Papers

Imagination performs as a high-level function of large language models (LLMs) which determines the potential of how an LLM creates unseen or creative content. While existing works have built a rich family of creativity benchmarks for this ability, they only measure how far an output departs from common answers and never check whether the departure is licensed by the prompt. Moreover, hallucination, the closest neighbor of imagination, is always measured in a separate pipeline on different generations, so the influential claim that imagination and hallucination stem from the same generative mechanism has never been directly testable. In this paper, we propose Whiteboard, the first LLM imagination evaluation benchmark. Its design follows the authoritative cognitive instruments developed to measure human imagination: seven mechanism-grounded imagination subtypes are adapted from classic paradigms, then crossed with ten support-boundary hallucination subtypes and scored jointly on the same generation. Different from previous creativity or hallucination benchmarks, Whiteboard gates every imagination score with an explicit support check and computes both axes deterministically through an auditable atom matrix, with no LLM judge on the primary path. The full Whiteboard item bank contains 1,660 prompts; on its shared 80-item anchor set, we evaluate 79 state-of-the-art LLMs and validate the instrument against 13,280 human judgments. Additionally, we further explore whether imagination derives from the same generative tendency as hallucination and what key factors shape it. Our analysis indicates a counterintuitive correlation between hallucination and imagination: Most of the subtype couplings are negative, every one of the anchor items reproduces the negative coupling on its own.

We ask whether behavioral constraints acquired through post training remain explicitly reportable. Using constrained recipe generation as a testbed, five banned ingredients enforced via LoRA fine tuning of Llama 3.1 8B Instruct we compare supervised fine tuning (SFT) and Group Relative Policy Optimization (GRPO) against an untrained baseline on a four tier Constraint Awareness Benchmark. Averaged over three seeds, both methods raise behavioral compliance from 4% to about 90% while reducing explicit constraint reporting below the untrained model (0.48/5 to 0.16/5 for SFT, 0.07/5 for GRPO) and eroding retained third person knowledge (93% to 36% for SFT, 14% for GRPO; p less than 0.01 between methods). Contrary to our initial hypothesis, the reward based signal is the more destructive of the two: a reward that penalizes banned ingredient tokens regardless of framing learns a context independent suppression rather than a self directed constraint. A context conditioned reward designed to teach the self to other distinction fails, collapsing toward inclusion in both framings. Probing prompt time hidden states recovers per ingredient avoidance at 83.8% (layer 24 MLP), but only 6.4 points above a per ingredient base rate predictor (77.4%), and the model's own verbal self report is more accurate still (87.8%). A positive control adding explicit self description examples does not restore reporting. The failure is therefore specific to enumerating constraints on request, not a general loss of access to them.

Content promotion spans a broad set of skills, from understanding content to forecasting its market reception. However, LLMs' ability to support such promotion decisions remains underexplored. Existing studies are often limited to a single task (e.g., popularity prediction) or a small set of tasks within a single domain (e.g., movies). As a result, there is a lack of understanding of LLMs' abilities in the full promotion process and how these abilities generalize across different tasks and domains. In this work, we introduce ECP-Bench, a benchmark containing 1.9M movie, game, and music items and 423,451 questions across 33 tasks in five content-promotion skill families. Our evaluation shows that frontier models achieve only 51.9% overall accuracy and lose much of their advantage on post-cutoff content, with drops of up to 19.1 percentage points. In contrast, open-weight models fine-tuned on ECP-Bench achieve up to 60.3%, remain substantially more stable across the knowledge cutoff, generalize to unseen content and tasks, and exhibit meaningful cross-domain generalization.

Multimodal synthetic datasets combine structured attributes with free text, but are often evaluated separately. Such metrics can remain high after tabular–text pairings are disrupted. We present a projection-based evaluator for tabular–text synthetic data. A fixed sentence encoder maps text to embeddings, \(k\)-means converts them to cluster states, and tabular variables are represented as categorical or quantile-binned states. Real and synthetic contingency tables are compared using Jensen–Shannon divergence (JSD), normalized mutual information (NMI), conditional JSD (cJSD), and joint-state entropy. We also report text-to-attribute (T2A) utility and a holdout-calibrated proximity flag rate (PFR) as a representation-level diagnostic. A text-permutation control preserves both marginal distributions while disrupting their pairing. Experiments on Amazon Reviews, Kiva Loans, and the Employment Scam Aegean Dataset show that modality-specific scores remain high under this control. The projection diagnostics detect disruption when real projected dependence exceeds a permutation baseline, but are less informative for weak or sparse projections. Some conditioned LLM baselines also exhibit stronger measured dependence than the corresponding real-data projections. These results support explicit cross-modal evaluation with permutation baselines and coverage reporting.

