Peirong Zhang, Zhenhua Yang, Jiaxin Zhang, Moises Diaz, Miguel A. Ferrer, Umapada Pal, Wei Zhou, Lianwen Jin
Handwritten signature verification (HSV) is a critical biometric technique in legal and forensic authentication, whose efficacy hinges on the discriminability of signature representations. Current HSV methods predominantly adopt supervised learning to enhance representation quality, leaving self-supervised learning largely unexplored. We propose \emph{SigDiffuser}, a diffusion-based self-supervised framework for signature representation and verification. At its core, \emph{SigDiffuser} introduces a novel pretext task termed \emph{Reconstruction from Ruins (RFR)}, which deliberately ``ruins'' signatures through severe crumpling, obliterating their structural integrity and writing styles. A visual encoder is employed to capture crucial handwriting patterns from intact signature regions, guiding the denoiser to reconstruct the ``ruined'' portions and learning meaningful representations. Additionally, we introduce a \emph{pyramidal feature aggregation module (PFAM)} to bridge the visual encoder and denoiser, enhancing representation quality via hierarchical aggregation and modulation. Extensive experiments on multilingual signature datasets demonstrate that \emph{SigDiffuser} significantly outperforms both state-of-the-art SSL methods and HSV models. We further show that increasing the crumpling severity on signatures effectively improves representation quality. Notably, our work demonstrates that extreme destruction, coupled with self-supervised diffusion models, can yield superior signature representation compared to traditional mild deformations, paving new avenues for HSV and other biometric domains. Code will be publicly available.
Hong-Su Nam, Seokhwan Lee, Jungwoo Cho, Hak-Tae Lee
A sequential engineering framework is presented for urban drone delivery, linking hub location, route planning, mission-specific vehicle sizing, and energy and operating cost assessment. Aggregate origin-destination demand is assumed known a priori. For each hub configuration, the maximum required link distance is minimized, and feasible routes that return to their departure hubs are generated. Route frequencies are determined using mixed-integer linear programming to satisfy delivery demand. The resulting range requirement guides motor-propeller selection and battery sizing to minimize vehicle takeoff mass. Flight distances and frequencies, cruise performance, and vehicle dimensions are combined to estimate monthly energy consumption, fleet size, hub area, staffing, and operating cost. The framework is applied to district-level Seoul delivery data. Increasing the number of hubs from one to four reduces the required range from 30.6 to 21.9 km and vehicle takeoff mass from 8.12 to 6.12 kg. Despite a 21.5% increase in total flight distance, monthly flight energy consumption decreases by 13.1%, from 15.2 to 13.2 MWh. Battery replacement is the largest vehicle-related operating expense, while operating cost per delivery increases from USD 1.18 to USD 2.20 because of higher rent and labor costs at the hubs. Among the designs evaluated, range-matched vehicles achieve the lowest operating cost in the two- and four-hub networks; a longer-range vehicle is least costly in the three-hub network. Sensitivity analyses further examine the effects of delivery demand and operating assumptions. The results demonstrate that reductions in vehicle mass and energy consumption do not necessarily lead to lower system operating cost.
Two concept probes can be equally accurate at predicting a concept from a language model's hidden states while their scores contain different mixtures of the target concept and a correlated nuisance attribute. In four target--nuisance settings (two aspect sentiments in CEBaB; occupation and gender in BiasBios; Amazon review sentiment with negation, and with first-person framing), two LLMs, and a population of concept extractors, we compare decodability with discriminant evidence: the score's dependence on the nuisance at fixed target, and its response to input edits intended to change only the nuisance, filtered by two LLM judges and compared against placebo edits. Under correlated training data, extractors that are statistically equivalent in held-out AUROC differ up to several-fold in nuisance sensitivity in three of the four settings, and decodability is not a reliable proxy for it: their rank correlation changes sign across settings. The effect follows the probe's training data, not the nuisance's natural association with the target: first-person framing, unrelated to sentiment in natural reviews, is absorbed at least as much as negation, which co-occurs with negative sentiment, and decorrelated training removes the systematic effect. Selecting extractors with nuisance-aware development diagnostics, which need nuisance labels but no counterfactuals, lowers counterfactual nuisance sensitivity wherever the default choice is sensitive, at a small accuracy cost. Concept measurements should be validated, not just decoded.
