arXiv:2606.09059v1 Announce Type: new Abstract: Two-stage post-training -- a Stage-1 warm-start (supervised fine-tuning, SFT, or on-policy distillation, OPD) followed by Stage-2 reinforcement learning (RL) -- is increasingly used for vision-language models (VLMs). We ask what Stage-1 actually controls in a small-data study using Qwen2.5-VL-7B with a same-modality 72B VLM teacher for OPD. First, the three warm-starts reach a narrow $53$--$54\%$ band on Geometry3K internal validation, consistent with the narrow range reported by recent specialized methods; this setup provides little evidence that Stage-1 changes the in-domain endpoint. Second, a matched-recipe, early-stopped SFT improves out-of-domain MathVista by $+2.1$ points, reversing the $-9.5$-point drop of an over-trained variant. The clearest difference is the \emph{entropy regime}: OPD enters RL with substantially higher policy entropy than either SFT initialization, and the separation remains visible through the available trajectories. At the in-domain initialization, OPD also has higher answer diversity and pass@16 ($+2.0$ to $+5.2$ points over SFT), although problem-level bootstrap intervals show that the smaller contrast is uncertain. The advantage is absent after RL (endpoint pass@16 values within $1.1$ points) and on MathVista (six models within $1.2$ points). Our contribution is therefore a bounded empirical characterization: Stage-1 is strongly associated with the entropy regime in this setup, but the downstream payoff is small, localized, and not evidence that OPD is a better RL warm-start.
Science Journals
arXiv:2606.09293v1 Announce Type: new Abstract: Dialogue systems in e-commerce scenarios often need to satisfy multiple objectives: accurately reasoning over user profiles (e.g., eligibility, credit limit) to ensure correct decision-making and user state interpretation, while also generating natural and faithful responses. These goals are complementary but not identical. In this work, we propose MORE, an adaptive Multi-Objective REinforcement learning framework that jointly optimizes reasoning accuracy and linguistic naturalness. Our preliminary experiments show that directly mixing rewards with diverging optimization dynamics can cause oscillations and unstable learning. Thus, instead of optimizing a single mixed reward, we treat reasoning functions as constraints that guide policy optimization. At inference time, the system directly generates responses without explicit reasoning steps, while still benefiting from reasoning-enhanced scaffold and avoiding additional inference overhead. To better balance linguistic objectives during response generation, we introduce an adaptive multi-reward mechanism that aggregates signals such as fluency and naturalness and dynamically reweighs them via gradient feedback. We evaluate MORE on two real-world dialogue systems at ByteDance and the MultiWOZ 2.2 benchmark, where it consistently outperforms strong baselines. In 14-day online experiments on ByteDance production traffic, MORE improves overall and reached conversion by 16.53% and 30.09%, while increasing user satisfaction and reducing handoff rates. Notably, in a human-machine comparison, MORE recovers about 60% of the incremental conversion lift achieved by human agents.
arXiv:2606.09078v1 Announce Type: new Abstract: Process Reward Models (PRMs) improve credit assignment for reasoning by providing step-level feedback. However, we identify a hidden bias in PRMs caused by severe imbalance in step-level training data. Standard cross-entropy training amplifies this bias, causing PRMs to overcredit plausible but incorrect steps and produce high false-positive rates. We show that these false positives have an asymmetric downstream effect: false negatives mainly slow exploration, whereas false positives actively steer Best-of-N selection, guided decoding, and policy optimization toward flawed reasoning. This suggests that PRM training should shift from pointwise label fitting to reliable relative comparisons. To address this, we propose PRISM (Precision Ranking for Improved Step Modeling), a policy-aware PRM training framework that learns from contrastive step-level comparisons and hard negatives generated by a temporal lookahead strategy, requiring no new human labels. We further use a difficulty-aware curriculum to optimize the contrastive step margin. Across PRMBench and ProcessBench, PRISM substantially reduces false positives (22% on PRMBench) and improves macro F1 over strong discriminative PRMs. When applied to policy optimization and search tasks, including guided decoding and Best-of-N selection, it consistently improves accuracy (up to 22% for guided decoding and 33% for Best-of-N) and robustness. More broadly, trustworthy process supervision is not just about assigning high rewards, but about rewarding the right reasoning for the right reasons.