We study how post-training changes the weights of Large Language Models (LLMs) relative to their pretrained weights. Across 12 post-training chains with supervised fine-tuning (SFT) and reinforcement learning (RL), we express each weight update in the pretrained matrix's singular value decomposition (SVD) frame. This decomposition separates the changes of three geometrically distinct components: diagonal values, which reshapes singular values; off-diagonal values, which rotates the coupling between pretrained input and output directions; and null-space values, which routes outside the matrix's original nonzero SVD core. On a math evaluation suite, we find that removing the diagonal component usually preserves most of the gains from post-training. These results suggest that post-training gains are carried primarily by reconfiguring and extending pretrained pathways rather than by substantially changing singular values of pre-trained models.

Diffusion large language models (dLLMs) offer a compelling alternative to autoregressive models, yet they may expose sensitive training data during denoising. Detecting such usage is challenging because dLLMs lack the efficient one-pass probability decomposition of causal architectures. Existing methods rely on random masking to obtain tractable token-wise detection signals under limited query budgets, but fail to control dependencies among masked tokens. We demonstrate that this token-wise approximation introduces a non-negative structural estimation error, which is theoretically characterized by the cumulative conditional mutual information (CMI) among masked tokens and can obscure subtle memorization signals. This insight suggests that reliable detection requires masked token sets with weak internal dependency. To avoid the prohibitive cost of directly estimating CMI over token combinations, we propose Independent Token Sampling (ITS), a query-efficient framework that uses an attention-derived pairwise dependency proxy to approximate the CMI-aware selection criterion. ITS further incorporates a diversity-promoting strategy to improve token coverage across sampling rounds, yielding aggregated token-wise signals that are less affected by dependency-induced approximation error. Experiments on multiple datasets show that ITS consistently outperforms state-of-the-art baselines across different models and datasets, achieving an AUC improvement of 0.18 on the ArXiv dataset while maintaining strong performance under limited query budgets. The code is available at https://github.com/Chrisqcwx/DLLM-MIA .

Preserving safety alignment during large language models fine-tuning is critical, however, recent studies have demonstrated that even benign fine-tuning data may contain safety-degrading samples that silently undermine safety alignment. Existing approaches typically identify such samples using representations from a single safety-sensitive layer. While this assumption has shown effectiveness in monolingual settings, its validity for multilingual models remains unclear due to potential cross-lingual differences in representation patterns. Through a cross-lingual analysis, we show that sensitive layers are only partially shared across languages, with safety-relevant signals often distributed across multiple layers. Motivated by these observations, we propose MMSAFE, a multi-layer framework for multilingual safety-degrading data identification that captures both shared and language-specific safety signals. Extensive experiments across multiple models, languages, and safety benchmarks demonstrate that MMSAFE reduces the average harmful-response ratio by 60% compared with random filtering and achieves stronger average performance than the strongest single-layer baseline, demonstrating the effectiveness of multi-layer modeling for robust multilingual safety alignment.

As the population ages, the number of patients with cardiovascular diseases continues to increase, highlighting the need for early detection before progression to severe and irreversible functional decline. Consequently, estimating cardiovascular biomarkers from non-invasive biosignals, such as photoplethysmography (PPG) and arterial pressure wave (APW) signals, has attracted increasing attention. These signals can be measured using wearable and cuff-type devices. Previous studies have used PPG and APW signals to estimate cardiovascular biomarkers. However, these signals exhibit strong similarities in both the temporal and frequency domains and primarily reflect peripheral and arterial pulse waveforms. Therefore, they may provide limited information about cardiac mechanical function. In contrast, the quantitative impact of additional biosignals, such as ballistocardiography (BCG), which reflect the body's minute mechanical responses to cardiac ejection, remains unclear. In this study, we generated synthetic PPG, APW, and BCG signals from a unified whole-body cardiovascular circulation model and evaluated the complementary contribution of BCG to probabilistic cardiovascular biomarker estimation. We estimated posterior distributions of cardiovascular biomarkers using neural posterior estimation and simulation-based inference. The results showed that adding BCG signals significantly improved estimation performance. Furthermore, even in ill-posed cases where PPG and APW alone produced multimodal posterior distributions, adding BCG yielded unimodal posterior distributions. These findings provide fundamental insights into signal selection for estimating cardiovascular dynamics.