Yihang She, Andrew Blake, Jianbo Qi, Srinivasan Keshav
Geo-foundation models (GFMs) are evaluated by downstream predictive performance. This reveals little about which physical properties their embeddings are sensitive to or which are used in predictions. This limits developers' ability to test hypotheses about model behaviour and users' ability to select models for new tasks. We propose Physics-Informed Concept Probing (PiCo), a post-hoc framework for explaining GFM predictions. PiCo identifies concept vectors in GFM embedding space using synthetic multispectral satellite observations from a 3D radiative transfer model coupled with a game engine. These vectors characterise GFM sensitivities to physical properties, informing domain-based hypotheses about downstream performance. Projecting embeddings onto concept vectors produces low-dimensional representations for quantifying concept importance in predictions. We evaluate PiCo on three GFMs with different input modalities using seven physical concepts covering forest leaf optics and canopy structure. In ground-cover estimation, RGB-only inputs reduce dry-matter sensitivity and disproportionately degrade predictions for dry vegetation and bare ground, as anticipated by PiCo's sensitivity analysis. For hierarchical forest type and tree species classification, concept representations retain 70.0--93.8% of full-embedding accuracy. Different GFMs capture physical differences between classes, such as canopy structure between broadleaf forest and cleared ground and leaf-water-content between oak and beech. Yet they differ in the strength of these contrasts and the concepts they use for classification. PiCo provides an interpretable basis for hypothesis testing and model assessment, with potential applicability beyond Earth observation wherever physical models enable controlled simulation and pretrained embeddings are accessible for probing. Code is available at https://github.com/yihshe/PiCo.git.
Karolina Trajkovska, Matjaž Kljun, Maheshya Weerasinghe, Klen Čopič Pucihar
Mnemonics support vocabulary learning by linking unfamiliar words to familiar concepts through memorable verbal and visual associations. We present a generative AR system that enables learners to create personalised 3D mnemonics by transforming familiar objects in their surroundings into situated mnemonic anchors. The system scans the environment, detects visible objects, and generates bilingual flashcards. After selecting a word, the learner describes a personal association. The system combines this description with an image of the selected object to generate a textured 3D model using generative AI. Learners can then place the model relative to the real object, transforming it into a situated mnemonic anchor.
Kolmogorov-Arnold Networks (KANs) learn univariate functions on edges, making the choice of edge response central to their design. Existing variants use basis expansions such as splines or polynomials, whose functional form is chosen before training. We introduce geometry-constrained KANs, which instead learn the shape of power-law edge responses through an exponent inspired by Banach duality maps. Banach-KAN combines this adaptive power-law response with a bounded hyperbolic tangent (tanh) component. We relate these responses to convex potentials and bound edge sensitivity on bounded input ranges. Across symbolic regression benchmarks, Banach-KAN is competitive with fixed-basis models, particularly with limited clean data. Learned power-law responses remain competitive under measurement noise, while splines are stronger with plentiful clean data. Fixed-exponent and branch-removal controls on a core subset support learning the exponent and retaining both Banach components. Learned exponents describe the shapes of the fitted edge responses.
This paper describes the curation of a high-quality parallel corpus from OPUS Books and the fine-tuning of Meta's NLLB-200 models for German--English translation. We detail a dataset extraction pipeline that filters 45k raw OPUS sentence pairs to 25k high-quality examples through encoding validation, length filtering, language identification, deduplication, and quality scoring. We present a reproducible fine-tuning methodology optimized for consumer GPUs using mixed precision, gradient accumulation, and gradient checkpointing. Our fine-tuned NLLB-600M model achieves statistically significant improvements (+3.4 BLEU, +2.6 chrF++, -3.2 TER) over the base model on literary and technical German-English translation. We demonstrate practical deployment by integrating the fine-tuned model into LinguaHaru, an existing open-source document translation system, achieving format-preserving translation across PDF and Office documents. All dataset preparation scripts, training code, and evaluation tools are provided for reproducibility. The fine-tuned model is available at HuggingFace.
