arXiv:2510.18941v2 Announce Type: replace
Abstract: Evaluating progress in large language models (LLMs) is often constrained by the challenge of verifying responses, limiting assessments to tasks like mathematics, programming, and short-form question-answering. However, many real-world applications require evaluating LLMs in processing professional documents, synthesizing information, and generating comprehensive reports in response to user queries. We introduce ProfBench: a set of over 7000 response-criterion pairs as evaluated by human-experts with professional knowledge across Physics PhD, Chemistry PhD, Finance MBA and Consulting MBA. We build robust and affordable LLM-Judges to evaluate ProfBench rubrics, by mitigating self-enhancement bias and reducing the cost of evaluation by 2-3 orders of magnitude, to make it fair and accessible to the broader community. Our findings reveal that ProfBench poses significant challenges even for state-of-the-art LLMs, with top-performing models like GPT-5-high achieving only 65.9% overall performance. Furthermore, we identify notable performance disparities between proprietary and open-weight models and provide insights into the role that extended thinking plays in addressing complex, professional-domain tasks. Data: https://huggingface.co/datasets/nvidia/ProfBench and Code: https://github.com/NVlabs/ProfBench and Leaderboard: https://huggingface.co/spaces/nvidia/ProfBench
Science Journals
arXiv:2605.18342v1 Announce Type: new
Abstract: This work continues the development of an intensional approach to computability initiated in previous work, in which programs and computations, rather than functions, constitute the primary objects of study. In this setting, models of computation are described as monoid actions on a configuration space, and programs as dynamical systems constrained by this action. Within this framework, we introduce a formal notion of algorithm as a finite directed graph whose edges are labelled by partial maps over an abstract data structure. This definition separates control from data, representing the former as a graph and the latter as an algebra of operations. We then define what it means for a program, in a given model of computation, to implement such an algorithm, by requiring a correspondence between computational steps and labelled transitions that preserves the induced transformations on representations of data. This yields a precise notion of implementation and situates algorithms as abstract partial specifications of computational behaviour.
arXiv:2605.18346v1 Announce Type: new
Abstract: Recent advances in autoregressive video diffusion have enabled sequential and streaming video generation. However, long-horizon generation requires increasingly large KV caches, making efficient compression without sacrificing quality challenging. Existing methods mostly select historical frames based on attention scores, but their context decisions remain coarse. When multiple frames are generated in the same chunk, these methods often apply a shared history selection to the whole chunk, score historical frames solely by attention, and assign head-wise budgets either uniformly or by attention-pattern heuristics rather than explicit head-importance estimation. We show that frames within the same generated chunk can depend on distinct historical frames, that the same historical frame can receive different attention scores as its relative temporal distance to the current frames changes, and that masking different heads induces unequal generation degradation. Motivated by these findings, we propose \textbf{Focused Forcing}, a training-free KV selection method that focuses cached history along both generated-frame and head dimensions. For each generated frame, Focused Forcing preserves the most relevant and distinctive historical frames by combining attention scores with diversity scores of historical frames, while assigning larger budgets to heads with higher estimated importance. Across multiple autoregressive generation paradigms, Focused Forcing achieves up to $\textbf{1.48}\times$ end-to-end acceleration without training, while \textbf{improving visual quality and text alignment}. \textit{Our code will be released on GitHub.}
arXiv:2601.05569v3 Announce Type: replace
Abstract: Distributed AI systems face critical memory management challenges across computation, communication, and deployment layers. RRAM based in memory computing suffers from scalability limitations due to device non idealities and fixed array sizes. Decentralized AI frameworks struggle with memory efficiency across NAT constrained networks due to static routing that ignores computational load. Multi agent deployment systems tightly couple application logic with execution environments, preventing adaptive memory optimization. These challenges stem from a fundamental lack of coordinated memory management across architectural layers. We introduce Self Evolving Distributed Memory Architecture for Scalable AI Systems, a three layer framework that unifies memory management across computation, communication, and deployment. Our approach features (1) memory guided matrix processing with dynamic partitioning based on device characteristics, (2) memory aware peer selection considering network topology and computational capacity, and (3) runtime adaptive deployment optimization through continuous reconfiguration. The framework maintains dual memory systems tracking both long term performance patterns and short term workload statistics. Experiments on COCO 2017, ImageNet, and SQuAD show that our method achieves 87.3 percent memory utilization efficiency and 142.5 operations per second compared to Ray Distributed at 72.1 percent and 98.7 operations per second, while reducing communication latency by 30.2 percent to 171.2 milliseconds and improving resource utilization to 82.7 percent. Our contributions include coordinated memory management across three architectural layers, workload adaptive resource allocation, and a dual memory architecture enabling dynamic system optimization.
