arXiv2026-04-23
Yen-Siang Wu, Rundong Luo, Jingsen Zhu, Tao Tu, Ali Farhadi et al.
How can we tell whether a video has been sped up or slowed down? How can we generate videos at different speeds? Although videos have been central to modern computer vision research, little attention has been paid to perceiving and controlling the passage of time. In this paper, we study time as a learnable visual concept and develop models for reasoning about and manipulating the flow of time in videos. We first exploit the multimodal cues and temporal structure naturally present in videos to learn, in a self-supervised manner, to detect speed changes and estimate playback speed. We then show that these learned temporal reasoning models enable us to curate the largest slow-motion video dataset to date from noisy in-the-wild sources. Such slow-motion footage, typically filmed by high-speed cameras, contains substantially richer temporal detail than standard videos. Using this data, we further develop models capable of temporal control, including speed-conditioned video generation, which produces motion at specified playback speed, and temporal super-resolution, which tranforms low-FPS, blurry videos into high-FPS sequences with fine-grained temporal details. Our findings highlight time as a manipulable, perceptual dimension in video learning, opening doors to temporally controllable video generation, temporal forensics detection, and potentially richer world-models that understand how events unfold over time.
arXiv2026-04-23
Nicolae Filat, Ahmed Hussain, Konstantinos Kalogiannis, Elena Burceanu
Streaming Continual Learning (CL) typically converts a continuous stream into a sequence of discrete tasks through temporal partitioning. We argue that this temporal taskification step is not a neutral preprocessing choice, but a structural component of evaluation: different valid splits of the same stream can induce different CL regimes and therefore different benchmark conclusions. To study this effect, we introduce a taskification-level framework based on plasticity and stability profiles, a profile distance between taskifications, and Boundary-Profile Sensitivity (BPS), which diagnoses how strongly small boundary perturbations alter the induced regime before any CL model is trained. We evaluate continual finetuning, Experience Replay, Elastic Weight Consolidation, and Learning without Forgetting on network traffic forecasting with CESNET-Timeseries24, keeping the stream, model, and training budget fixed while varying only the temporal taskification. Across 9-, 30-, and 44-day splits, we observe substantial changes in forecasting error, forgetting, and backward transfer, showing that taskification alone can materially affect CL evaluation. We further find that shorter taskifications induce noisier distribution-level patterns, larger structural distances, and higher BPS, indicating greater sensitivity to boundary perturbations. These results show that benchmark conclusions in streaming CL depend not only on the learner and the data stream, but also on how that stream is taskified, motivating temporal taskification as a first-class evaluation variable.
arXiv2026-04-23
Thibault Bañeras-Roux, Shashi Kumar, Driss Khalil, Sergio Burdisso, Petr Motlicek et al.
Automatic Speech Recognition (ASR) is traditionally evaluated using Word Error Rate (WER), a metric that is insensitive to meaning. Embedding-based semantic metrics are better correlated with human perception, but decoder-based Large Language Models (LLMs) remain underexplored for this task. This paper evaluates their relevance through three approaches: (1) selecting the best hypothesis between two candidates, (2) computing semantic distance using generative embeddings, and (3) qualitative classification of errors. On the HATS dataset, the best LLMs achieve 92--94\% agreement with human annotators for hypothesis selection, compared to 63\% for WER, also outperforming semantic metrics. Embeddings from decoder-based LLMs show performance comparable to encoder models. Finally, LLMs offer a promising direction for interpretable and semantic ASR evaluation.
arXiv2026-04-23
Paul-Tiberiu Iordache, Elena Burceanu
Continual learning (CL) studies how models acquire tasks sequentially while retaining previously learned knowledge. Despite substantial progress in benchmarking CL methods, comparative evaluations typically keep the fine-tuning regime fixed. In this paper, we argue that the fine-tuning regime, defined by the trainable parameter subspace, is itself a key evaluation variable. We formalize adaptation regimes as projected optimization over fixed trainable subspaces, showing that changing the trainable depth alters the effective update signal through which both current task fitting and knowledge preservation operate. This analysis motivates the hypothesis that method comparisons need not be invariant across regimes. We test this hypothesis in task incremental CL, five trainable depth regimes, and four standard methods: online EWC, LwF, SI, and GEM. Across five benchmark datasets, namely MNIST, Fashion MNIST, KMNIST, QMNIST, and CIFAR-100, and across 11 task orders per dataset, we find that the relative ranking of methods is not consistently preserved across regimes. We further show that deeper adaptation regimes are associated with larger update magnitudes, higher forgetting, and a stronger relationship between the two. These results show that comparative conclusions in CL can depend strongly on the chosen fine-tuning regime, motivating regime-aware evaluation protocols that treat trainable depth as an explicit experimental factor.
