as one-shot generation, OrchestrXR supports a controllable workflow across study design, scene generation, and interaction generation through structured schemas, multi-agent orchestration, and interactive human-agent interfaces, producing a Unity-based prototype from a researcher's idea. A user study with 12 XR researchers suggests that OrchestrXR provides effective support for early-stage XR study authoring with strong intent preservation across stages.
arXiv:2607.01597v1 Announce Type: new Abstract: Modern LLM coding agents are commonly evaluated using pass@k, but developers typically apply a single final patch in real-world settings. This pass@k-to-pass@1 gap is a post-generation problem: a candidate patch pool may contain a correct patch, but the system must decide which one to suggest to developers. Existing post-generation approaches mainly rank whole candidates, filter them with tests, or query an LLM judge, but none deterministically reuse shared edit-atom evidence to both select and construct the final patch. Thus, we propose PatchFusion, a deterministic atomic evidence fusion approach for candidate patches that consults no test outcome at decision time. PatchFusion first fuses whole-diff agreement into a repair neighborhood, selects an auditable representative, and then applies evidence-constrained fusion (ECF) to retain repeated edit atoms and prune unsupported parts. To evaluate this setting, we build PatchFuseBench, a fixed-pool benchmark covering SWE-bench Verified, SWE-bench Multilingual, and Defects4J candidate patches. On PatchFuseBench, PatchFusion solves 426/500 bugs on SWE-bench Verified and 236/300 on SWE-bench Multilingual, and reaches 87/371 plausible patches on Defects4J, outperforming every matched candidate-pool selector on all three. PatchFusion recovers 41 and 27 bugs that no single source solves (30 and 18 more over the best single source). Ablation studies show that ECF adds +5/+6/+9 solved bugs by recovering in-pool repairs that selection misses, with no observed regression, and that PatchFusion's gains remain stable as candidate pools are resampled. On these complementary multi-source pools, cross-candidate evidence recovers more correct patches than the test-based and LLM-based selectors we evaluate, at orders-of-magnitude lower cost, reaching within 96.2% and 89.7% of the candidate-reachable ceiling on the two SWE-bench benchmarks.
arXiv:2607.01616v1 Announce Type: new Abstract: This paper proposes a novel unified control framework for achieving hybrid grid-forming (GFM) and grid-following (GFL) inverter operation by integrating dispatchable virtual oscillator control with reference-following synchronization. The proposed inverter control method supports multiple operating modes within a unified structure, including voltage- and frequency-following (PQ mode), voltage-forming and frequency-following (PV mode), voltage-following and frequency-forming (Qf mode), voltage- and frequency-forming (Vf mode), and a hybrid mode with mixed GFM and GFL behaviors. In particular, the proposed method achieves smooth pre-synchronization and enables seamless transitions across a spectrum of inverter operating modes by tuning a small set of continuous control parameters, rather than relying on discrete controller switching. This framework provides a flexible and physically interpretable approach for adapting inverter dynamics to varying grid conditions and operational requirements. The small-signal stability and input-output frequency-domain characteristics are further analyzed under different control parameter settings. The effectiveness and robustness of the proposed unified control method are demonstrated through extensive electromagnetic transient (EMT) simulations and hardware-in-the-loop (HIL) experiments.
arXiv:2607.01633v1 Announce Type: new Abstract: Comprehensive 3D scene understanding from sparse, unposed images requires a model to recover renderable geometry, open-vocabulary semantics, and free/occupied 3D space without relying on external camera calibration. Recent feed-forward Gaussian methods improve pose-free reconstruction and semantic rendering, but their Gaussian primitives are mainly optimized through image-space objectives and remain weakly constrained in unobserved regions. We propose \textit{COVScene}, a pose-free semantic Gaussian framework that couples renderable Gaussian primitives with a dense semantic occupancy field through differentiable volumetric lifting. Instead of converting Gaussians to voxels only at evaluation time, COVScene lifts the predicted semantic Gaussians inside the training computation graph, so volumetric regularization provides gradients to Gaussian opacity, geometry, and semantic features. The framework combines a semantic-aware Geometry Transformer, multi-task Gaussian decoding, geometric foundation distillation, and occupancy entropy regularization to support novel view synthesis, open-vocabulary semantic querying, and semantic occupancy prediction within a single representation. Experiments on ScanNet and ScanNet++ show that COVScene maintains competitive rendering quality, improves open-vocabulary segmentation, and achieves stronger semantic occupancy prediction than the self-supervised baseline without direct voxel-level supervision.
arXiv:2607.01678v1 Announce Type: new Abstract: Communication increasingly dominates the cost of Large Language Model (LLM) pre-training, especially under data-parallel and sharded training schemes, where gradient synchronization and parameter reconstruction overhead increase with model size and system scale. Existing communication-reduction methods either sparsify raw gradients, which can be unstable for modern Adam-style optimizers at high sparsity, or quantize communication, whose savings are fundamentally bounded by bit width and often incur additional runtime overhead. We present SCAPE, a communication-efficient distributed optimizer for LLM training that exploits the stability of AdamS's first-moment to enable aggressive sparsification without loss of LLM quality. Instead of constructing masks from raw gradients, SCAPE derives them from first-moment-based statistics, partitions mask generation across workers to align with optimizer sharding, and delays mask usage by one step so that mask synchronization can overlap with computation. SCAPE also reconstructs the quantities required for second-moment updates from a single synchronized sparse buffer, avoiding an additional collective. We implement SCAPE in Megatron-LM and evaluate its convergence by pre-training GPT-345M on OpenWebText and Llama-500M on SlimPajama-6B using 32 NVIDIA GH200 GPUs on TACC Vista. In both models, SCAPE preserves training stability, validation loss, and downstream task accuracy under 90\% and 99\% sparsity. For Llama-500M, SCAPE reduces end-to-end pre-training wall-clock time by up to 43.3\% while maintaining model quality comparable to dense AdamW and AdamS. For Llama-1.8B, SCAPE achieves up to 3.26$\times$ speedup per step compared to dense AdamS.