arXiv:2601.06116v5 Announce Type: replace
Abstract: Generative AI models reproduce the human biases in their training data and further amplify them through mechanisms such as mode collapse. The loss of diversity produces homogenization, which not only harms the minoritized but impoverishes everyone. We argue homogenization should be a central concern in AI safety. To meaningfully characterize homogenization in Large Language Models (LLMs), we introduce a framework that allows stakeholders to encode their context and value system. We illustrate our approach with an experiment that surfaces gender bias in an LLM (Claude 3.5 Haiku) on an open-ended story prompt. Building from queer theory, we formalize homogenization in terms of normativity. Borrowing language from feminist theory, we introduce the concept of xeno-reproduction as a class of tasks for mitigating homogenization by promoting diversity. Our work opens a collaborative line of research that seeks to understand and advance diversity in AI.
arXiv:2507.16481v3 Announce Type: replace
Abstract: Jumping poses a significant challenge for quadruped robots, despite being crucial for many operational scenarios. While optimisation methods exist for controlling such motions, they are often time-consuming and demand extensive knowledge of robot and terrain parameters, making them less robust in real-world scenarios. Reinforcement learning (RL) is emerging as a viable alternative, yet conventional end-to-end approaches lack efficiency in terms of sample complexity, requiring extensive training in simulations, and predictability of the final motion, which makes it difficult to certify the safety of the final motion. To overcome these limitations, this paper introduces a novel guided reinforcement learning approach that leverages physical intuition for efficient and explainable jumping, by combining B\'ezier curves with a Uniformly Accelerated Rectilinear Motion (UARM) model. Extensive simulation and experimental results clearly demonstrate the advantages of our approach over existing alternatives.
arXiv:2602.02830v3 Announce Type: replace
Abstract: Discovering causal structures from multivariate time series is a key problem because interactions span across multiple lags and possibly involve instantaneous dependencies. Additionally, the search space of the dynamic graphs is combinatorial in nature. In this study, we propose Stable Causal Dynamic Differentiable Discovery (SC3D), a two-stage differentiable framework that jointly learns lag-specific adjacency matrices and, if present, an instantaneous directed acyclic graph (DAG). In Stage 1, SC3D performs edge preselection through node-wise prediction to obtain masks for lagged and instantaneous edges, whereas Stage 2 refines these masks by optimizing a likelihood with sparsity along with enforcing acyclicity on the instantaneous block. Numerical results across synthetic SVAR systems, nonlinear and chaotic benchmarks, nonstationary dynamics and real-world datasets demonstrate that SC3D achieves improved stability and more accurate recovery of both lagged and instantaneous causal structures compared to existing baselines.
arXiv:2602.12978v2 Announce Type: replace
Abstract: Action chunking enables Vision Language Action (VLA) models to run in real time, but naive chunked execution often exhibits discontinuities at chunk boundaries. Real-Time Chunking (RTC) alleviates this issue but is external to the policy, leading to spurious multimodal switching and trajectories that are not intrinsically smooth. We propose Legato, a training-time continuation method for action-chunked flow-based VLA policies. Specifically, Legato initializes denoising from a schedule-shaped mixture of known actions and noise, exposing the model to partial action information. Moreover, Legato reshapes the learned flow dynamics to ensure that the denoising process remains consistent between training and inference under per-step guidance. Legato further uses randomized schedule condition during training to support varying inference delays and achieve controllable smoothness. Empirically, Legato produces smoother trajectories and reduces spurious multimodal switching during execution, leading to less hesitation and shorter task completion time. Extensive real-world experiments show that Legato consistently outperforms RTC across five manipulation tasks, achieving approximately 10% improvements in both trajectory smoothness and task completion time.
arXiv:2507.18406v2 Announce Type: replace
Abstract: Wikipedia serves as a globally accessible knowledge source with content in over 300 languages. Despite covering the same topics, the different versions of Wikipedia are written and updated independently. This leads to factual inconsistencies that can impact the neutrality and reliability of the encyclopedia and AI systems, which often rely on Wikipedia as a main training source. This study investigates cross-lingual inconsistencies in Wikipedia's structured content, with a focus on tabular data. We developed a methodology to collect, align, and analyze tables from Wikipedia multilingual articles, defining categories of inconsistency. We apply various quantitative and qualitative metrics to assess multilingual alignment using a sample dataset. These insights have implications for factual verification, multilingual knowledge interaction, and design for reliable AI systems leveraging Wikipedia content.