arXiv2026-04-23
Natalie Collina, Jiuyao Lu, Georgy Noarov, Aaron Roth
We study the minimax sample complexity of multicalibration in the batch setting. A learner observes $n$ i.i.d. samples from an unknown distribution and must output a (possibly randomized) predictor whose population multicalibration error, measured by Expected Calibration Error (ECE), is at most $\varepsilon$ with respect to a given family of groups. For every fixed $κ> 0$, in the regime $|G|\le \varepsilon^{-κ}$, we prove that $\widetildeΘ(\varepsilon^{-3})$ samples are necessary and sufficient, up to polylogarithmic factors. The lower bound holds even for randomized predictors, and the upper bound is realized by a randomized predictor obtained via an online-to-batch reduction. This separates the sample complexity of multicalibration from that of marginal calibration, which scales as $\widetildeΘ(\varepsilon^{-2})$, and shows that mean-ECE multicalibration is as difficult in the batch setting as it is in the online setting, in contrast to marginal calibration which is strictly more difficult in the online setting. In contrast we observe that for $κ= 0$, the sample complexity of multicalibration remains $\widetildeΘ(\varepsilon^{-2})$ exhibiting a sharp threshold phenomenon. More generally, we establish matching upper and lower bounds, up to polylogarithmic factors, for a weighted $L_p$ multicalibration metric for all $1 \le p \le 2$, with optimal exponent $3/p$. We also extend the lower-bound template to a regular class of elicitable properties, and combine it with the online upper bounds of Hu et al. (2025) to obtain matching bounds for calibrating properties including expectiles and bounded-density quantiles.
arXiv2026-04-23
Zhiqiu Xu, Shibo Jin, Shreya Arya, Mayur Naik
As frontier language models attain near-ceiling performance on static mathematical benchmarks, existing evaluations are increasingly unable to differentiate model capabilities, largely because they cast models solely as solvers of fixed problem sets. We introduce MathDuels, a self-play benchmark in which models occupy dual roles: each authors math problems under adversarial prompting and solves problems authored by every other participant. Problems are produced through a three-stage generation pipeline (meta-prompting, problem generation, and difficulty amplification), and validated by an independent verifier that excludes ill-posed questions. A Rasch model (Rasch, 1993) jointly estimates solver abilities and problem difficulties; author quality is derived from the difficulties of each model's authored problems. Experiments across 19 frontier models reveal that authoring and solving capabilities are partially decoupled, and that dual-role evaluation reveals capability separations invisible in single-role benchmarks. As newer models enter the arena, they produce problems that defeat previously dominant solvers, so the benchmark's difficulty co-evolves with participant strength rather than saturating at a fixed ceiling. We host a public leaderboard that updates as new models are released.
arXiv2026-04-23
Pegah Khayatan, Jayneel Parekh, Arnaud Dapogny, Mustafa Shukor, Alasdair Newson et al.
Despite impressive progress in capabilities of large vision-language models (LVLMs), these systems remain vulnerable to hallucinations, i.e., outputs that are not grounded in the visual input. Prior work has attributed hallucinations in LVLMs to factors such as limitations of the vision backbone or the dominance of the language component, yet the relative importance of these factors remains unclear. To resolve this ambiguity, We propose HalluScope, a benchmark to better understand the extent to which different factors induce hallucinations. Our analysis indicates that hallucinations largely stem from excessive reliance on textual priors and background knowledge, especially information introduced through textual instructions. To mitigate hallucinations induced by textual instruction priors, we propose HalluVL-DPO, a framework for fine-tuning off-the-shelf LVLMs towards more visually grounded responses. HalluVL-DPO leverages preference optimization using a curated training dataset that we construct, guiding the model to prefer grounded responses over hallucinated ones. We demonstrate that our optimized model effectively mitigates the targeted hallucination failure mode, while preserving or improving performance on other hallucination benchmarks and visual capability evaluations. To support reproducibility and further research, we will publicly release our evaluation benchmark, preference training dataset, and code at https://pegah-kh.github.io/projects/prompts-override-vision/ .