Daniel Collin, Yuri Shprits, Luca Chiarabini, Stefan J. Hofmeister, Nadja Klein, Guillermo Gallego
Accurately predicting fast solar wind conditions is challenging, as uncertainties are large and unquantified by traditional single-value prediction models. In particular, the risks of high-speed solar wind streams (HSSs), which can cause damage to technological infrastructure, cannot be reliably assessed without probabilistic forecasts. We present PROSWIN, a probabilistic machine learning model that forecasts the hourly solar wind speed (SWS) at Earth with a four-day lead time. The approach combines solar images and magnetograms using a deep neural network coupled to a distributional regression algorithm. Because standard error metrics underweight the relevance of HSS peaks, we further introduce the prediction score, a model-selection metric that jointly rewards timeline and HSS peak accuracy. On 14 years of data, our forecast achieves very well-calibrated uncertainties (<1% average deviation). Using the continuous ranked probability score (CRPS), a metric that assesses distributional accuracy, we obtain a timeline CRPS of 41.0 km/s, an HSS peak CRPS of 45.3 km/s, and a prediction score of 42.3 km/s. We find that the 171 Å channel is an important complement to the typically used 193 Å and 211 Å channels and that the prediction score for model selection improves the applicability of the model. Compared to selected models from the literature, ours is the only one that is accurate for both timeline and HSS peak values, rather than trading one off against the other. These results support the advantages of probabilistic over single-value solar wind models. The introduced methods are also transferable to other forecasting problems.
Melissa Tijink, Kirill Tolstobrov, Shunxin Wang, Estefania Talavera, Duc V. Le, Luuk Spreeuwers, Shaodi You, Nicola Strisciuglio
Realistic rain synthesis is a persistent challenge for vision systems operating in adverse weather. Existing methods primarily focus on generating rain streaks, often neglecting consequent surface effects such as reflections and puddles, which are critical for perceptual realism and robustness of downstream vision tasks. We introduce CascadeRS, a rain synthesis framework that leverages depth and segmentation priors to render scene-consistent rain and surface effects. In addition to rain streaks, CascadeRS produces reflections and puddles aligned with scene semantics through a physics-inspired zero-shot, controllable generative pipeline. It produces photorealistic rainy urban scenes, with high perceptual realism, which we validate qualitatively with an extensive user study and quantitatively. We produce the Cityscapes-CascadeRS dataset, to study downstream task performance under real rainy conditions. Our results establish CascadeRS as a scalable and realistic rain-generation framework for evaluating and enhancing the robustness of vision in adverse rainy weather. Code and dataset are available via https://github.com/nis-research/CascadeRainSynthesis
Lucile Favero, Tanja Käser, Juan Antonio Pérez-Ortiz, Nuria Oliver
Supporting students' argumentative writing with AI requires connecting reflection to their revision processes. We present Maike, a Socratic chatbot supporting writing through argument diagnosis, targeted questioning, and a student model across Think and Write modes. In a classroom study, 65 secondary-school students used Maike or a control chatbot sharing the interface, language model, and Think/Write modes. Approximately 40% of students improved their essay scores. However, Maike users engaged more in idea-level dialogue (56% vs. 44%) and moved iteratively between discussion and editing. Transitions from ideas discussed in dialogue to revisions were positively associated with score gains. These findings suggest a design target for AI writing support: coordinating reflection with revision. We contribute an architecture for supporting argumentative reasoning without generating essay text and an approach linking interaction patterns to writing processes and outcomes. As AI becomes embedded in classrooms, understanding these connections is essential to assessing (and designing for) its educational value.
We study decentralized stochastic smooth convex optimization, where $M$ workers minimize an average objective using local stochastic gradients and neighbor-only communication over a fixed gossip network. A central question in this setting is to determine the largest number of workers that can be used under a total budget of $N$ gradient samples while still preserving the centralized $O(1/\sqrt N)$ statistical rate. We introduce an accelerated decentralized method that preserves this rate for up to $\smash{M\lesssim \sqrtρ\,N^{3/4}}$ workers, where $ρ$ is the spectral gap of the gossip network, improving the best prior maximal scaling of $\smash{M\lesssim ρ\sqrt N}$. The method is based on a one-step-delayed stochastic acceleration scheme that enables workers to interleave minibatching with accelerated gossip while controlling residual disagreement, and its guarantee depends only logarithmically on the optimum-local heterogeneity. We also establish a matching lower bound for linear-span decentralized first-order methods, showing that the method is optimal up to logarithmic factors.