OASIS (Open Assessment and Scoring Infrastructure Stack) is a systems platform for rubric-based grading of video, audio, and text with large language models. Scoring one artifact with an LLM is straightforward; deploying assessment at scale requires encounter management, rubric versioning, modality-aware execution, provenance capture, and human review. OASIS pairs a standalone command-line interface with a canonical integrated Elephant + MAPLES stack for encounter management and multimodal grading orchestration. Both paths can target hosted APIs or self-hosted open-weight models through Ollama and OpenAI-compatible endpoints such as vLLM. SimRubrics rubric authoring and the Wayfinder conversational agent gateway are optional extensions that use the same authenticated interfaces as human operators. Given a rubric and recorded encounters, OASIS produces per-criterion scores, evidence, and rationales, preserving execution artifacts for audit. Distinctive features include rubric-as-program compilation, progressive execution plans, content-addressable grading identity, transcript-augmented multimodal grading, explicit review state, and a shared command surface for humans and autonomous agents. Though developed in medical education, the architecture is domain-agnostic, applying wherever structured performance can be evaluated from recorded or written artifacts. In production at UT Southwestern Medical Center since Fall 2023, the platform has processed more than 7,000 encounters. This publication includes the report and project information, not application source, binaries, installation materials, sample data, or a tagged software release.

Hydrodynamic ram (HRAM) loading remains a persistent challenge in impact mechanics, less due to exotic physics than to the difficulty of achieving convincing quantitative agreement in reduced-order representations. Prevailing studies typically employ a single mesh and boundary treatment validated against one experimental dataset, leaving unresolved whether agreement reflects genuine fidelity or compensating discretization errors. This work presents a planar 2D, GPU-accelerated WCSPH solver employing an Adami-type ghost-particle boundary condition, extended for the first time to a moving, decelerating disk penetrating a confined liquid channel at ballistic velocity. The boundary condition is examined against a purpose-derived potential-flow added-mass solution and the analytical acoustic reflection coefficient at the steel-water interface; this exploration reveals that the stiff equation of state and cavitation cutoff impose identifiable delineation of the solver's operating regime on quantitative agreement. A three-point resolution convergence study reveals a non-monotone near-probe pressure peak, attributed to a bounded ghost-fluid density inconsistency. A comprehensive coefficient sweep, conservation diagnostics, and O(N) GPU throughput scaling enable exhaustive characterization impractical in 3D. Qualitative comparison against literature evidence at 900 and 600m/s clarifies load bearing versus approximate elements. Notably, energy diagnostics reveal a modest total energy growth over the simulated window, with the fluid absorbing disproportionately more energy than the projectile relinquishes - an instructive signature of prescribed, non-back-reacting projectile kinematics that helps map the formulation's operating envelope. The resulting solver, while confined to planar geometry, delivers verified, convergence-checked performance well suited for rapid parametric design exploration.

This paper presents a procedure to optimize the way trains are driven, which pursues, in addition to fulfilling operational constraints such as admissible speeds or journey durations, the minimization of the cost related to supplying electrical energy to the trains, including the cost of the energy consumption and the cost of the power capacity utilization. This procedure combines: (i) a traffic model that merges the energy and power footprint of each rail service part of the traffic mesh, and (ii) an evolutionary computation framework that enables searching for the optimal way to drive the trains to achieve an optimal traffic mesh. This procedure is applied to a 450 km long section of the high-speed line from Madrid to Barcelona (Spain).