arXiv:2606.09088v1 Announce Type: new Abstract: Autonomous FPV quadrotor flight in complex environments using a monocular RGB camera as the sole exteroceptive sensor remains a fundamental challenge. Recent research has shown that using optical flow as the input of a neural network can achieve end-to-end autonomous flight in cluttered scenes. However, extracting the most relevant information from the flow estimation is the key bottleneck limiting agility and robustness. Existing methods struggle to disentangle obstacle-induced optical flow from the ego-motion background flow and suffer from low signal-to-noise ratios near the focus of expansion (FoE). To address these issues, we decompose the optical flow into translational and rotational components and utilize only the translational flow, which captures scene geometry and depth cues. In addition, we introduce an uncertainty mask derived from inconsistencies between forward and backward flow estimates. This mask highlights obstacle structures, including those within the FoE region. Both cues are fed to a control policy trained in a differentiable simulation framework, which enables efficient first-order optimization across perception and control. We validate our approach through extensive experiments in both simulated and real-world forest environments. The proposed system achieves robust flight at speeds of up to 13.91 m/s in simulation and 11.79 m/s in real-world tests, with a 93.3\% success rate over 30 real-world trials, nearly doubling the previously reported 6 m/s real-world speed of the monocular-RGB optical-flow UAV obstacle avoidance system.
arXiv:2606.09090v1 Announce Type: new Abstract: Developers increasingly provide AI coding assistants with persistent context through configuration files such as CLAUDE.md, AGENTS.md, and .cursorrules. These files describe code elements, architecture, and development conventions, forming the context that guides AI tool behavior across sessions. As software evolves, this context can become stale, a phenomenon we call context rot. While AI configuration artifacts are new, the underlying consistency problem connects to decades of software documentation research. Researchers have built tools to check consistency between documentation and code, spanning README files, code comments, API documentation, architecture descriptions, and installation instructions. We argue that this existing toolbox is an immediate starting point for detecting context rot, and we present a research roadmap mapping documentation consistency approaches to corresponding problems in this new setting. As preliminary evidence, applying an existing README/wiki consistency checker to a statistically representative sample of 356 repositories identifies stale code element references in 23.0% of repositories, showing that traditional documentation consistency tools can already surface context rot.
arXiv:2606.03632v2 Announce Type: replace-cross Abstract: This article presents a finite-horizon linear quadratic regulator for the control of the first-order Lighthill-Whitham-Richards traffic model with a triangular fundamental diagram. The in-domain control action is realized through variable speed limits implemented as a source term in the governing hyperbolic partial differential equation. Unlike prior studies on infinite-horizon formulations, this article develops a finite-horizon LQR framework, deriving a space and time varying state feedback function for hyperbolic PDEs. The solution to the finite time optimal control problem relies on the solution of another PDE, called the Riccati PDE. The resulting nonlinear Riccati PDE is solved analytically via the parametric method of characteristics. The Riccati PDE solution is a function of both time and space, as well as the traffic regime. A sensitivity analysis demonstrates the effects of the LQR parameters for both the infinite and finite time horizon problem in different traffic situations, while siulations validate the finite-horizon LQR's ability to guarentee finite-time convergence. Comapred to the infinite-horizon LQR, the proposed approach achieves significantly improved control performance across various scenarios, making it particularly suitable for time-sensitive traffic management applications.
arXiv:2604.18180v3 Announce Type: replace Abstract: We examine the English translation of Albert Einstein's groundbreaking 1925 paper on Bose-Einstein condensation. We guide readers to execute the calculations Einstein outlined for the specific heat above the condensation temperature, correct some numerical errors, and compare his formula with a different one published in the American Journal of Physics in 2004. The history of the acceptance of Einstein's theory will be summarized.
