Papers

Decentralized exchanges record trading and liquidity provision on public blockchains, but empirical analysis requires interpreting these records and linking them to execution metadata. dexamine is a Python package that parses Uniswap v2 and v3 events on Ethereum. It converts transaction receipt logs into observations of trades and liquidity changes, with token quantities, pool state, transaction order, and gas information. The package separates data retrieval, contract metadata, protocol interpretation, and output construction. The repository provides recorded Ethereum responses and an offline reproducible example, and version 1 has been used to construct data for an empirical study of price discovery in decentralized markets.

Motivated by recent work on tree independence number, we study the path independence number of a graph $G$: the minimum integer $k$ such that there is a path decomposition of $G$ where each bag induces a graph with independence number at most $k$. We show that every graph excluding both an induced forest minor and an induced star has bounded path independence number. This characterises when a graph class that excludes an induced star has bounded path independence number while also partially resolving a conjecture of Dallard, Krnc, Kwon, Milanič, Munaro, Štorgel and Wiederrecht (2024). Furthermore, we show that graphs excluding both an apex-forest induced minor and an induced star have bounded tree independence number. As a consequence, for every fixed apex-forest $H$ and integer $t$, there is a polynomial-time algorithm to test whether a $K_{1,t}$-induced-subgraph-free graph contains $H$ as an induced minor. Moreover, it follows that the Maximum Weight Independent Set problem, as well as several other NP-hard problems, can be solved in polynomial-time on $K_{1,t}$-induced-subgraph-free graphs that exclude $H$ as an induced minor.

Robot actions are temporally correlated trajectories whose frequency components encode motion at different scales with highly non-uniform energy distributions. Yet Flow Matching–based vision-language-action (VLA) models typically generate actions in temporal coordinates, without explicitly modeling or systematically leveraging this frequency heterogeneity. We introduce FreqFM, a frequency-conditioned Flow Matching framework for VLA models. It raises action frequency from an implicit trajectory property to an explicit conditioning dimension that spans the entire generation pipeline. Concretely, in DCT frequency coordinates, FreqFM constructs a spectrum-matched source distribution, adaptively balances the objective across frequencies, and constrains per-frequency guidance residuals using the corresponding reference transport scales. FreqFM integrates into existing Flow Matching action experts without changing the VLA backbone. Across LIBERO, LIBERO-Plus, and VLA-Arena, FreqFM consistently improves performance, including a 9.3-point gain on LIBERO-Plus, and further demonstrates its effectiveness on six real-robot tasks.

Cross-silo Federated Learning (FL) enables geographically distributed institutions to collaboratively train machine learning models without sharing raw data. In wide-area deployments, however, communication delays often dominate round completion time and exacerbate the straggler effect. Hybrid FL addresses this challenge by combining synchronous and asynchronous client participation, but effective partitioning requires visibility into network conditions such as shared bottlenecks, link utilization, and path contention that individual clients cannot observe. We present HybridFLow, a closed-loop SDN-driven orchestration framework that integrates network-layer intelligence directly into hybrid FL. Leveraging the SDN controller's global topology view, HybridFLow generates calibrated per-client communication-time estimates before each training round and uses them to partition clients into synchronous and asynchronous groups while balancing round latency and update staleness. After each round, measured communication times are fed back to the controller to continuously refine future predictions. Experimental results across multiple network topologies show that HybridFLow reaches 80% target accuracy 33-40% faster than SmartFLow and reduces average round duration by 30-40 seconds, while FedAsync fails to reach the target accuracy under non-IID data distributions.