Nirmit Joshi, Roey Magen, Nathan Srebro, Nikolaos Tsilivis, Gal Vardi
Chain-of-thought (CoT) supervision makes computationally hard learning problems tractable by exposing intermediate steps that are easy to learn via next-token prediction. However, in practice, CoT datasets draw on heterogeneous sources with different reasoning styles, and substantial effort goes into curating supervision suitable for next-token training. What role does this curation play in enabling the computational advantage of CoT supervision? In this work, we take a first step toward understanding this question from a learning-theoretic perspective. We introduce several models of $heterogeneous$ $CoT$ $supervision$ from multiple sources, each providing correct traces with the same final answer but different intermediate steps. Assuming that fitting a next-token predictor to $homogeneous$ traces from any single source is computationally tractable, we ask when this suffices for efficient learning from heterogeneous supervision. We show $cryptographic$ $hardness$ of learning from $passively$ collected traces from multiple sources, even though learning from homogeneous CoTs is easy. This hardness can stem either from $hard$-$to$-$learn$ $contribution$ $biases$ determining which sources contribute traces on different parts of the domain, or from receiving an $unfiltered$ heterogeneous mixture (though a filtered subset of homogeneous traces is sufficient for efficient learning). On the positive side, inspired by iterative and adaptive fine-tuning of language models, we give a computationally efficient learning algorithm that $actively$ and $adaptively$ collects CoTs from multiple sources with a per-source CoT budget completely independent of the target error $\varepsilon$. We argue that our results illuminate data collection and curation practices central to making CoT supervision effective for learning.
An algorithm is presented for computing the determinant and the characteristic polynomial of a matrix $A$ over an arbitrary commutative ring R. The algorithm uses $O(n^ω)$ ring additions, subtractions and multiplications, where $ω>2$ is a feasible exponent for matrix multiplication, that is, such that two $n\times n$ matrices over R can be multiplied using $O(n^ω)$ ring operations. The algorithm involves no division and no zero test, and its control depends only on $n$: for each $n$ it is a straight-line program. The approach combines a polynomial matrix point of view and a block Krylov point of view on the characteristic polynomial, which makes Strassen's elimination of divisions efficient. A bivariate matrix $λI-L(t)$, obtained from $A$ by a homotopy, is compressed in $\log n$ steps, each of which halves the dimension while only doubling the degree in $λ$. The cost of the homotopy is controlled by truncating the power series in $t$ at an order that only grows with the compression steps, from a constant to $n$.
Evgenii Genov, Ander Martinez Alonso, Christoph Bergmeir
Energy forecasting models are usually compared on backtests and fixed public datasets. Backtests can use data that did not yet exist when the forecast would have been made, and a fixed test set, reused across studies and possibly contained in the pretraining data of foundation models, invites overfitting to the benchmark. EnergyBench evaluates every entry live instead. Each day at 11:30 CET/CEST, thirty minutes before the day-ahead (SDAC) gate closes, every model forecasts the next day's price, wind and solar generation and load on the 15-minute grid for six bidding zones (BE, NL, FR, DE-LU, DK1, DK2). Unlike existing live benchmarks, EnergyBench runs the models itself, on one information set that it freezes at the cut-off and publishes, including three numerical weather prediction models, so that foundation models can be compared with and without the same weather covariates under the actual market deadline. Errors are pooled per series against a seasonal-naive baseline, and models are ranked by a Bradley-Terry rating on the Elo scale with a day-bootstrap interval. The field spans baselines, linear and gradient-boosted models on the frozen weather, eighteen time-series foundation models from eleven families, ensembles, and the grid operators' own forecasts. Over the first thirty-two live days, the covariates reduced the error of each of the ten foundation models run with and without them by 37-51% on matched races (64-73% on wind, 48-61% on solar). Used zero-shot, these models match or outperform a LightGBM model trained on the same covariates. Model size, from 3M to 331M parameters, has a much smaller effect, and median ensembles of the covariate models rank highest. The grid operators' pre-gate forecasts remain ahead on wind and solar, where the best single foundation models have 16-22% more error; on load the gap is 4-6%, within the intervals.
Jonas Knupp, Jan Hendrik Metzen, Jeremias Bohn, Georg Groh, Kristian Kersting
Depth-recurrence facilitates latent reasoning by sharing parameters across depths. However, prior work lacks combined FLOP-, parameter-, and memory-matched baselines, underutilizes depth-recurrence due to partially fixed layer stacks, and ignores the bottleneck of constant hidden-sizes that restricts many-step latent reasoning. To address this, we introduce a modular framework of depth-recurrent attention mixtures (Dreamer), combining sequence attention, depth attention, and sparse expert attention. It alleviates the hidden-size bottleneck through attention along depth, decouples scaling dimensions, and allows depth-recurrent models to scale efficiently and effectively. Across language reasoning benchmarks, our models require 2 to 8x fewer training tokens for the same accuracy as FLOP-, parameter-, and memory-matched SOTA, and outperform ca. 2x larger SOTA models with the same training tokens. We further present insights into knowledge usage across depths, e.g., showing 2 to 11x larger expert selection diversity than SOTA MoEs.