arXiv:2606.08512v1 Announce Type: new Abstract: As Russia's war against Ukraine extends into generative AI, large language models (LLMs) adapted for local post-Soviet languages are deployed in contested information environments. Policy and industry discourse assumes that culturally aligned adaptation encodes the political orientation of the target community: a Ukrainian-oriented model will resist Russian narratives, a Russian-oriented one will reinforce them. Does it? This article systematically disconfirms that assumption. We run a controlled audit of four openly available LLMs sharing a common base model but fine-tuned for different linguistic communities, querying them in Ukrainian, Russian and English across ten contested wartime narratives: Crimea, "denazification", the "one people" thesis, and atrocity denial at Bucha and Mariupol. The result is a Fine-Tuning Paradox: the Ukrainian-oriented model shows the weakest resistance to Russian disinformation in Russian, while the Russian-oriented one exhibits the strongest rejection. Corpus composition, language coverage and prompt format prove more decisive than nominal cultural provenance. We situate these findings within debates on hybrid warfare, digital sovereignty and post-imperial information orders, arguing that the principal threat to regional information sovereignty is not adversarial fine-tuning but the untested assumption that cultural alignment guarantees resilience.
arXiv:2606.08515v1 Announce Type: new Abstract: Modern scientific workflows increasingly span diverse computing architectures, yet executing a single computational model across disparate systems often forces researchers to maintain fragmented, site-specific pipelines. In this paper, we address this challenge within the domain of computational neuroscience by presenting a unified, cloud-based workflow orchestrated via EBRAINS JupyterLab. This workflow enables users to transparently execute spiking neural networks on both von-Neumann supercomputers and neuromorphic hardware. Using a single federated identity, the system dispatches jobs to HPC sites (JUSUF, Galileo100) via PyUNICORE and to the SpiNNaker-1 neuromorphic system via the Neuromorphic Computing Platform Interface. To guarantee cross-site reproducibility and mitigate software version drift, we utilize a zero-installation execution mode that dynamically pulls PMIx-aware Apptainer containers to HPC compute nodes. Furthermore, we demonstrate genuine model-level portability using the NESTML domain-specific language, allowing custom neuron models to be written once and automatically compiled for either the NEST (C++) or sPyNNaker backends. Validated with a balanced random network case study, this work illustrates a practical, end-to-end path for hardware-agnostic workflows while highlighting the critical role of containerization and domain-specific languages in achieving true cross-platform reproducibility.
arXiv:2606.09117v1 Announce Type: new Abstract: While Ising machines serve as advanced physical solvers for the Ising model,enabling applications in combinatorial optimization and neural network training,their scalability for large-scale neural networks remains constrained by hardware connectivity limitations and suboptimal training methodologies. In this work,we leverage a Coherent Ising Machine (CIM) to train an energy-based neural network using Equilibrium Propagation, achieving performance comparable to existing software-based implementations. We further enhance the algorithm by integrating the Adam optimizer to solve for the ground state of a Hopfield energy network, significantly improving convergence speed and solution accuracy. Additionally, we demonstrate the scalability of our approach across deeper network architectures and convolutional operations. Our results highlight the potential of CIM dynamics as a scalable platform for training complex neural networks, offering a pathway toward energy-efficient implementations via analog circuits, optoelectronics, or integrated photonics. This work establishes a novel physical framework for next-generation AI hardware development.