The coordination of Automated Guided Vehicles (AGVs) in high-density industrial environments represents a critical challenge within Logistics 4.0, as traditional traffic management methods often lead to inefficiencies caused by negotiation-based priority assignment. To overcome the resulting limitations, this paper presents an innovative AGV traffic management system based on a Lifelong Multi-Agent Path Finding (L-MAPF) algorithm operating on roadmaps generated with Non-Uniform Rational B-Splines (NURBS) curves. The approach guarantees locally optimal coordination and ensures safe operation of large and heterogeneous AGVs. Building on this concept, the proposed framework integrates a modified version of the Bounded Horizon Conflict Based Search (CBS) technique within a Rolling Horizon Conflict Resolution strategy, utilizing an extended time horizon for each agent to enable effective conflict resolution in corridors identified by a topological map. In contrast to state-of-the-art methods for AGV fleet traffic management, the proposed solution is designed for real-world, non-standardized (i.e., non-grid-like) industrial settings characterized by narrow bidirectional corridors and high-traffic density, where AGVs of various sizes and capabilities operate simultaneously. Key contributions include an anytime conflict resolution strategy with adaptive time horizon regulation, an execution layer for safe and standard-compliant interaction with real AGVs, and an advanced mechanism for deadlock detection and resolution. Experimental results obtained in realistic industrial environments demonstrate higher throughput, with improvements of up to 11% over a conventional rule-based traffic management system, a state-of-the-art industrial method, and a priority-based L-MAPF variant, while maintaining continuous operation and improved efficiency.

Temporal-network models place the memory seen in contact data either on nodes, through self-excitation (branching ratio n_node), or on ties, through reinforcement (kappa). The two choices reproduce the same coarse statistics but predict different epidemics. We ask whether contact data can tell them apart and find two limits. The first is attribution. When the initiator of every event is recorded, the likelihood factorises into a timing block containing n_node and a selection block containing kappa, so the two are estimated independently. When it is not, as in proximity data, a missing-information term couples them, with a size set by the entropy of the initiator posterior. The second issue is interpretation. Even where the mechanisms separate, the fitted n_node might not accurately measure memory and it may be set by the distribution of waiting times between events. Shuffling each node's inter-event order, which keeps that distribution, typically changes the estimated n_node by less than 10%; this is a bias that longer records and a flexible scale-free kernel do not remove. Whether node memory is present must therefore be decided by model-free statistics, which find only weak order memory in the proximity records, far less than the fitted n_node around 0.9 would imply. Tie reinforcement remains recoverable, although a latent initiator inflates it by 28%-45%. The two limits lead to two recommendations: record who initiates each contact, and test a fitted node memory against shuffled and model-free benchmarks before interpreting it. On a high-school record, simulating from the fitted node memory under-predicts outbreak sizes by up to a factor of 2, whereas keeping tie reinforcement alone is closer at low transmissibility but overshoots at high.

Exception Related Code (ERC), which includes throw statements, conditions (if statements) that guard those throw statements, and try/catch blocks, is an essential component of software systems, allowing developers to detect and handle exceptional states that deviate from the expected program behavior. However, manually writing ERC across large codebases is tedious. We propose a novel task: retrofitting existing code with ERC. Namely, given code (without ERC) and Exceptional Behavior Tests (EBTs) (e.g., check if method throws InvalidArgumentException if null is given as the value to the argument) we aim to automatically generate missing ERC, such that the given tests pass. We design and implement Exception Coder (EXCODER) that performs context engineering to help Large Language Models (LLMs) tackle this task. EXCODER integrates static and dynamic program analysis with LLMs by providing the extracted contextual information to the LLMs. To evaluate EXCODER, we build a benchmark constructed from GitHub Java repositories, where we systematically remove ERC in 304 methods from 75 projects. Our results demonstrate that EXCODER provides an effective, though imperfect, solution to this problem in automated code generation, offering developers the first way to implement ERC following test-driven development. When combined with Qwen 2.5 Coder 32b, EXCODER achieves pass@1, 5, and 10 rates of 85.92% (12.56 percentage points over baseline), 86.18% (12.82 p.p. over baseline), and 86.51% (13.15 p.p. over baseline), respectively, on developer-written test suites. Our manual inspection of the generated code further reveals limitations of EXCODER, pointing to directions for future work.

This paper describes the Rosetta system for Subtask 1 (Context-Aware English-to-Dialectal Arabic Dialogue Translation) of the AlexandriaX shared task, participating in both constrained and unconstrained tracks. The approach fine-tunes a LoRA adapter on NileChat-3B using structured system/user prompts that condition generation on dialect and dialogue context. For the unconstrained track, the adapter is additionally pretrained on MADAR and PADIC. Rosetta ranked 4th in the constrained track (spBLEU 26.10) and 5th in the unconstrained track (spBLEU 25.09). The experimental results demonstrate that external pretraining helps only two of thirteen dialects while slightly hurting overall performance, suggesting negative transfer.