arXiv2026-04-23
Bartosz Balis, Michal Orzechowski, Piotr Kica, Michal Dygas, Michal Kuszewski
Scientific workflow systems automate execution -- scheduling, fault tolerance, resource management -- but not the semantic translation that precedes it. Scientists still manually convert research questions into workflow specifications, a task requiring both domain knowledge and infrastructure expertise. We propose an agentic architecture that closes this gap through three layers: an LLM interprets natural language into structured intents (semantic layer); validated generators produce reproducible workflow DAGs (deterministic layer); and domain experts author ``Skills'': markdown documents encoding vocabulary mappings, parameter constraints, and optimization strategies (knowledge layer). This decomposition confines LLM non-determinism to intent extraction: identical intents always yield identical workflows. We implement and evaluate the architecture on the 1000 Genomes population genetics workflow and Hyperflow WMS running on Kubernetes. In an ablation study on 150 queries, Skills raise full-match intent accuracy from 44% to 83%; skill-driven deferred workflow generation reduces data transfer by 92\%; and the end-to-end pipeline completes queries on Kubernetes with LLM overhead below 15 seconds and cost under $0.001 per query.
arXiv2026-04-23
Bingcong Li, Yilang Zhang, Georgios B. Giannakis
Low-rank adaptation (LoRA) has emerged as the de facto standard for parameter-efficient fine-tuning (PEFT) of foundation models, enabling the adaptation of billion-parameter networks with minimal computational and memory overhead. Despite its empirical success and rapid proliferation of variants, it remains elusive which architectural choices, optimization techniques, and deployment constraints should guide practical method selection. This overview revisits LoRA through the lens of signal processing (SP), bridging modern adapter designs with classical low-rank modeling tools and inverse problems, as well as highlighting how SP principles can inform principled advances of fine-tuning approaches. Rather than providing a comprehensive enumeration and empirical comparisons of LoRA variants, emphasis is placed on the technical mechanisms underpinning these approaches to justify their effectiveness. These advances are categorized into three complementary axes: architectural design, efficient optimization, and pertinent applications. The first axis builds on singular value decomposition (SVD)-based factorization, rank-augmentation constructions, and cross-layer tensorization, while the second axis deals with initialization, alternating solvers, gauge-invariant optimization, and parameterization-aware methods. Beyond fine-tuning, emerging applications of LoRA are accounted across the entire lifecycle of large models, ranging from pre- and post-training to serving/deployment. Finally, open research directions are outlined at the confluence of SP and deep learning to catalyze a bidirectional frontier: classical SP tools provide a principled vocabulary for designing principled PEFT methods, while the unique challenges facing modern deep learning, especially the overwhelming scale and prohibitive overhead, also offer new research lines benefiting the SP community in return.
arXiv2026-04-23
Max Defez, Filippo Quarenghi, Mathieu Vrac, Stephan Mandt, Tom Beucler
Deep-learning video super-resolution has progressed rapidly, but climate applications typically super-resolve (increase resolution) either space or time, and joint spatiotemporal models are often designed for a single pair of super-resolution (SR) factors (upscaling spatial and temporal ratio between the low-resolution sequence and the high-resolution sequence), limiting transfer across spatial resolutions and temporal cadences (frame rates). We present a scale-adaptive framework that reuses the same architecture across factors by decomposing spatiotemporal SR into a deterministic prediction of the conditional mean, with attention, and a residual conditional diffusion model, with an optional mass-conservation (same precipitation amount in inputs and outputs) transform to preserve aggregated totals. Assuming that larger SR factors primarily increase underdetermination (hence required context and residual uncertainty) rather than changing the conditional-mean structure, scale adaptivity is achieved by retuning three factor-dependent hyperparameters before retraining: the diffusion noise schedule amplitude beta (larger for larger factors to increase diversity), the temporal context length L (set to maintain comparable attention horizons across cadences) and optionally a third, the mass-conservation function f (tapered to limit the amplification of extremes for large factors). Demonstrated on reanalysis precipitation over France (Comephore), the same architecture spans super-resolution factors from 1 to 25 in space and 1 to 6 in time, yielding a reusable architecture and tuning recipe for joint spatiotemporal super-resolution across scales.
arXiv2026-04-23
Neeraj Gangwar, Rishabh Deshmukh, Michael Shavlovsky, Hancao Li, Vivek Mittal et al.