arXiv:2507.22057v2 Announce Type: replace
Abstract: Difficult few-shot image recognition has significant application prospects, yet remaining the substantial technical gaps with the conventional large-scale image recognition. In this paper, we have proposed an efficient original method for few-shot image recognition, called CIELab-Guided Coherent Meta-Learning (MetaLab). Structurally, our MetaLab comprises two collaborative neural networks: LabNet, which can perform domain transformation for the CIELab color space and extract rich grouped features, and coherent LabGNN, which can facilitate mutual learning between lightness graph and color graph. For sufficient certification, we have implemented extensive comparative studies on four coarse-grained benchmarks, four fine-grained benchmarks, and four cross-domain few-shot benchmarks. Specifically, our method can achieve high accuracy, robust performance, and effective generalization capability with one-shot sample per class. Overall, all experiments have demonstrated that our MetaLab can approach 99\% $\uparrow\downarrow$ accuracy, reaching the human recognition ceiling with little visual deviation.
arXiv:2506.06114v5 Announce Type: replace
Abstract: Unsupervised feature selection is critical for improving clustering performance in high-dimensional data, where irrelevant features can obscure meaningful structure. In this work, we introduce the Minkowski weighted $k$-means++, a novel initialisation strategy for the Minkowski Weighted $k$-means. Our initialisation selects centroids probabilistically using feature relevance estimates derived from the data itself. Building on this, we propose two new feature selection algorithms, FS-MWK++, which aggregates feature weights across a range of Minkowski exponents to identify stable and informative features, and SFS-MWK++, a scalable variant based on subsampling. We support our approach with a theoretical analysis, demonstrating that, under explicit assumptions on noise features and cluster structure, relevant features are assigned consistently higher weights than noise features across a range of Minkowski exponents. Our software can be found at https://github.com/xzhang4-ops1/FSMWK.
arXiv:2511.16776v3 Announce Type: replace
Abstract: In high-Reynolds-number wall-bounded flows, the inner-scaled wall-pressure variance \ra{is often represented as a} logarithmic increase with frictional Reynolds number.
We consider the two sources of the incompressible pressure--Poisson equation: a linear (rapid) term linked to mean shear and a nonlinear (slow) term composed of quadratic velocity fluctuations. This paper establishes a link between the sources and the coefficients in \rtwo{a logarithmic} inner-scaled variance \rtwo{representation}. \rone{To leading order} we \rone{posit that} the \ra{linear source provides a Reynolds-number-independent offset, while the nonlinear source contributes the logarithmic coefficient}. The illustrative dataset is direct numerical simulation (DNS) at \rtwo{frictional Reynolds number} $\delta^+\approx 550$, although the principal contribution is the establishment of a mechanistic link to well-known high-$\delta^+$ scalings of wall-bounded turbulence.
Through consideration of the sources and the integral solution method of the Poisson equation, we find that the linear source contribution sits predominantly in the buffer layer and maps to the near-wall cycle. \rone{To leading order}, this contribution becomes $\delta^+$ invariant under inner scaling, thus contributing an offset in the \rtwo{logarithmic representation}.
The interfacial regions between uniform momentum zones characteristic of the inertial layer (vortical fissures) spatially localise strain and vorticity contributions and contain an increasingly large proportion of the strain and vorticity. We show that fissures act as a compact carrier for the source terms, with the nonlinear term especially prominent in these regions. By considering the inertial layer statistics, we link the changing nonlinear contribution to \rtwo{the} $\ln \delta^+$ \rtwo{growth}, in agreement with previous empirical observations.
arXiv:2511.20742v4 Announce Type: replace
Abstract: China, the world's largest electric vehicle (EV) market, plays a pivotal role in global decarbonization of the transport sector. We present the first high-resolution assessment of EV adoption in 295 cities, utilizing more than 20 million registrations of 586 EV models tracked monthly from 2022 to 2024 and projecting transition pathways to 2035. Real-world data reveal that EVs are 30.9-212.8 megajoules per 100 km more energy efficient than internal combustion vehicles, yet their carbon intensities range from 18.2 to 270.4 gCO2/km among provinces. The limited electrification of hybrids means that gasoline still accounts for 44% of EV energy use. Scenario projections suggest that emissions will peak about 2030 at 21.1-30.9 megatonnes of CO2 and decline by 2035 under continued market transition. The findings establish an empirical foundation for accurate emissions accounting, emphasize the need to reduce regional disparities in adoptability, and offer globally relevant insights for road-transport decarbonization.