Current audio-visual speech recognition (AVSR) benchmarks, like LRS3, rely heavily on clean, scripted and rehearsed speech. They fail to reflect the complexity of natural conversation, which involves overlapping speech, spontaneous turn-taking, unscripted vocabulary and variable acoustic conditions. To shift the field toward realistic dialogue, we introduce Candor-LR, a conversational benchmark derived from the CANDOR corpus of 1,656 natural dyadic videoconferences. Our custom data preparation pipeline yields 713.5, 10.1, and 60.1 hours of training, validation, and test data, respectively. Evaluating pretrained AVSR models on Candor-LR reveals that audio-only accuracy drops sharply compared to LRS3, but visual cues compensate effectively, driving much larger performance gains on Candor-LR than on LRS3. Furthermore, training on this corpus significantly improves cross-domain robustness under both clean and noisy conditions, as its realistic conversational data captures broader audio-video features. We open-source our pipeline to ensure reproducibility, establishing Candor-LR as a challenging benchmark for conversational AVSR.

Building fast charging stations (FCSs) is crucial for transportation electrification, but there exists an indirect network effect: while the increasing number of electric vehicles (EVs) decides the FCS capacity expansion, the spatial locations of these facilities strongly influence drivers' willingness to adopt EVs. Ignoring this interaction can lead to bad capital investments and exacerbate power grid vulnerabilities during tidal traffic peaks. Therefore, we explicitly model the EV adoption dynamics as decision-dependent uncertainties (DDUs) in a new multi-period collaborative planning framework. This framework evaluates the economic viability of V2G-enabled FCSs across both transportation and distribution networks. To simplify the complex calculation, we introduce an aggregated fleet virtual battery model to catch macroscopic vehicle-to-grid (V2G) flexibility. This successfully circumvents the dimension curse inherent in tracking microscopic state-of-charge. To further guarantee calculation speed, the nonlinear infrastructure exposure is transformed into a mixed-integer program by using Special Ordered Set type 2 (SOS2) variables and Second-Order Cone Programming (SOCP) relaxations for grid limits. Finally, numerical studies on a coupled Sioux Falls and IEEE 33-bus testbed prove that our framework achieves superior expected social welfare. Also, macroscopic V2G aggregation is highlighted for its capability to mitigate distribution grid congestion penalties.

Deformable convolution networks have recently become popular for many computer vision tasks, especially for semantic segmentation, because of their exceptional capabilities in dynamic spatial modeling. However, due to the dense deformable offsets and the lack of longer-range dependencies, they can not fully adopt proper and precise deformations for feature representations. To tackle the issues, in this paper, we propose Enhanced Deformable ConvNets (EDCN) for semantic segmentation. Specifically, a novel Enhanced Deformable Convolution (EDC) is exploited in the decoder, which integrates the Center-invariant Offset Module (COM) and Edge-aware Mask Module (EMM). The COM employs larger kernels and eliminates deformations at the kernel center, obtaining offsets that are more in line with the target from richer spatial information. Concurrently, the EMM obtains the significance of image content via Sobel edge detection, then selectively applies deformations based on the content significance, minimizing unnecessary deformations associated with relatively less important information, thereby avoiding impact from less informative regions. Experiments show that EDC outperforms state-of-the-art deformable convolution variants, including Deformable ConvNets V1-V4 and Entire Deformable ConvNets, across mainstream segmentation datasets with various decoder settings. Moreover, ablation studies confirm the effectiveness of each component. In addition, visualizations illustrate that EDC enhances spatial adaptation and target focus. We further analyze the extendibility of EDC to larger kernels on the image classification benchmark. Code will be publicly released.