Financial document recognition is often assessed using character and word error rates, although these metrics do not express whether a system preserves the financial facts on which people and organisations act. This paper develops a human-centred, risk-constrained framework for evaluating financial document recognition as evidence recovery and decision support. It defines typed financial facts linked to visible source regions and separates verbatim transcription, deterministic normalization, and business interpretation. A layered quality model covers text, localization, layout, tables, fields, fact correctness, evidence grounding, uncertainty, robustness, and operational performance. Non-compensatory acceptance gates use one-sided uncertainty bounds for critical-field errors, preventing strong aggregate scores from masking failures in amounts, identifiers, signs, periods, or entity associations. Selective automation is formulated as a constrained routing problem that accounts for residual risk, human-review capacity, and review cost. The framework further specifies annotation and adjudication procedures, leakage-resistant benchmark partitions, statistical estimands, subgroup analyses, and a reproducibility card. Formal results establish the limitations of compensatory scoring, the non-zero upper risk bound after zero observed errors, and a loss sensitive decision rule for routing uncertain cases to human review. The contribution is theoretical and methodological; no new model, dataset, or empirical performance result is claimed.
Katherine Tieu, Dongqi Fu, Si Zhang, Hanqing Zeng, Tianxin Wei, Chenglin Wei, Yinglong Xia, Hong Li 等 9 位作者
Diffusion Large Language Models (dLLMs) commonly decode responses by proceeding autoregressively across blocks while iteratively denoising multiple tokens within each block. This structure makes block-level policy optimization a natural adaptation of autoregressive policy optimization. However, the exact likelihood of a completed block is intractable because it marginalizes over the intermediate states and reveal orders of the denoising process. To realize the block-level formulation, we construct a prefix-block state and use a single model evaluation to define a factorized one-step surrogate for the block likelihood. The resulting block surrogate ratio is a product of its token surrogate ratios, allowing variation at individual positions to propagate across the entire block before clipping. We therefore introduce Prefix-Block Policy Optimization (PBPO), which preserves block-level conditioning but applies surrogate importance weighting and clipping separately to each token. PBPO further diversifies repeated updates by resampling corrupted views of the prompt and revealed prefix, a design motivated by masked-dLLM pre-training. Under our analysis assumptions, block-product weighting amplifies the variance of gradient contributions relative to token-local weighting. Across two LLaDA-family initializations, six benchmarks, and three generation lengths, PBPO achieves competitive performance against existing dLLM RL methods.
Fuzzy grammars and weighted automata usually attach to each word a single grade, which records how strongly the word is generated but not how far that record can be trusted. We study weighted grammars and finite automata whose weights are scalar grade-reliability pairs inspired by Z-numbers. Sequential composition multiplies both components, while aggregation selects a derivation by its credible grade, the product of grade and reliability, with ties resolved by grade. On the canonical carrier, in which the weights of zero grade or zero reliability are identified with zero, the resulting structure is a commutative selective semiring, isomorphic to a subsemiring of a lexicographically ordered product, and its credible-grade projection is a homomorphism onto the Viterbi semiring. We compare several alternative combination rules and identify the carriers on which the relevant algebraic laws hold. Standard results on weighted automata then yield a rational characterization and closure properties. We prove that positive credible-grade cuts and selected-run reliability filters of finite automata are regular and effectively constructible for rational weights and thresholds, and we exhibit distinctions that the scalar projection cannot see: a reliability filter that no scalar reweighting of the same one-state automaton implements, nonmonotonicity under the addition of runs, and an unambiguous automaton with no deterministic equivalent although its scalar projection is deterministic. A count-based example illustrates an attestation penalty for grammar rules. The construction concerns scalar pairs, and its extension to arbitrary fuzzy-valued Z-numbers remains open.
Semantic accuracy is an important dimension of knowledge graph quality. Graph-based scoring methods exploit relational structure, while textual representations allow classifiers to draw on knowledge encoded by pre-trained language models (PLMs). We present GenVer, a generative verifier that scores triples using both their serialized form and generated natural language representations (NLRs). A triple-text alignment procedure selects training pairs for a sequence-to-sequence generator; a BERT-based classifier then combines features from each triple and its generated NLR. On four FactFB variants, constructed from FB15k using perturbed negative triples, GenVer obtains the highest classification accuracy among the evaluated baselines, ranging from 88.56% to 91.52%. The experiments suggest that generated representations can help triple classification, while the case analysis also exposes semantic drift and high-confidence errors.