Omnimodal large language models (Omni-LLMs) integrate audio, video, and text, yet remain vulnerable to cross-modal hallucinations, where one modality improperly influences predictions about another. Existing training-free decoders modulate modality influence through perturbation or relevance weighting, but do not assess predictive compatibility within the joint audio-visual branch. Because joint-branch discrepancies may indicate either harmful interference or useful complementarity, reliable intervention requires assessing both discrepancy magnitude and actionability. To this end, we propose Conflict-Aware Decoding (CAD), a training-free framework comprising Potential Conflict Magnitude Estimation (PCME) and Conflict Actionability Assessment (CAA). PCME quantifies potential conflict using audio-video disagreement and the deviation of the joint prediction from a relevance-weighted unimodal reference. CAA then applies Dempster-Shafer reliability discounting to task-space answer relations, using query relevance and answer decisiveness to determine whether intervention is warranted. When an actionable conflict is identified, CAD selectively reallocates decoding weight from the joint branch to the unimodal branches. Experiments on CMM, AVHBench, WorldSense, and VideoMME show that CAD consistently outperforms the base decoder and competitive training-free methods across multiple audio-visual backbones. On Qwen2.5-Omni-7B, CAD improves overall accuracy by 14.1 and 8.0 percentage points on CMM and AVHBench, respectively, without model retraining.

Modern multi-agent systems are increasingly deployed at scale over large populations of agents in settings such as ad-auctions, traffic routing, and recommendation systems. The dominant approach in such settings is to optimize each agent's policy independently, treating the other agents as part of a fixed single-agent environment rather than modeling the population dynamics. In many large-population systems, the dynamics depend on an aggregate summary of the population rather than the identity of any individual. Mean-field RL exploits such structure, providing a principled framework that models each agent's environment as an explicit function of the population distribution. However, in large state-action spaces or high-dimensional control problems, modeling the population distribution is itself intractable. How can we design a scalable framework for high-dimensional control problems with large populations? This work explores this question from the perspective of representation learning. We introduce a mean-field RL framework in which the rewards and transition dynamics depend on the population only through an unknown low-dimensional aggregate statistic. We then study this framework in the offline setting and design a provable approach that learns a near-optimal policy by learning a low-dimensional representation. Motivated by real-life supply-chain optimization problems, we design a one-step routing game to test the hypothesis that learning a low-dimensional population representation improves reward prediction and Nash gap estimation relative to baselines that don't exploit this structure. We show that under a fixed neural-network parameter count and optimization budget, learning a low-dimensional population representation improves reward prediction and the equilibrium quality of the resulting policies.

In this paper, we introduce ES-AHD, a novel framework that fundamentally integrates Evolution Strategy (ES) into Large Language Model (LLM)-driven Automatic Heuristic Design (AHD). Existing evolutionary approaches predominantly rely on random, individual-level mutation, leading to blind search and an imbalance between exploration and exploitation. To address these issues, ES-AHD introduces two core mechanisms. First, Semantic Recombination via LLMs discards traditional point-to-point reproduction. By leveraging the LLM's contextual reasoning to explicitly extract core insights from top-performing individuals, the algorithm establishes a promising semantic search direction. This transforms random code mutation into targeted, center-guided sampling inspired by ES. Second, Stochastic Covariance Adaptation via Temperature Sampling dynamically addresses the exploration-exploitation dilemma. By mapping the covariance matrix in ES to the LLM's sampling temperature, the framework employs a stochastic random walk mechanism with momentum. This approach primarily shrinks the search radius for micro-level code refinement, while retaining the critical ability to occasionally sample higher temperatures to escape semantic local optima. Ultimately, ES-AHD provides a highly directional, robust, and efficient search paradigm, significantly accelerating the generation of high-quality heuristic algorithms. The source code is available at: https://github.com/Mriya0306/ES-AHD.