Animation and VFX pre-production review requires teams to translate loosely specified creative intent–briefs, evolving specifications, heterogeneous references, and verbal decisions–into revisions that junior artists can execute without repeated clarification. In practice, criteria drift across iterations, review judgments lose their evidential basis, and the reasoning behind a request rarely survives the senior-junior handoff. We contribute a design framework for intent-evidence-action alignment: intent is articulated into a shared project record, judgments are anchored to grounded evidence, and authorized decisions are converted into clear revision tasks tied directly to reference notes. We instantiate this framework in MOONWALK, a professional pre-production review system comprising a shared intent record, reference/specification anchoring, structured work-in-progress comparison, and supervisor-authorized action planning. In this workflow, AI handles administrative coordination–flagging missing context and organizing notes–while artists retain full creative direction. An in-studio study with professional practitioners compares MOONWALK with a chat-only (chatbot) interface using matched production materials, while participants' existing workflows provide a retrospective ecological baseline. Results indicate stronger intent alignment, decision traceability, and checklist executability, while also showing that aesthetic authority and final prioritization must remain with practitioners. The evaluation establishes the value of the integrated structured workflow over unstructured conversational AI chatbot. Code: https://github.com/Akinesia112/Moonwalk/tree/english-version

Finding new physics (NP) is the most important problem in particle physics today. Studying “anomalies”, i.e., measurements of low-energy observables whose values disagree with the predictions of the Standard Model (SM), is a powerful search strategy. The SM Effective Field Theory (SMEFT) provides a general model-independent framework for parameterizing NP; it is natural to try to find the SMEFT operator(s) that can explain such anomalies. This is a challenging task because (i) the number of SMEFT operators is enormous, and (ii) at loop level there are very complicated correlations among the operators. Analyses by humans typically rely on phenomenological intuition to decide which operators are relevant. This is often biased and does not explore the complete SMEFT operator space. Interestingly, reinforcement learning (RL) techniques excel at tasks that require decision making to achieve their goals. In this paper, we introduce an RL method that can be used to find the SMEFT operators that explain any anomalies. We test it on the CDF $W$-mass anomaly, and show that it reproduces (and improves upon) known results. We then consider a far more complicated situation with multiple anomalies and show that, even here, this method is able to find the SMEFT operators that explain the data. Our RL method can therefore be used to efficiently search for NP at the level of SMEFT.

Safety is a fundamental requirement for autonomous driving, yet existing end-to-end driving models still lack explicit risk-aware learning capacities. Existing rule-based risk models provide interpretable safety priors, yet their absolute risk scores depend on handcrafted functions, coefficients, and thresholds. Learning-based risk representations reduce part of this manual design, but their supervision often relies on occupancy-derived labels or heuristic cost values, which may not capture ego-conditioned planning risk. In this paper, we propose DRiF, a data-driven risk-field framework for safer end-to-end autonomous driving. DRiF learns a shared BEV feature with static map segmentation, dynamic risk prediction, and vehicle planning. For dynamic risk learning, DRiF converts rule-based safety priors into pairwise risk labels, and trains the risk field to preserve relative risk ordering instead of regressing handcrafted absolute scores. Experiments on Bench2Drive show that DRiF achieves competitive overall performance, with consistent improvements in driving score, success rate, and collision-related metrics. These results establish relative risk supervision as an effective way to connect explicit safety structure with end-to-end planning. The data and code will be publicly available.

Sparse-view X-ray 3D reconstruction is essential for reducing radiation exposure, but recovering a density field from a handful of X-ray projections is severely ill-posed. Recently, 3D Gaussian Splatting has achieved state-of-the-art performance in sparse-view reconstruction by representing the volume using explicit, optimized primitives, but it requires dozens of projected views. With fewer views, reconstruction quality degrades severely since the explicit primitives are optimized freely without any anatomical information. Anatomical structures, in contrast, share similar geometry and density across a population. Their variations are bounded within a limited range that statistical shape models can capture. This paper proposes a shape-guided Gaussian splatting framework for sparse-view X-ray 3D reconstructions. Our contribution lies in driving Gaussian positions toward anatomically valid configurations, alongside atlas-based density regularization. Our method ensures anatomically consistent reconstruction and improves PSNR by 2.83 dB over a state-of-the-art Gaussian splatting baseline with as few as 5 views. Code Available: https://github.com/polyshape-lab/ShapeGuidedGaussian

A combination of Taylor polynomial approximation and averaging results in a powerful quasi-interpolation technique that can be used to analyze the approximation properties of finite element spaces. With this particular approach, the notion of affine equivalent families is completely bypassed in the sense that the degrees of freedom are defined locally rather than being exported from a reference element. In particular, domains with curved boundaries can be handled in a natural manner. Finally, the ease of its application to a particular finite element makes it a valuable pedagogical tool.