Tactile sensing provides information about object properties that can improve robotic grasping and manipulation. However, accurate object recognition during the early stages of grasping remains challenging, particularly under strict real-time constraints. This study presents a flexible, distributed piezoelectric tactile sensing system for early-stage object recognition. The system was experimentally evaluated using six everyday objects and three recognition approaches: feature-based classification using support vector machines (SVMs), raw-signal classification using 1D convolutional neural networks (1D-CNNs) and convolutional recurrent neural networks (C-RNNs), and spatiotemporal heatmap classification using a 2D-CNN. The effects of sensor count and temporal window size on recognition accuracy and real-time feasibility were systematically investigated. Increasing the number of sensing elements improved recognition performance across all approaches. The best-performing method, based on spatiotemporal heatmaps and a 2D-CNN, achieved F1-scores of 0.9796, 0.9846, and 0.9903 using 16, 24, and 32 sensors, respectively. The optimal configuration, comprising 32 sensors and a 100-ms temporal window (50 samples), was deployed on an embedded edge platform, achieving an end-to-end recognition latency of approximately 101 ms from contact onset and an energy consumption of 63.8 microjoules per inference. These results demonstrate the potential of distributed piezoelectric tactile sensing for accurate, energy-efficient, and real-time object recognition during robotic grasping.
Language models lose accuracy when a prompt contains non-evidential context: irrelevant statements from unrelated domains, or random off-distribution tokens, with no competing answer and no semantic overlap with the query. Such noise pervades retrieval-augmented, tool-using, and long-context deployments, yet the failure has lacked a mechanistic account. We trace the corruption to the Intrusion Pathway, which starts with MLPs enriching both query-subject and irrelevant-token representations, parroting heads carry prefix-token content to the prediction position, and relational readers largely avoid unrelated sources. Nevertheless, preserved subject enrichment and selective reading do not prevent intrusion in the broader computation. We then localize part of this interference to a sparse set of attention heads, which we call intrusion heads. Their prefix-derived writes promote distractor-related content, while their reduced support for the correct answer arises primarily from weaker non-prefix contributions rather than direct suppression by the prefix. The same heads transfer across tasks and distractor types and are largely weight-disjoint from the heads that integrate relevant contextual evidence, enabling a class-conditional intervention. Replacing the corrupted last-token residual with its clean counterpart, an oracle probe that requires a matched clean forward pass, recovers 97.6% on average of the distractor-induced drop across four downstream tasks. A deployable mask level knockout of about ten heads, roughly 1% of the model's attention heads, recovers 57% at bounded cost to helpful context.
William Grolleau, Achraf Chaouch, Astrid Sabourin, Guillaume Lapouge, Catherine Achard
Animal re-identification (ReID) faces critical challenges due to viewpoint variations, particularly in Aerial-Ground (AG-ReID) settings where models must match individuals across drastic elevation changes. However, existing datasets lack the precise angular annotations required to systematically analyze these geometric variations. To address this, we introduce the Multi-view Oriented Observation (MOO) dataset, a large-scale synthetic AG-ReID dataset of $1,000$ cattle individuals captured from $128$ uniformly sampled viewpoints ($128,000$ annotated images). Using this controlled dataset, we quantify the influence of elevation and identify a critical elevation threshold, above which models generalize significantly better to unseen views. Finally, we validate the transferability to real-world applications in both zero-shot and supervised settings, demonstrating performance gains across four real-world cattle datasets and confirming that synthetic geometric priors effectively bridge the domain gap. Collectively, this dataset and analysis lay the foundation for future model development in cross-view animal ReID. MOO is publicly available at https://github.com/TurtleSmoke/MOO.
For every fixed integer $k\ge2$ and fixed parameters $δ,\varepsilon\in(0,1)$ and $η\in[0,1)$, we give a deterministic polynomial-time reduction from finding a $δ$-approximate Nash equilibrium ($δ$-ANE) in a $k$-player game $G$ with payoffs in $[0,1]$ to finding an $(\varepsilon,η)$-weak approximate Nash equilibrium (weak ANE) in a game $H$ with $C$ players, where $C$ depends only on $k,δ,\varepsilon,η$, independently of the action-set sizes. The constructed game is symmetric with binary payoffs. The games and strategies are represented by complete payoff tables and probabilities, with rational entries encoded in binary. Consequently, the existence of deterministic polynomial-time weak-ANE algorithms at one fixed pair of parameters $\varepsilon\in(0,1),η\in[0,1)$ for every fixed number of players would give deterministic polynomial-time $δ$-ANE algorithms at every fixed approximation parameter $δ\in(0,1)$ and number of players. Under deterministic PPAD-ETH, combining our reduction with Rubinstein's hardness result (FOCS 2016) for bimatrix games at some fixed approximation parameter $γ_0\in(0,1)$ rules out a deterministic algorithm for $(\varepsilon,η)$-weak ANE with running time $N^{O((\log N)^{1-ξ})}$ for any fixed $ξ\in(0,1)$. This holds for every fixed $\varepsilon\in(0,1)$ and $η\in[0,1)$ at a suitable constant number $C$ of players, where $N$ is the binary encoding length of the constructed game's complete payoff table.