arXiv:2604.26176v4 Announce Type: replace Abstract: The integration of Large Language Models (LLMs) with Retrieval-Augmented Generation (RAG) has significantly advanced Knowledge Graph Question Answering (KGQA). However, existing LLM-driven KGQA systems act as stateless planners, generating retrieval plans in isolation without exploiting historical query patterns: analogous to a database system that optimizes every query from scratch without a plan cache. This fundamental design flaw leads to schema hallucinations and limited retrieval coverage. We propose CacheRAG, a systematic cache-augmented architecture for LLM-based KGQA that transforms stateless planners into continual learners. Unlike traditional database plan caching (which optimizes for frequency), CacheRAG introduces three novel design principles tailored for LLM contexts: (1) Schema-agnostic user interface: A two-stage semantic parsing framework via Intermediate Semantic Representation (ISR) enables non-expert users to interact purely in natural language, while a Backend Adapter grounds the LLM with local schema context to compile executable physical queries safely. (2) Diversity-optimized cache retrieval: A two-layer hierarchical index (Domain $\rightarrow$ Aspect) coupled with Maximal Marginal Relevance (MMR) maximizes structural variety in cached examples, effectively mitigating reasoning homogeneity. (3) Bounded heuristic expansion: Deterministic depth and breadth subgraph operators with strict complexity guarantees significantly enhance retrieval recall without risking unbounded API execution. Extensive experiments on multiple benchmarks demonstrate that CacheRAG significantly outperforms state-of-the-art baselines (e.g., +13.2% accuracy and +17.5% truthfulness on the CRAG dataset).
arXiv:2605.28525v2 Announce Type: replace Abstract: The material point method (MPM) is a hybrid particle-grid method widely used for simulating large deformation with history-dependent behavior. Standard MPM often relies on a dense background grid, which can be highly inefficient when material occupies a small fraction of the computational domain. Such sparsity is common in many large-scale problems, from geophysical mass flows over large terrain domains to visual-computing applications. Here, we introduce a unified sparse background-grid framework for large-scale MPM simulation. The framework treats sparse grid construction as a general active-node indexing problem. We develop two architecture-specific implementations to realize the same sparse framework: a scan-based strategy for CPUs and a hash-based strategy for GPUs. Through benchmark problems and a large-scale landslide simulation, we show that the framework provides the same results as standard dense MPM while reducing computational time and memory usage by one to two orders of magnitude in strongly sparse cases.
arXiv:2606.09671v1 Announce Type: new Abstract: Alzheimer's disease (AD) progression is highly heterogeneous and is typically observed through sparse and irregular longitudinal data, posing challenges for prediction and personalised monitoring. Existing machine learning approaches have improved AD prediction using multimodal data, yet often focus on static classification or cohort-level risk estimation, providing limited support for subject-specific modelling and uncertainty-aware reasoning. To address these limitations, we present a personalised digital twin framework for AD prediction and scenario-based analysis using multimodal longitudinal data. The proposed approach integrates complementary modelling strategies to capture clinical transitions and temporal dependencies across visits. Using data from the Alzheimer's Disease Neuroimaging Initiative (ADNI), including cognitive assessments, clinical variables, and MRI-derived phenotypes, the framework predicts cognitive status and diagnostic categories while quantifying predictive uncertainty and enabling patient-specific what-if trajectory analysis. Evaluation on leak-free subject-level splits demonstrates strong performance in score forecasting and diagnosis classification. In this sparse and irregular ADNI setting, transition-based modelling of adjacent visits achieved higher predictive accuracy than the sequence-based branch, suggesting that local transition modelling may be more data-efficient. While sequence models remain valuable for uncertainty-aware trajectory forecasting, local transition modelling offers a more data-efficient and robust predictive strategy. These findings highlight the importance of aligning temporal modelling strategies with clinical data structure and suggest that transition-based digital twin formulations may provide a practical and interpretable approach for personalised disease forecasting in neurodegenerative disorders.