arXiv:2511.21654v2 Announce Type: replace
Abstract: We introduce EvilGenie, a benchmark for reward hacking in programming settings. We source problems from LiveCodeBench and create an environment in which agents can easily reward hack, such as by hardcoding test cases or editing the testing files. We measure reward hacking in three ways: held out unit tests, LLM judges, and test file edit detection. We verify these methods against human review and each other. We find the LLM judge to be highly effective at detecting reward hacking in unambiguous cases, and observe only minimal improvement from the use of held out test cases. In addition to testing many models using Inspect's basic\_agent scaffold, we also measure reward hacking rates for three popular proprietary coding agents: OpenAI's Codex, Anthropic's Claude Code, and Google's Gemini CLI. We observe explicit reward hacking by both Codex and Claude Code, and misaligned behavior by all three agents. Our codebase can be found at https://github.com/JonathanGabor/evilgenie_inspect .
arXiv:2512.02691v3 Announce Type: replace
Abstract: Consider a high-multiplicity Bin Packing instance $I$ with $d$ distinct item types. In 2014, Goemans and Rothvoss gave an algorithm with runtime ${{|I|}^2}^{O(d)}$ for this problem~[SODA'14], where $|I|$ denotes the encoding length of the instance $I$. Although Jansen and Klein~[SODA'17] later developed an algorithm that improves upon this runtime in a special case, it has remained a major open problem by Goemans and Rothvoss~[J.ACM'20] whether the doubly exponential dependency on $d$ is necessary.
We solve this open problem by showing that unless the ETH fails, there is no algorithm solving the high-multiplicity Bin Packing problem in time ${{|I|}^2}^{o(d)}$. To prove this, we introduce a novel reduction from 3-SAT. The core of our construction is efficiently encoding all information from a 3-SAT instance with $n$ variables into an ILP with $O(\log(n))$ variables and constraints.
This result confirms that the Goemans and Rothvoss algorithm is essentially best-possible for Bin Packing parameterized by the number $d$ of item sizes in the context of XP time algorithms.
arXiv:2601.01593v2 Announce Type: replace
Abstract: Manual font design is an intricate process that transforms a stylistic visual concept into a coherent glyph set. This challenge persists in automated Few-shot Font Generation (FFG), where models often struggle to preserve both the structural integrity and stylistic fidelity from limited references. While autoregressive (AR) models have demonstrated impressive generative capabilities, their application to FFG is constrained by conventional patch-level tokenization, which neglects global dependencies crucial for coherent font synthesis. Moreover, existing FFG methods remain within the image-to-image paradigm, relying solely on visual references and overlooking the role of language in conveying stylistic intent during font design. To address these limitations, we propose GAR-Font, a novel AR framework for multimodal few-shot font generation. GAR-Font introduces a global-aware tokenizer that effectively captures both local structures and global stylistic patterns, a multimodal style encoder offering flexible style control through a lightweight language-style adapter without requiring intensive multimodal pretraining, and a post-refinement pipeline that further enhances structural fidelity and style coherence. Extensive experiments show that GAR-Font outperforms existing FFG methods, excelling in maintaining global style faithfulness and achieving higher-quality results with textual stylistic guidance.
arXiv:2601.02244v2 Announce Type: replace
Abstract: We derive a state-space characterization of all dynamic state-feedback controllers that make an equilibrium of a nonlinear input-affine continuous-time system locally exponentially stable. Specifically, any controller obtained as the sum of a linear state-feedback $u=Kx$, with $K$ stabilizing the linearized system, and the output of internal locally exponentially stable controller dynamics is itself locally exponentially stabilizing. Conversely, every dynamic state-feedback controller that locally exponentially stabilizes the equilibrium admits such a decomposition. The result can be viewed as a state-space nonlinear Youla-type parametrization specialized to local, rather than global, and exponential, rather than asymptotic, closed-loop stability. The residual locally exponentially stable controller dynamics can be implemented with stable recurrent neural networks and trained as neural ODEs to achieve high closed-loop performance in nonlinear control tasks.