As model sizes continue to grow, parameter-efficient fine-tuning has emerged as a powerful alternative to full fine-tuning. While LoRA is widely adopted among these methods, recent research has explored vector-based adaptation methods due to their extreme parameter efficiency. However, these methods typically require substantially higher ranks than LoRA to match its performance, leading to increased training costs. This work introduces GiVA, a gradient-based initialization strategy for vector-based adaptation. It achieves training times comparable to LoRA and maintains the extreme parameter efficiency of vector-based adaptation. We evaluate GiVA across diverse benchmarks, including natural language understanding, natural language generation, and image classification. Experiments show that our approach consistently outperforms or achieves performance competitive with existing vector-based adaptation methods and LoRA while reducing rank requirements by a factor of eight ($8\times$).
arXiv2026-04-23
Flávio Soriano, Victoria F. Mello, Pedro B. Rigueira, Gisele L. Pappa, Wagner Meira et al.
Analyses of legislative behavior often rely on voting records, overlooking the rich semantic and rhetorical content of political speech. In this paper, we ask three complementary questions about parliamentary discourse: how things are said, what is being said, and who is speaking in discursively similar ways. To answer these questions, we introduce a scalable and generalizable computational framework that combines diachronic stylometric analysis, contextual topic modeling, and semantic clustering of deputies' speeches. We apply this framework to a large-scale case study of the Brazilian Chamber of Deputies, using a corpus of over 450,000 speeches from 2003 to 2025. Our results show a long-term stylistic shift toward shorter and more direct speeches, a legislative agenda that reorients sharply in response to national crises, and a granular map of discursive alignments in which regional and gender identities often prove more salient than formal party affiliation. More broadly, this work offers a robust methodology for analyzing parliamentary discourse as a multidimensional phenomenon that complements traditional vote-based approaches.
arXiv2026-04-23
Chee Wei Tan, Yuchen Wang, Shangxin Guo
This paper introduces a new paradigm for AI game programming, leveraging large language models (LLMs) to extend and operationalize Claude Shannon's taxonomy of game-playing machines. Central to this paradigm is Nemobot, an interactive agentic engineering environment that enables users to create, customize, and deploy LLM-powered game agents while actively engaging with AI-driven strategies. The LLM-based chatbot, integrated within Nemobot, demonstrates its capabilities across four distinct classes of games. For dictionary-based games, it compresses state-action mappings into efficient, generalized models for rapid adaptability. In rigorously solvable games, it employs mathematical reasoning to compute optimal strategies and generates human-readable explanations for its decisions. For heuristic-based games, it synthesizes strategies by combining insights from classical minimax algorithms (see, e.g., shannon1950chess) with crowd-sourced data. Finally, in learning-based games, it utilizes reinforcement learning with human feedback and self-critique to iteratively refine strategies through trial-and-error and imitation learning. Nemobot amplifies this framework by offering a programmable environment where users can experiment with tool-augmented generation and fine-tuning of strategic game agents. From strategic games to role-playing games, Nemobot demonstrates how AI agents can achieve a form of self-programming by integrating crowdsourced learning and human creativity to iteratively refine their own logic. This represents a step toward the long-term goal of self-programming AI.