arXiv:2606.09138v1 Announce Type: new Abstract: Agentic reinforcement learning (RL) has become an important post-training paradigm for turning LLMs from static chatbots into interactive agents, giving rise to representative applications such as OpenClaw. Existing work mainly focuses on policy optimization algorithms and training frameworks, but pays less attention to the full data lifecycle of agent-environment interactions, from data production to training consumption. To bridge this gap, we present Claw-R1, an interactive step-level data middleware system for agentic RL. Claw-R1 connects heterogeneous agent runtimes with RL training backends through two core components: a Gateway Server and a Data Pool. The Gateway Server captures multi-turn interaction steps through a unified LLM API entry point, while the Data Pool organizes them into step-level records consisting of prompt IDs, response IDs, rewards and other metadata. In our demo, users can interactively inspect live trajectories, examine the state, action, and reward of each step, curate data by quality and readiness, and configure training-ready batches for different downstream RL algorithms. Overall, Claw-R1 treats agent interaction traces as managed data assets rather than temporary runtime logs. Through this demonstration, we hope to encourage the community to recognize the importance of data management in agentic RL. Our code is available at https://github.com/AgentR1/Claw-R1 and the demonstration video can be found at link https://youtu.be/Pw47dAOw6B0.
arXiv:2606.09139v1 Announce Type: new Abstract: Despite the rapid advancements in event-based motion estimation, current geometric methods primarily focus on velocity estimation. However, absolute pose estimation, which is equally crucial for key applications such as robotic navigation and augmented reality, remains relatively underexplored. Consequently, the simultaneous recovery of absolute pose and velocity from event streams remains an open and challenging problem. To address this gap, we propose a geometric framework for absolute pose and velocity estimation by leveraging 3D lines in the scene and the events they trigger. At the core of the framework lie two key geometric constraints: the orthogonality between a 3D line and the normal vector of its corresponding event plane, and the collinearity of an event with the 2D projection of its associated line. Based on these constraints, we present both linear and polynomial solvers for absolute pose estimation. The former enables efficient computation, while the latter provides a globally optimal solution for rotation. For velocity estimation, we develop an efficient linear solver and a more accurate optimization-based solver to recover both angular and linear velocities. Notably, our methods require a minimum of three event-line correspondences to determine the 6-DoF absolute pose or velocities independently. Extensive experiments in simulation and on real-world datasets demonstrate that our methods achieve state-of-the-art performance, with significant improvements in accuracy and computational efficiency compared to existing methods. The demo code is publicly available at https://github.com/Zibin6/EventPoseVelocity.
arXiv:2606.08542v1 Announce Type: new Abstract: Exploratory manipulation often turns an apparent failed attempt into the key evidence for what to do next. For example, a robot pulls a locked cabinet drawer, fails, and only succeeds after opening the lock. The failed pull reveals a latent precondition (the drawer is locked) that determines the minimal-success action chain (the fewest actions that complete the task), here [lock-open, drawer-pull]. Correctly reading this trace is therefore the prerequisite for recovering that chain. We formalize this setting as Exploratory Manipulation Trace QA (EMT-QA): given synchronized video and proprioception from an exploratory trace, predict the minimal-success action chain under the latent precondition revealed by the probe. However, even state-of-the-art VLMs and embodied multimodal LLMs misread this evidence: they do not reliably recover the chain from raw video, raw proprioception, or their combination. We introduce Closed-Loop Trace Distillation, a pipeline that uses a per-task coding agent to inspect labeled training traces and distill a one-line natural-language prompt over the trace, which we call the Distilled Reading Heuristic (DRH). At inference, no agent is invoked and no model weights are updated; a frozen VLM receives the raw trace plus the DRH as a prompt entry. Across three simulator and two real-robot tasks, the DRH improves chain accuracy by +0.38 to +0.47 over the best raw-modality baseline. The same DRH also serves as the sole specification for one-shot programmatic classifiers that match the prompted VLM.