arXiv:2601.03851v2 Announce Type: replace
Abstract: Table Question Answering (TableQA) benefits significantly from table pruning, which extracts compact sub-tables by eliminating redundant cells to streamline downstream reasoning. However, existing pruning methods typically rely on sequential revisions driven by unreliable critique signals, often failing to detect the loss of answer-critical data. To address this limitation, we propose TabTrim, a novel table pruning framework which transforms table pruning from sequential revisions to gold trajectory-supervised parallel search. TabTrim derives a gold pruning trajectory using the intermediate sub-tables in the execution process of gold SQL queries, and trains a pruner and a verifier to make the step-wise pruning result align with the gold pruning trajectory. During inference, TabTrim performs parallel search to explore multiple candidate pruning trajectories and identify the optimal sub-table. Extensive experiments demonstrate that TabTrim achieves state-of-the-art performance across diverse tabular reasoning tasks: TabTrim-8B reaches 73.5% average accuracy, outperforming the strongest baseline by 3.2%, including 79.4% on WikiTQ and 61.2% on TableBench.
arXiv:2601.11895v3 Announce Type: replace
Abstract: DevBench is a telemetry-driven benchmark designed to evaluate Large Language Models (LLMs) on realistic code completion tasks. It includes 1,800 evaluation instances across six programming languages and six task categories derived from real developer telemetry and synthesized using generator models from multiple provider families to mitigate single-source bias. Unlike prior benchmarks, it emphasizes ecological validity, avoids training data contamination, and enables detailed diagnostics. The evaluation combines functional correctness, similarity-based metrics, and LLM-judge assessments focused on usefulness and contextual relevance. 9 state-of-the-art models were assessed, with the strongest achieving only 43.5% Pass@1, confirming the benchmark remains challenging and revealing differences in syntactic precision, semantic reasoning, and practical utility. Our benchmark provides actionable insights to guide model selection and improvement, detail that is often missing from other benchmarks but is essential for both practical deployment and targeted model development.
arXiv:2605.14038v2 Announce Type: replace
Abstract: Large language models (LLMs) increasingly act as autonomous agents that must decide when to answer directly vs. when to invoke external tools. Prior work studying adaptive tool use has largely treated tool necessity as a model-agnostic property, annotated by human or LLM judge, and mostly cover cases where the answer is obvious (e.g., fetching the weather vs. paraphrasing text). However, tool necessity in the wild is more nuanced due to the divergence of capability boundaries across models: a problem solvable by a strong model on its own may still require tools for a weaker one. In this work, we introduce a model-adaptive definition of tool-necessity, grounded in each model's empirical performance. Following this definition, we compare the necessity against observed tool-call behavior across four models on arithmetic and factual QA dataset, and find substantial mismatches of 26.5-54.0% and 30.8-41.8%, respectively. To diagnose the failure, we decompose tool use into two stages: an internal cognition stage that reflects whether a model believes a tool is necessary, and an execution stage that determines whether the model actually makes a tool-call action. By probing the LLM hidden states, we find that both signals are often linearly decodable, yet their probe directions become nearly orthogonal in the late-layer, last-token regime that drives the next-token action. By tracing the trajectory of samples in the two-stage process, we further discover that the majority of mismatch is concentrated in the cognition-to-action transition, not in cognition itself. These results reveal a knowing-doing gap in LLM tool-use: improving tool-use reliability requires not only better recognition of when tools are needed, but also better translation of that recognition into action.
arXiv:2601.16414v2 Announce Type: replace
Abstract: Difficulty replicating baselines, high computational costs, and required domain expertise create persistent barriers to clinical AI research. To address these challenges, we introduce PyHealth 2.0, an enhanced clinical deep learning toolkit that enables predictive modeling in as few as 7 lines of code. PyHealth 2.0 offers three key contributions: (1) a comprehensive toolkit addressing reproducibility and compatibility challenges by unifying 15+ datasets, 20+ clinical tasks, 25+ models, 5+ interpretability methods, and uncertainty quantification including conformal prediction within a single framework that supports diverse clinical data modalities - signals, imaging, and electronic health records - with translation of 5+ medical coding standards; (2) accessibility-focused design accommodating multimodal data and diverse computational resources with up to 39x faster processing and 20x lower memory usage, enabling work from 16GB laptops to production systems; and (3) an active open-source community of 400+ members lowering domain expertise barriers through extensive documentation, reproducible research contributions, and collaborations with academic health systems and industry partners, including multi-language support via RHealth. PyHealth 2.0 establishes an open-source foundation and community advancing accessible, reproducible healthcare AI. Available at pip install pyhealth.