Moritz Grävinghoff, Konstantin Wehmeyer, Aron Asefaw, Boris Knyazev, Damian Borth
LoRA adapters are usually treated as finished artifacts rather than as a data modality. Prior work has shown that LoRA adapters populate a low-dimensional manifold that a linear PCA basis already organizes well enough to support different operations such as sampling, editing, and inversion. We ask what a learned, nonlinear latent adds beyond this. We train a transformer autoencoder on the same population of LoRA identity adapters, mapping each into a latent space and compare every operation against the identical operation applied directly to the raw adapter weights. The latent preserves the capabilities already available in weight space, sampling diverse identities and editing individual attributes. Beyond preservation, we show that the latent is far more robust to displacement than weight space, degrading into distorted but still valid faces rather than texture. Fixed-dimensional weight-space representations cannot natively host adapters of more than one rank, so we extend our sequential autoencoder to hold mixed-rank adapters within one shared latent. This gives a path toward treating adapter weights of varying architecture as a single, general modality rather than one tied to a fixed rank, and points to a learned, nonlinear latent as the mechanism that could carry this generalization further, toward heterogeneous populations of adapters.
We prove that every fan-in 2 noncommutative arithmetic circuit computing the palindrome polynomial $\mathrm{Pal}_{n,d}(X,Y)$ of degree $2d$ in $2n$ variables has size $Ω(nd)$, which is tight up to a constant. In particular, when $d = n$ we obtain an $Ω(n^2)$ lower bound, improving the previous lower bound of $Ω(n \log n)$ by Nisan and concurrent work of $Ω(n^{1.5})$ by Raz (FOCS 2026). The proof builds on and refines a previous work of the first author, by constructing for every gate a small set that spans a subset of the coefficients of the polynomial computed by that gate. We show that the structure of the set depends only on the subsets of multiplication gates along paths going from that gate to a leaf. From this description, we are then able to get an upper bound on this set based on the amount of product gates in the circuit. The proof is surprisingly short and simple to understand, considering that improving Nisan's $Ω(n \log n)$ lower bound for noncommutative circuits has been an open problem for decades.
Emmanuel Esposito, Andrew Jacobsen, Hao Qiu, Alexander Ryabchenko, Mengxiao Zhang
We study learning in zero-sum games with delayed feedback. We introduce Multi-Anchor Optimistic Online Mirror Descent (MAO-OMD), a single algorithm which obtains optimal fast rates in self-play on smooth games, while simultaneously maintaining minimax optimal guarantees against arbitrary opponents. In particular, in smooth zero-sum games with arbitrary and unknown feedback delays, MAO-OMD obtains $O(σ_{\max}+1)$ social and individual regrets when used by both players, where $σ_{\max}$ denotes the maximum number of outstanding gradients, while also guaranteeing minimax optimal $O(\sqrt{T+d_{\mathrm{tot}}})$ individual regret against arbitrary opponents, where $d_{\mathrm{tot}}$ is the total delay. Moreover, we show that these optimal rates cannot be obtained simultaneously using the standard black-box reduction to the undelayed setting. We also extend our results to multi-player games, and to games with player-dependent delay sequences.