arXiv:2606.09143v1 Announce Type: new Abstract: Multimodal 3D object detection based on LiDAR and cameras has demonstrated excellent performance in ground-vehicle scenarios, but has not been explored for Unmanned Aerial Vehicle (UAV) platforms. In UAV top-down scenes, frequent groundobject occlusion dominated by tree canopies causes spatially varying and modality-dependent information degradation. Existing multimodal fusion frameworks neither explicitly model such ground-object occlusion nor embed occlusion awareness into the detection pipeline, limiting their performance in occluded UAV scenes. To address these challenges, we propose CAMF-Det, a closure-aware multimodal fusion framework for LiDAR-camera 3D object detection on UAV platforms, which derives dual-modal occlusion intensity through physics-inspired modeling and embeds them as priors throughout the detection pipeline. First, a dual-modal closure modeling module explicitly constructs occlusion intensity ground truth for both modalities offline via a Beer-Lambert-inspired formulation and building-mask correction. Second, using these ground-truth maps as supervision, a dual-modal prediction network converts the offline modeling results into online occlusion intensity predictions under single-frame inference. Third, both ground-truth and predicted occlusion intensity are injected into data augmentation, feature encoding, multimodal fusion, and detection head, enabling adaptive detection under spatially varying and modality-dependent information degradation. Experiments on two self-built UAV-based multimodal datasets, SI3D-DI and SI3D-DII, demonstrate that CAMF-Det achieves the best performance across all difficulty levels, with hard-level mAP$_{\mathrm{BEV}}$ improvements of 9.43% and 4.88% over the best competing methods, respectively. These results confirm the effectiveness of explicit occlusion prior modeling and exploitation for robust multimodal 3D detection in UAV scenes.
arXiv:2606.09148v1 Announce Type: new Abstract: Multimodal affective analysis aims to understand human sentiment and emotion by jointly modeling heterogeneous modalities such as text and images. However, multimodal models often fail to consistently outperform strong text-only baselines, with performance varying significantly across fusion strategies. In this work, we identify representation misalignment between independently pretrained modality encoders as a key bottleneck for effective multimodal learning, and show through controlled experiments that alignment prior to fusion is often more important than fusion complexity. To address this issue, we propose a unified multimodal affective analysis framework that leverages vision-language models (VLMs) to convert visual content into structured textual descriptions, projecting heterogeneous modalities into a shared linguistic space and enabling interpretable text-centric reasoning. To further improve robustness, we introduce a hybrid learning strategy that combines semantic token selection with a batch-level uniformity regularization objective, encouraging a more dispersed and stable global feature space while mitigating noise introduced by VLM-generated descriptions. Experiments on multiple multimodal sentiment and emotion benchmarks show that our method consistently outperforms strong unimodal and multimodal baselines, achieving state-of-the-art performance. Our analysis further highlights the critical role of representation alignment in multimodal affective learning.
arXiv:2606.06360v2 Announce Type: replace Abstract: Modelling individual decision-making during infectious disease outbreaks is crucial for understanding behavioural dynamics and informing effective public health interventions. Prior work has shown that large language models can simulate realistic human behaviour by generating agent decisions based on demographic prompts and situational context. We build on this foundation with a spatially grounded, agent-based simulation framework that integrates LLM-generated decisions about self-reported influenza-like illness into a census-based synthetic population of agents. Location is treated as a central feature: agents are assigned to spatial units within cities, capturing the spatial distributions of different demographic groups using real-world census data and enabling geographically diverse behavioural modelling. We implement and compare three decision scenarios, independent reasoning, household influence, and message framing, and simulate self-reporting outcomes in San Francisco and Atlanta. Results reveal that income and education are the dominant drivers of reporting rate variation, with smaller but consistent effects from geography, LLM model choice, and message framing. Our framework generates synthetic data that captures both social and geographic heterogeneity, supporting spatial epidemiological modelling and bias-aware behavioural analysis.