We present the PACE, a framework for retrieval-augmented dialogue serving that formalizes Perceived Time-to-First-Response (PTFR) as a QoE objective and minimizes it under quality/cost constraints. Unlike prior work on cascaded routing, semantic caching, or adaptive retrieval, PACE jointly controls which answer source composes the response and what fills the waiting window. Deployed on a humanoid-robot sales service, it combines three mechanisms: a load-adaptive cascading router, a joint path-filler controller, and volatility-aware cache admission. On 75k CarQA requests, the cascade halves pure-LLM PTFR at P95 (0.29 vs 0.53s at c16). The adaptive controller reaches 0.41s P95, outperforming RAG by 2.4 times at high load with equal quality. The filler controller cuts calls by 94% with zero conflict. Volatility-aware admission reduces stale answers from 86% to 0%. A gating rule ensures the controller never worse than the baseline, with exposure bounded by one hold period. This is the first quantification of filler-answer conflict risk in deployed services.

High-resolution water mapping supports environmental monitoring and related applications, but accurate pixel-level labels are difficult and costly to produce. Official hydrographic vectors provide scalable weak supervision, but they contain artifacts like boundary noise, temporal mismatch, and omissions of small water structures. We propose a two-stage framework for weakly supervised water segmentation in high resolution multispectral imagery. Stage 1 learns initial masks from rasterized vector pseudo-labels, and Stage 2 converts these masks into structured component-wise prompts for localized refinement. On a manually corrected validation set, refinement improves SegFormer-B0 from 0.9509 to 0.9535 IoU and U-Net from 0.9408 to 0.9486 IoU, with corresponding F1 gains from 0.9749 to 0.9762 and 0.9695 to 0.9736. It leads to sharper shorelines, reduced boundary spillover, and better thin-structure delineation. The results indicate that prompt-guided refinement can improve pseudo-label-based water segmentation by targeting local errors that are poorly captured by global training supervision.

Mean field planning on a surface prescribes initial and terminal densities and minimizes a transport energy subject to the continuity equation. Proximal algorithms for this problem repeatedly solve a time–space Poisson equation, whose temporal derivative and surface gradient determine the density and momentum corrections. We study a gradient-enhanced approximation of this constraint projection using finite differences in time, surface finite elements in space, temporal polynomial preserving recovery, and spatial parametric polynomial preserving recovery. The same construction is incorporated into ISTA, FISTA, and Douglas–Rachford splitting. We distinguish the recovered update from an exact discrete projection and derive residual identities and conditional finite-iteration perturbation bounds that retain data, boundary, and linear-solver errors. Existing derivative-recovery estimates identify a higher-order contribution under suitable regularity and mesh assumptions; they do not by themselves establish convergence of the outer optimization iteration. Available numerical illustrations on the sphere and a more complicated algebraic surface are discussed together with the limits of the recorded refinement data.

Nonlinear complexity is a fundamental criterion in the evaluation of pseudorandom sequences. The construction of multi-sequences with high nonlinear complexity is both theoretically and practically important in cryptography. Motivated by prior constructions of multi-sequences with high nonlinear complexity in [IEEE Trans. Inf. Theory, 60(10), 2014] and [IEEE Trans. Inf. Theory, 63(12), 2017], we provide a unified framework via narrow ray class fields and the cyclic descent introduced by Guruswami and Xing in [J. Combin. Theory Ser. A 129 (2015) ]. Then we can generate new multi-sequences with high nonlinear complexity over function fields with arbitrary genera.