arXiv2026-04-23
Sherly Alfonso-Sánchez, Cristián Bravo, Kristina G. Stankova
Geographic context is often consider relevant to motor insurance risk, yet public actuarial datasets provide limited location identifiers, constraining how this information can be incorporated and evaluated in claim-frequency models. This study examines how geographic information from alternative data sources can be incorporated into actuarial models for Motor Third Party Liability (MTPL) claim prediction under such constraints. Using the BeMTPL97 dataset, we adopt a zone-level modeling framework and evaluate predictive performance on unseen postcodes. Geographic information is introduced through two channels: environmental indicators from OpenStreetMap and CORINE Land Cover, and orthoimagery released by the Belgian National Geographic Institute for academic use. We evaluate the predictive contribution of coordinates, environmental features, and image embeddings across three baseline models: generalized linear models (GLMs), regularized GLMs, and gradient-boosted trees, while raw imagery is modeled using convolutional neural networks. Our results show that augmenting actuarial variables with constructed geographic information improves accuracy. Across experiments, both linear and tree-based models benefit most from combining coordinates with environmental features extracted at 5 km scale, while smaller neighborhoods also improve baseline specifications. Generally, image embeddings do not improve performance when environmental features are available; however, when such features are absent, pretrained vision-transformer embeddings enhance accuracy and stability for regularized GLMs. Our results show that the predictive value of geographic information in zone-level MTPL frequency models depends less on model complexity than on how geography is represented, and illustrate that geographic context can be incorporated despite limited individual-level spatial information.
arXiv2026-04-23
Muhy Eddin Za'ter, Anna Van Boven, Bri-Mathias Hodge, Kyri Baker
Maintaining instantaneous balance between electricity supply and demand is critical for reliability and grid instability. System operators achieve this through solving the task of Unit Commitment (UC),ca high dimensional large-scale Mixed-integer Linear Programming (MILP) problem that is strictly and heavily governed by the grid physical constraints. As grid integrate variable renewable sources, and new technologies such as long duration storage in the grid, UC must be optimally solved for multi-day horizons and potentially with greater frequency. Therefore, traditional MILP solvers increasingly struggle to compute solutions within these tightening operational time limits. To bypass these computational bottlenecks, this paper proposes a novel framework utilizing a transformer-based architecture to predict generator commitment schedules over a 72-hour horizon. Also, because raw predictions in highly dimensional spaces often yield physically infeasible results, the pipeline integrates the self-attention network with deterministic post-processing heuristics that systematically enforce minimum up/down times and minimize excess capacity. Finally, these refined predictions are utilized as a warm start for a downstream MILP solver, while employing a confidence-based variable fixation strategy to drastically reduce the combinatorial search space. Validated on a single-bus test system, the complete multi-stage pipeline achieves 100\% feasibility and significantly accelerates computation times. Notably, in approximately 20\% of test instances, the proposed model reached a feasible operational schedule with a lower overall system cost than relying solely on the solver.
arXiv2026-04-23
Praval Sharma, Ashok Samal, Leen-Kiat Soh, Deepti Joshi
Event extraction identifies the central aspects of events from text. It supports event understanding and analysis, which is crucial for tasks such as informed decision-making in emergencies. Therefore, it is necessary to develop automated event extraction approaches. However, existing datasets for algorithm development have limitations, including limited coverage of event types in closed-domain settings and a lack of large, manually verified dataset in open-domain settings. To address these limitations, we create EVENT5Ws , a large, manually annotated, and statistically verified open-domain event extraction dataset. We design a systematic annotation pipeline to create the dataset and provide empirical insights into annotation complexity. Using EVENT5Ws, we evaluate state-of-the-art pre-trained large language models and establish a benchmark for future research. We further show that models trained on EVENT5Ws generalize effectively to datasets from different geographical contexts, which demonstrates its potential for developing generalizable algorithms. Finally, we summarize the lessons learned during the dataset development and provide recommendations to support future large-scale dataset development.
arXiv2026-04-23
Jun Wang, Ziyin Zhang, Rui Wang, Hang Yu, Peng Di et al.