arXiv:2604.07421v3 Announce Type: replace Abstract: Full-waveform inversion (FWI) is pivotal for reconstructing high-resolution subsurface velocity models but remains computationally intensive and ill-posed. While deep learning approaches promise efficiency, existing Convolutional Neural Networks (CNNs) and single-paradigm Neural Operators (NOs) struggle with one fundamental issue: frequency entanglement of multi-scale geological features. To address this challenge, we propose Spectral-Preserving Adaptive MoE (SPAMoE), a novel spectrum-aware framework for solving inverse problems with complex multi-scale structures. Our approach introduces a Spectral-Preserving DINO Encoder that enforces a lower bound on the high-to-low frequency energy ratio of the encoded representation, mitigating high-frequency collapse and stabilizing subsequent frequency-domain modeling. Furthermore, we design a novel Spectral Decomposition and Routing mechanism that dynamically assigns frequency bands to a Mixture-of-Experts (MoE) ensemble comprising FNO, MNO, and LNO. On the ten OpenFWI sub-datasets, experiments show that SPAMoE reduces the average MAE by 44.4% relative to the best officially reported OpenFWI baseline, thereby establishing a new architectural framework for learning-based full-waveform inversion. Our code and data are available at https://github.com/zhenyuwang12366/SPAMoE
arXiv:2606.09160v1 Announce Type: new Abstract: This paper presents a unified system designed to support precision agriculture by integrating advanced weather prediction, crop recommendation, and a question-answering tool for farmers. We propose two deep learning models -- a Transformer-based Graph Neural Network and a Spatio-Temporal Graph Convolutional Network (STGCN) -- to forecast weather conditions for the next 30 days using data from 1,359 locations in Nepal. The STGCN outperforms the Transformer-based model in accuracy (MSE ~0.011 vs. 0.013), effectively modeling both spatial and temporal dependencies in climate data. These predictions are combined with static soil properties such as pH, moisture, and organic content to generate localized crop recommendations through a scoring algorithm that matches each crop's optimal growing conditions. Additionally, we develop a Retrieval-Augmented Generation (RAG) chatbot that leverages domain-specific agricultural documents to answer farmers' questions in natural language. The entire system is deployed via a mobile application, offering real-time suggestions and conversational support. User feedback confirms the system's usability and relevance, especially in rural settings where personalized farming guidance is limited. Overall, our approach demonstrates how combining machine learning models with local agricultural data can empower farmers with actionable insights, promoting more informed decisions, better crop yields, and increased resilience to climate variability.
arXiv:2606.09163v1 Announce Type: new Abstract: EnclaveScale is a distributed, hardware-assisted telemetry architecture providing post-extraction attestation, enabling operators to collaboratively model high-resolution generative AI power transients. Existing cryptographic techniques scale poorly for 10-Hz streaming or fail to authenticate origins, permitting malicious hosts to spoof sensor inputs. We implement and evaluate a post-extraction pipeline utilizing DCAP attestation, differential privacy noise injection, and Byzantine rejection across 32 GCP Confidential VMs, achieving 0\% post-extraction attack success rate. This edge-DP approach distils continuous GPU transients into discrete Markov-chain transition matrices, guaranteeing event-level differential privacy. To mitigate pre-ingestion vulnerabilities, we propose an SPDM-authenticated first-mile layer. While current platforms lack attested I/O, emerging hardware architectures integrate PCIe IDE and TDISP to natively prevent host-level synthesis, securing the end-to-end provenance boundary. A Global Aggregation Enclave verifies these cryptographic proofs prior to capacity-weighted aggregation. Evaluation demonstrates a steady-state throughput of $131{,}406$ samples/s per enclave, amortising attestation overhead to $0.23\,\mu$s/sample. On empirical NVML-sampled H100, A100, and L4 traces, EnclaveScale achieves a dynamic orchestration margin error of $1.3$\,MW compared to $0.1$\,MW for an honest-aggregator central-DP baseline. EnclaveScale establishes a secure foundation for dynamic multi-tenant power orchestration, obfuscating sub-second anomalies locally and protecting macro-workload confidentiality via spatial dilution during global aggregation.