Tensor compilers such as TinyTC and OpenAI Triton were originally developed for AI workloads, but the same tiling and memory abstractions can be applied to implement efficient high-order stencils for scientific and industrial applications. We demonstrate this for an 8th-order, 25-point acoustic stencil with boundary conditions over an a demanding-sized grid, targeting GPGPUs, where we compare the hardware-specialized TinyTC implementation with a portable PyTorch/Triton implementation. The target platforms for evaluation include Intel B70, B580, GPU MAX 1550, NVIDIA A100/RTX6000 Blackwell/H100, and AMD MI325x. For instance, on Battlemage B580 TinyTC reaches 15.6 Gpts/s versus 13.5 Gpts/s for PT/Triton under random initialization, while zero-initialized runs reach up to 35.8 Gpts/s due to hardware memory compression. Using roofline and memory-hierarchy profiling, we show that -as expected- performance is predominantly bandwidth-limited and that compiler-managed L1/LSC caching can effectively replace programmer-managed shared-memory staging for this stencil class. Overall, the results position TinyTC as the performance-oriented path on Intel hardware and PyTorch/Triton as a strong portability/productivity baseline for cross-vendor HPC stencil development.

While AVSR has achieved sub-1% word error rates on the standard LRS3 benchmark, its reliance on broadcast speech obscures whether this reflects true generalization or just domain adaptation. To investigate this gap, we evaluate three AVSR architectures across six conditions: controlled broadcast speech, fixed-grammar utterances, hyper-articulated Lombard speech, read speech from professional lipspeakers and non-professional speakers, and spontaneous multi-party video conversations. We find that visual-only performance deteriorates rapidly beyond broadcast domains, and audio-video fusion mainly benefits Lombard speech environments. Visual understanding degrades sharply at 90{\deg} profile views, with multimodal systems relying largely on acoustic fallback. Additionally, speaker articulation proves more critical than minor camera shifts, and LLM-based architectures suffer from poor out-of-domain generalization. Our work highlights a significant generalization gap in current AVSR research. To address this, we also introduce RoomReader-AV as a new benchmark for AVSR and release a unified data preprocessing pipeline to make comprehensive multi-condition evaluation accessible.

Simultaneous assessment of medical imaging and patient records is often required in clinical diagnosis. However, standard machine learning algorithms cannot analyze these data types together. Meanwhile, compliance with HIPAA and GDPR can constrain centralized aggregation of sensitive patient data. This leaves a crucial void of secure fusion of visual and textual context across distant networks. Thus, we present OmniMed-FL, a controlled systems study of multimodal federated learning for five-class clinical condition classification (Normal, Pneumonia, COVID-19, Pleural Effusion, Cardiomegaly). Our proxy corpus pairs 3,000 public chest radiographs with 3,000 class-conditioned synthetic notes, matched by class, not by patient. The framework benchmarks eight fusion strategies, three initializations, four missing-text imputation rules, and matched federated baselines under non-IID Dirichlet partitioning across 3 to 20 hospital clients. As all notes are synthetic and pairing is not patient-level, these are descriptive proxy comparisons, not estimates of diagnostic performance or deployment readiness. Within those limits with clients ($K=5$) and severe skew ($\alpha=0.1$), local-only training achieves a macro-F1 score of 0.297, FedAvg achieves $0.662\pm0.074$, FedProx $0.737\pm0.085$, a matched FedMME-style one-shot ensemble $0.647\pm0.080$, and our SCAFFOLD-AdamW adaptation $0.070\pm0.015$, the 0.075 FedProx-FedAvg gap falling inside the wider of the two two-seed standard deviations. Over a $4\times3$ grid, label skew costs up to 0.27 F1 whereas a near-sevenfold client increase costs at most 0.10, while bidirectional volume grows linearly to 183.5 GiB at $K=20$. Multimodal fusion leads on both corpora, scoring 0.956 against 0.934 for text and 0.664 for images on the synthetic corpus and 0.906 against 0.880 and 0.737 on the radiograph corpus, for $2.3\times$ the model state of text alone.