Max Unterbusch, Julian Frattini, Michael Mircea, Alexander Korn, Kurt Schneider, Jonathan Ullrich, Andreas Vogelsang
External validity is a central concern in empirical software engineering, yet the debate has largely focused on whether study participants are representative. How well the study objects they reason about - code, models, or requirements - are representative of each participant's own work is often overlooked. Practitioners' own artifacts would be ideal, but are often out of reach, so researchers sample from public datasets or construct objects artificially. Whether this lack of subject-object fit affects participants' ability to act on the material remains unknown. We take a first step toward answering this question for requirements. We propose an approach that uses an LLM to generate context-adapted synthetic requirements just-in-time during an online survey from a short, participant-supplied context description, optionally injecting requirements smells as controlled stimuli. To validate the approach, we conducted a controlled experiment with 31 industry practitioners in a 2x2 design that crosses stimulus generation (static vs. synthetic) with quality (clean vs. smelly). Each participant rated the perceived representativeness and assessability of 20 requirements. Using Bayesian data analysis within a statistical causal-inference framework, we find that perceived representativeness has a strong positive effect on assessability. Synthetic requirements are rated as more representative and, primarily due to this gain, more assessable than static ones sourced from public datasets; smell injection leaves both perceptions unchanged. Our results support treating a lack of study-object representativeness as a first-class validity threat and position context-adapted synthetic study objects as a practical addition to the empirical methodology toolbox.
Julian Ganz, David Knothe, David Oswald, Sebastian Reiter, Thorben Schneider, Simon Wegener
Constant-time execution is an important security property, especially for IoT devices, that prevents the leakage of sensitive information over timing side-channels. However, achieving constant-time execution is very hard when going down to the cycle level, at least on realistic devices. A lot of research is concerned with producing tools that either determine whether code is constant-time or that ensure it is compiled into a constant-time binary, with various degrees of accuracy. In this work, we present and evaluate a full workflow for hardening against timing side-channels during compilation. It starts with taint analysis to determine the code locations that depend on sensitive information. These are then the object of automated control-flow transformations inside the compiler to seal possible timing side-channels. We evaluate our workflow in detail on a realistic application running on a RISC-V core using both static timing analysis and statistical methods. Even though we do not reach cycle-accurate constant-time execution, our statistical results suggest that our hardened binary is safe against timing attacks.
Ziyi Wang, Li Li, Aolin Zhou, Yankun Shen, Chonghan Liu, Shuxia Lin, Xu Yang
Most Vision-Language Models (VLMs) are built by extending pretrained Large Language Models (LLMs) with visual modules and multimodal alignment. However, this multimodal scaling often degrades the language-side reasoning ability originally encoded in the base LLM. While the base LLM retains usable reasoning after scaling, the aligned VLM itself cannot reliably access this ability. Therefore, recovering the degraded reasoning capability in VLMs would benefit more from seeking help from the base LLM than from the VLM alone. Motivated by this, we propose LIFT (Language-side reasonIng Facilitation and Transfer), a lightweight vector-intervention method that transfers reasoning capability from the base LLM to the VLM without retraining the backbone. LIFT defines Reasoning Vectors as answer-token hidden-state differences between a Reasoner path with an explicit reasoning trace and a Solver path without it, and injects these vectors into language-side activations of the target VLM. LIFT further supports learnable vector adaptation while keeping the VLM backbone frozen. We evaluate LIFT on two VLMs across six reasoning benchmarks, comparing Reasoning Vectors extracted from the base LLM and from the aligned VLM under matched protocols. Results show that LLM-derived vectors consistently outperform VLM-derived vectors, confirming that the base LLM is a more effective source for recovering reasoning. LIFT partially recovers degraded reasoning through lightweight language-side interventions. Further analyses show that Reasoning Vectors influence intermediate reasoning behavior rather than merely altering final answers. The source code will be released soon.
Graphical User Interface (GUI) grounding aims to map natural language instructions to precise operational coordinates, serving as a critical task for autonomous agent interaction. Current approaches formalize GUI grounding as predicting action-coordinate pairs from instructions, with end-to-end training supervised solely by final coordinates. Training datasets typically provide only a small number of descriptions per target coordinate, whereas real-world scenarios involve a much larger set of varied descriptions for the same target, which limits robustness to linguistic variation. While recent GUI grounding paradigms have begun employing reinforcement learning to enhance localization accuracy, models with limited exploratory capability before reinforcement yield constrained improvements even with identical training data during the reinforcement phase. To overcome these limitations, we propose a bidirectional reward paradigm that enables model self-reinforcement. During SFT, bidirectional training equips the model to generate action descriptions from target coordinates. During RL, the model samples semantically consistent instruction variations on-policy and grounds each variation back to its target. A cycle-consistency gate couples semantic quality to grounding success, turning the model's own instruction policy into a source of continually refreshed reinforcement trajectories. Our 4B-parameter model achieves competitive accuracy across five grounding benchmarks in our evaluation, indicating the effectiveness of the proposed training paradigm. https://github.com/Spell-shi/BiGrounder