arXiv:2606.08984v1 Announce Type: cross Abstract: Warm starts are widely used to accelerate AC optimal power flow (ACOPF) solves, but the impact of different initialization strategies has received limited systematic study, particularly for the primal-dual interior-point methods that dominate large-scale ACOPF algorithms. This paper benchmarks initialization strategies for ACOPF solved with the interior-point solver IPOPT on 19 PGLib-OPF instances (5 to 30,000 buses), testing all 15 non-empty subsets of the primal blocks $\{P_g, Q_g, V_m, V_a\}$ under oracle conditions and three DC-seeded combinations in a practical setting. The experiments show that most partial primal-plus-dual restarts increase solve time or reduce convergence reliability. Among the oracle primal-plus-dual (O-PD) configurations, only the complete restart reliably converges on every baseline-convergent case, reaching a $47.6\%$ median solve-time speedup. Twelve of the 14 partial O-PD combinations have negative median speedups, and several fail repeatedly on larger networks. Decomposing the dual into constraint and bound multipliers shows that \emph{coverage}, not the presence of duals per se, governs robustness: the full bound-multiplier vector reaches 90.7\% convergence and a $+26.8$\% median speedup, whereas block-matched coverage (oracle multipliers on some bounds, defaults on the rest) drops to 70.4\% and $-31.1$\%. Practical DC seeding sometimes helps the AC solve, but the benefit is no longer statistically significant once the DCOPF presolve cost is included in the end-to-end comparison ($p = 0.4171$). For learned warm-start methods, the results support the following target ordering: predict the full primal vector first; if only partial coverage is possible, prioritize voltage variables; and avoid partial or inconsistent dual predictions unless the primal estimate is nearly complete.
Calibration of Structured Ignorance Certificates for Diagnosing Unknown Unknowns in Reasoning Models
arXiv:2606.08571v1 Announce Type: new Abstract: Large language models frequently fail in a characteristic way: rather than acknowledging ignorance, they produce fluent but incorrect answers to questions that lie beyond their knowledge boundaries. We introduce \textbf{Structured Ignorance Certificates} (SICs), a JSON-formatted output schema that demands a model explicitly name the missing domain intersection, enumerate required concepts, and propose a productive retrieval query rather than hallucinating an answer. To train models to produce high-quality SICs we construct a 7,347-sample \emph{Unknown-Unknown} (UU) dataset by prompting Qwen3-14B to stitch together questions from seven domains (physics, biology, engineering, CS, economics, medical, legal) into novel cross-domain queries that no single-domain expert could answer. We fine-tune a 14B-parameter model with Group Relative Policy Optimization (GRPO) using a composite reward that combines retrieval utility, concept specificity, and output-format validity. A paraphrase-divergence probe trained on model responses confirms that SIC-tuned outputs systematically exhibit higher unknown-unknown probability scores. Evaluation on 735 held-out UU questions achieves a 99.46\% JSON validity rate, a mean Certificate Specificity Score of 0.967, and a 3.6\% ROUGE-L improvement over the base model on retrieval-grounded generation -- demonstrating that explicit epistemic structuring is a learnable and measurable capability.
arXiv:2604.06210v4 Announce Type: replace Abstract: As LLMs are globally deployed, aligning their cultural value orientations is critical for safety and user engagement. However, existing benchmarks face the Construct-Composition-Context ($C^3$) challenge: relying on discriminative, multiple-choice formats that probe value knowledge rather than true orientations, overlook subcultural heterogeneity, and mismatch with real-world open-ended generation. We introduce DOVE, a distributional evaluation framework that directly compares human-written text distributions with LLM-generated outputs. DOVE utilizes a rate-distortion variational optimization objective to construct a compact value codebook from 10K documents, mapping text into a structured value space to filter semantic noise. Alignment is measured using unbalanced optimal transport, capturing intra-cultural distributional structures and subgroup diversity. Experiments across 12 LLMs show that DOVE achieves superior predictive validity, attaining a 31.56% correlation with downstream tasks, while maintaining high reliability with as few as 500 samples per culture.