SceneHI is a framework that lifts high-resolution, illumination-aware priors from 2D diffusion models to perform 3D texture synthesis. It is the first to demonstrate that high-resolution textures, previously limited to 2D synthesis, can be generated directly on 3D objects without model fine-tuning or optimization. Designed for complex, multi-object environments, SceneHI uniquely combines 3D-consistency, high-resolution fidelity, and physically plausible baked shadows within a single generative pipeline. To enforce strict geometric coherence, we introduce an exact analytical pixel-to-texel mapping that aligns diffusion trajectories across multiple viewpoints. We utilize High-Resolution Latent Textures (HRLTs) as a persistent canvas for gradually denoised textures, while camera views perform the denoising steps in latent pixel space. This ensures a shared base texture that can be subsequently refined to high resolution without compromising multi-view consistency. Finally, a light-aware generative pass embeds realistic geometry-consistent shadows directly into the atlases, bridging the gap to production workflows. SceneHI achieves high visual fidelity while reducing generation time by 80% compared to existing scene-level methods.

Time-series foundation models are evaluated almost exclusively on public archives that predate them, so a strong score cannot be separated from having seen the test set during pretraining. The obvious remedy is a hold-out that postdates the models. We build one: thirteen forecasters – four classical, three trained per dataset, six pretrained – on seven groups drawn from five domains, every observation published after the last model was released, and every dataset rebuildable without an API key. Under this protocol pretrained models win 5 of 7 groups, lose one to a Theta baseline, and on daily exchange rates are indistinguishable from a seasonal naive forecast, along with every other method tested. We then ask what separates the wins from the losses, and report a negative result: the two intrinsic properties one would reach for – seasonal strength and spectral entropy, measured on the input window – do not account for the pattern, and seasonal strength is if anything negatively associated with the advantage. What does track it is corpus familiarity. Our largest gain (28% lower MASE than the best classical method, on weekly Wikipedia pageviews) falls on Wikipedia pageviews, the domain TimesFM's authors describe as the bulk of its pretraining corpus, at the same granularities and differing only in time window. Within the pretrained family, where every model forecasts identical series so that series difficulty cancels, the TimesFM family outranks the Chronos family by -0.53 ranks on Wikipedia against -0.09 everywhere else (1,500 vs. 754 series, Mann-Whitney p < 1e-5). We conclude that a temporal hold-out removes memorisation of a window but not familiarity with a domain, that benchmarks therefore need domain hold-outs stated relative to disclosed corpora, and that the practitioner's question is less which model is better than whether their domain is one the model was raised on.

Long-term change understanding from images of the same place revisited over time is a challenging task with applications in map maintenance and urban infrastructure monitoring. Prior work addresses it either through pixel-level prediction or difference captioning, neither of which is sufficient to reliably measure how well models detect and describe such changes. We introduce SPOT-THE-SHIFT, a human-verified benchmark for grounded image difference captioning of long-term changes in real-world driving scenes. Our benchmark provides natural language captions and spatial masks for structural changes across each image pair. We further propose an evaluation protocol that reliably assesses models' captioning ability, validated through human studies. Benchmarking state-of-the-art MLLMs, we find that models struggle with the fine-grained multi-image spatial capability required for this task. Finally, we develop a synthetic data generation pipeline that improves an off-the-shelf MLLM without sacrificing general capabilities.

Video understanding has rapidly evolved toward video large language models (VideoLLMs): systems that couple video representations with pretrained large language models and condition generation on a textual prompt. Their strong performance on captioning, question answering, retrieval and temporal grounding comes at a computation and memory cost that grows with frame count and context length, limiting deployment in real-time, mobile and resource-constrained settings. This survey covers inference-efficiency mechanisms for visual and audiovisual VideoLLMs that report concrete reductions in parameter count, FLOPs per input, latency, memory, or visual and audio token count. We analyze bottlenecks across frame sampling, modality encoding, connector-level token reduction, and LLM prefilling and decoding. We organize methods by the pipeline stage at which they act, covering VideoLLMs developed since late 2022 together with earlier frame-sampling and vision-encoder mechanisms that remain components of current pipelines. We assemble literature-reported accuracy–cost comparisons under shared host models and input protocols wherever available, distinguish them from heterogeneous cross-paper evidence, and identify gaps in audiovisual efficiency and standardized evaluation. We maintain a repository at https://github.com/momentslab/awesome-efficient-videollm.