arXiv:2601.18235v2 Announce Type: replace
Abstract: In neural network surrogate solvers for electromagnetic simulations, accurately modeling resonant phenomena remains a central challenge. High-amplitude resonances generate strongly localized field patterns that deviate significantly from the general distribution of non-resonant cases, leading to instability and degraded predictive performance. To address this, we introduce dissipative relaxation transfer learning (DIRTL), a data-efficient training framework that integrates transfer learning with loss-regularized optimization principles from high-Q photonics. DIRTL first pretrains the model on data generated with a small fictitious material loss, which broadens sharp resonant modes and suppresses extreme field amplitudes. This smoothing of the response landscape enables the model to learn global modal features more effectively. The pretrained model is subsequently fine-tuned on the target lossless dataset containing true high-amplitude resonances, allowing stable adaptation based on the pretrained representation. Applied to both the Fourier Neural Operator (FNO) and UNet architectures, DIRTL yields substantial improvements in prediction accuracy, including up to a two-fold error reduction for the FNO variant. Furthermore, DIRTL demonstrates robustness across diverse training conditions and supports multi-tasking performance, suggesting the generalizability and flexibility of the pretrained core. Altogether, these results position DIRTL as a physically grounded curriculum for improving the reliability of neural network surrogate solvers.
arXiv:2601.18442v3 Announce Type: replace
Abstract: Autonomous Vehicle (AV) requires rigorous testing in safety-critical scenarios for safety validation, yet its validation is hindered by the high cost of field testing and the lack of fidelity in current simulations for rare safety-critical events. Crash reports offer rich and authentic specifications of real-world accident dynamics, making them a promising resource for Large Language Models and Vision-Language models to generate high-fidelity scenarios. However, the existing models frequently deviate from actual accident characteristics due to context suppression. To address these limitations, this paper presents SG-CADVLM, a framework integrateing Context-Aware Decoding with multimodal input processing to generate safety-critical scenarios from crash reports. The framework mitigates the hallucination of VLMs while generating road geometry and vehicle trajectories simultaneously. The experimental results demonstrate that SG-CADVLM generates combined critical and high-risk scenarios at a rate of 88.1% compared to 31.2% for the baseline methods, representing a 182% improvement, while producing executable simulations for autonomous vehicle testing.
arXiv:2601.18664v3 Announce Type: replace
Abstract: Generative Recommendation (GR) has emerged as a transformative paradigm with its end-to-end generation advantages. However, existing GR methods primarily focus on direct Semantic ID (SID) generation from interaction sequences, failing to activate deeper reasoning capabilities analogous to those in large language models and thus limiting performance potential. We identify two critical limitations in current reasoning-enhanced GR approaches: (1) Strict sequential separation between reasoning and generation steps creates imbalanced computational focus across hierarchical SID codes, degrading quality for SID codes; (2) Generated reasoning vectors lack interpretable semantics, while reasoning paths suffer from unverifiable supervision. In this paper, we propose stepwise semantic-guided reasoning in latent space (S$^2$GR), a novel reasoning enhanced GR framework. First, we establish a robust semantic foundation via codebook optimization, integrating item co-occurrence relationship to capture behavioral patterns, and load balancing and uniformity objectives that maximize codebook utilization while reinforcing coarse-to-fine semantic hierarchies. Our core innovation introduces the stepwise reasoning mechanism inserting thinking tokens before each SID generation step, where each token explicitly represents coarse-grained semantics supervised via contrastive learning against ground-truth codebook cluster distributions ensuring physically grounded reasoning paths and balanced computational focus across all SID codes. Extensive experiments demonstrate the superiority of S$^2$GR, and online A/B test confirms efficacy on large-scale industrial short video platform.
arXiv:2601.19104v2 Announce Type: replace
Abstract: This study aims to capture aerodynamic causality from snapshot data with a time-varying mode decomposition technique referred to as information-theoretic machine learning. The current approach extracts time-dependent informative vortical structures, contributing to the future evolution of the aerodynamic coefficients. The present decomposition is employed with a convolutional neural network, enabling the identification of the spatial continuous mode. In addition, a low-order representation, characterizing the informative vortical structures and their corresponding aerodynamic coefficients, can also be identified by considering autoencoder-based data compression. The present technique is applied to a range of aerodynamic examples, including extreme vortex-gust airfoil interactions, experimentally measured transverse jet-wing interaction, and a turbulent separated wake across different Reynolds numbers. For the cases of gust-wing interaction, the time-varying gust effect on the lift response is extracted in an interpretable manner. With the example of a turbulent wake, the relationship between large-scale vortical motion and lift force is identified without any spatial length-scale information. The proposed approach could serve as a foundation for data-driven causal modeling and control for a range of unsteady flows.