Real-time detection and mitigation of technical anomalies are critical for large-scale cloud-native services, where even minutes of downtime can result in massive financial losses and diminished user trust. While customer incidents serve as a vital signal for discovering risks missed by monitoring, extracting actionable intelligence from this data remains challenging due to extreme noise, high throughput, and semantic complexity of diverse business lines. In this paper, we present TingIS, an end-to-end system designed for enterprise-grade incident discovery. At the core of TingIS is a multi-stage event linking engine that synergizes efficient indexing techniques with Large Language Models (LLMs) to make informed decisions on event merging, enabling the stable extraction of actionable incidents from just a handful of diverse user descriptions. This engine is complemented by a cascaded routing mechanism for precise business attribution and a multi-dimensional noise reduction pipeline that integrates domain knowledge, statistical patterns, and behavioral filtering. Deployed in a production environment handling a peak throughput of over 2,000 messages per minute and 300,000 messages per day, TingIS achieves a P90 alert latency of 3.5 minutes and a 95\% discovery rate for high-priority incidents. Benchmarks constructed from real-world data demonstrate that TingIS significantly outperforms baseline methods in routing accuracy, clustering quality, and Signal-to-Noise Ratio.
arXiv2026-04-23
Praval Sharma
Event extraction is essential for event understanding and analysis. It supports tasks such as document summarization and decision-making in emergency scenarios. However, existing event extraction approaches have limitations: (1) closed-domain algorithms are restricted to predefined event types and thus rarely generalize to unseen types and (2) open-domain event extraction algorithms, capable of handling unconstrained event types, have largely overlooked the potential of large language models (LLMs) despite their advanced abilities. Additionally, they do not explicitly model document-level contextual, structural, and semantic reasoning, which are crucial for effective event extraction but remain challenging for LLMs due to lost-in-the-middle phenomenon and attention dilution. To address these limitations, we propose multimodal open-domain event extraction, MODEE , a novel approach for open-domain event extraction that combines graph-based learning with text-based representation from LLMs to model document-level reasoning. Empirical evaluations on large datasets demonstrate that MODEE outperforms state-of-the-art open-domain event extraction approaches and can be generalized to closed-domain event extraction, where it outperforms existing algorithms.
arXiv2026-04-23
Yuto Nishida, Naoki Shikoda, Yosuke Kishinami, Ryo Fujii, Makoto Morishita et al.
Understanding what kinds of factual knowledge large language models (LLMs) memorize is essential for evaluating their reliability and limitations. Entity-based QA is a common framework for analyzing non-verbatim memorization, but typical evaluations query each entity using a single canonical surface form, making it difficult to disentangle fact memorization from access through a particular name. We introduce RedirectQA, an entity-based QA dataset that uses Wikipedia redirect information to associate Wikidata factual triples with categorized surface forms for each entity, including alternative names, abbreviations, spelling variants, and common erroneous forms. Across 13 LLMs, we examine surface-conditioned factual memorization and find that prediction outcomes often change when only the entity surface form changes. This inconsistency is category-dependent: models are more robust to minor orthographic variations than to larger lexical variations such as aliases and abbreviations. Frequency analyses further suggest that both entity- and surface-level frequencies are associated with accuracy, and that entity frequency often contributes beyond surface frequency. Overall, factual memorization appears neither purely surface-specific nor fully surface-invariant, highlighting the importance of surface-form diversity in evaluating non-verbatim memorization.
arXiv2026-04-23
Umar Masud, Abhijith Punnappurath, Luxi Zhao, David B. Lindell, Michael S. Brown
The ability of generative AI (GenAI) methods to photorealistically alter camera images has raised awareness about the authenticity of images shared online. Interestingly, images captured directly by our cameras are considered authentic and faithful. However, with the increasing integration of deep-learning modules into cameras' capture-time hardware -- namely, the image signal processor (ISP) -- there is now a potential for hallucinated content in images directly output by our cameras. Hallucinated capture-time image content is typically benign, such as enhanced edges or texture, but in certain operations, such as AI-based digital zoom or low-light image enhancement, hallucinations can potentially alter the semantics and interpretation of the image content. As a result, users may not realize that the content in their camera images is not authentic. This paper addresses this issue by enabling users to recover the 'unhallucinated' version of the camera image to avoid misinterpretation of the image content. Our approach works by optimizing an image-specific multi-layer perceptron (MLP) decoder together with a modality-specific encoder so that, given the camera image, we can recover the image before hallucinated content was added. The encoder and MLP are self-contained and can be applied post-capture to the image without requiring access to the camera ISP. Moreover, the encoder and MLP decoder require only 180 KB of storage and can be readily saved as metadata within standard image formats such as JPEG and HEIC.