Large audio language models (LALMs) have shown promising progress in broad music-understanding tasks such as tagging, retrieval, and captioning. Music understanding that requires finer hearing over both the content and how it is realized within a performance through dynamics, phrasing, articulation, time, and other performance techniques, however, remains at an earlier stage. Existing audio-language model (ALM) training pipelines typically rely on coarse, weakly grounded captions and therefore provide little support for learning these subtle nuances in music, limiting their ability to serve real-world applications in education or artistic practice. We therefore introduce MuNo-SP (Music Notation unifying Score and Performance), a text-based representation that jointly encodes score content and performance information. Building on MuNo-SP, we develop an automatic training-data generation pipeline that uses aligned scores and performances to produce long-form auditory analyses and musically informed question-answer pairs. We use this pipeline to construct MAESTROCaps, a classical piano dataset comprising 148 long-form performance analyses and 31,080 question-answer pairs derived from 148 aligned score-performance pairs. In a human evaluation, MuNo-SP analyses were preferred by majority vote over MIDI-only analyses for eight of nine excerpts. MuNo-SP also performed strongly on a benchmark of score-performance understanding, suggesting that integrating score and performance information enables more reliable and musically informative LALM supervision than a MIDI-only baseline.

The banking system now depends on a small set of shared artificial intelligence vendors for fraud screening, credit decisioning, anti-money-laundering triage, customer analytics, and internal decision support. This paper studies how a compromise inside one of those vendors can propagate along a chain of operational, informational, and financial linkages until it triggers losses that look, from the outside, like a classical banking crisis. We build a four-layer heterogeneous network that couples AI vendors, financial institutions, interbank exposures, and customer accounts, and we propose CFC-Prop, a stochastic epidemic-and-clearing model that runs on that network. On a synthetic dataset with 60 vendors, 220 banks, roughly 2,500 vendor-bank service edges, and 1,400 interbank exposures, CFC-Prop reproduces the heavy-tailed loss distributions and the sharp dependence on patch latency that are consistent with prior cyber-financial evidence. We also train an early-warning model, CFC-GNN, that uses vendor-side incident telemetry and graph structure to flag high-cascade-risk vendors before impact. Across four baselines the proposed model reaches AUROC 0.82 and AUPRC 0.60 while keeping calibration errors bounded. We release the full code, synthetic data, and reproducible scripts. The results argue that cyber concentration among AI vendors is a first-order financial-stability problem and give supervisors a concrete quantitative tool for reasoning about it.

Data-intensive applications move large amounts of data from storage to the compute unit, incurring significant data movement overhead. Storage-centric computing reduces this overhead by moving computation near or inside solid-state drives (SSDs). Enabling it requires modifying SSD policies, e.g., address translation and garbage collection, which are part of the Flash Translation Layer (FTL), the SSD's firmware. Modifying the FTL is error-prone. Because FTL logic has direct access to security-critical device components, even a functionally correct FTL can leak data between tenants, drop integrity tags, or assign a flash block to the wrong tenant. We show that a faulty FTL can corrupt the device state at five surfaces inside the SSD, and demonstrate them on a DaisyPlus OpenSSD. Prior work verifies individual FTL designs, but has two limitations. (1) It establishes only functional correctness, so a modified FTL can violate isolation, integrity, and ownership and still pass verification. (2) It is tied to a single FTL design, so every modification requires redoing every proof. We propose CertiFlash, a formal verification framework for FTLs, mechanized in the Rocq proof assistant, that gives designers a machine-checked proof of security and correctness. CertiFlash models an FTL as a deterministic state machine with a single global invariant over mapping, isolation, integrity, ownership, and allocation. We prove once, over a general FTL model, that (i) every FTL operation preserves the invariant and (ii) the model refines an idealized block device. For a new design, a designer discharges five hypotheses about its own operations instead of redoing either proof. Across four case studies, a designer adds 27 to 3,231 lines against a 16,489-line framework, significantly reducing the verification effort. CertiFlash is open source.