Wearable VLM pipelines promise continuous multimodal assistance from egocentric visual capture: a user asks a task-driven question about the surrounding scene, and the system uses compact visual tokens to support language reasoning. The challenge motivating this work is that the same egocentric evidence needed for useful assistance can also reveal private attributes about the wearer or nearby bystanders. We investigate this as a joint privacy-utility problem for split VLM inference, where visual encoding occurs within a trusted device boundary but intermediate visual tokens may be transmitted to downstream reasoning components. This exposes an understudied leakage surface: even when final textual responses are benign, external attackers or untrusted downstream components can recover private attributes from transmitted visual tokens. To evaluate this tension, we construct a paired privacy-utility benchmark with 3,221 image-question records, each paired with a utility question and privacy labels covering location, income, sex, and interests. We further propose Token-Guided Attribute Privacy (TGAP), a pre-LLM token disentangler that learns a residual transformation of visual tokens before they leave the trusted boundary. TGAP combines utility preservation, identity regularization, semantic privacy suppression, and image-driven representation suppression, avoiding the utility loss caused by coarse hard or attention masking. On the benchmark used for source-model evaluation, TGAP reduces privacy accuracy from 56.7% to 7.4%, a 49.3% absolute drop, while maintaining relaxed utility at 74.4%. These results suggest that securing the compact token interface is a practical path toward privacy-preserving wearable multimodal AI.

360-degree video supports immersive applications such as virtual reality, autonomous driving, and education. Because spherical content cannot be processed directly by conventional video codecs, it must first be mapped to a two-dimensional projection. Projection choice affects spatial continuity, sampling uniformity, motion estimation, and compression efficiency. This thesis investigates how projection format influences end-to-end neural compression of 360-degree video. Seven formats supported by JVET 360Lib are evaluated using the scale-space flow model, JVET test sequences, and common test conditions. Each sequence is converted from its source equirectangular projection to a coding projection, compressed at multiple rate points, reconstructed, and converted back. Performance is assessed using PSNR, spherical PSNR, weighted spherical PSNR, and Bjøntegaard delta rate. A differentiable pipeline combining projection conversion, neural compression, and inverse projection is also compared with 360Lib. Results show that equirectangular and padded equirectangular projections provide the highest compression efficiency with the scale-space flow model, while cubemap-based and rhombic dodecahedron projections are less effective. This differs from the conventional HM-16.16 codec, for which cubemap-based formats, particularly equi-angular and adjusted cubemap projections, outperform equirectangular formats. Neural models based on optical flow benefit from the spatial continuity of single-face projections, whereas block-based hybrid codecs better accommodate multi-face layouts. These findings show that projection efficiency is codec-dependent and provide guidance for selecting projections for learning-based 360-degree video compression.

Generative models have significantly improved the performance ceiling of image lossy compression at low bitrates by exploiting learned priors. However, the generated textures and semantic details may deviate from the source content, thereby affecting the fidelity of image reconstruction. To solve these challenges, we propose FLM, a frequency-aware language model that improves compression efficiency through frequency-domain probabilistic modeling while retaining deterministic reconstruction. At the encoder, the input image is transformed into quantized DCT coefficients, which are organized into discrete sequences using macroblock-based coefficient tokenization. FLM then performs next-coefficient prediction to autoregressively estimate token-wise conditional probability distributions for arithmetic coding, thereby generating a compact bitstream. At the decoder, the LLM and arithmetic decoder jointly recover the frequency-domain data, followed by inverse transformations for image reconstruction. A task-specific frequency-domain dataset and a two-stage fine-tuning strategy are further developed to enable the model to operate across multiple bitrate settings. FLM is a versatile compressor that is compatible with both lossy compression and lossless JPEG recompression frameworks. Experiments show that FLM exceeds conventional and generative lossy compression methods in rate-distortion performance. FLM achieves BD-PSNR gains of 3.30 dB, 3.83 dB, and 3.80 dB than JPEG baseline on Kodak, Tecnick, and CLIC2020, respectively. Better qualitative quality of FLM can be achieved in improving semantically high fidelity and suppressing blocking artifacts. FLM is also validated to be applicable to the lossless recompression task with competitive performance.

Frequency features and compression-invariant representation learning are widely assumed to be key to deepfake detection that survives video compression. We test this with CAFRL - block-DCT and FFT-phase streams, compression-level-conditioned band attention, and adversarial (gradient-reversal) compression invariance - and report a controlled negative. Under a pre-registered protocol with capacity- and augmentation-matched controls, a plain EfficientNet-B0 on multi-quality data beat CAFRL as specified at every compression level on the FaceForensics++ test split, by 3.66 AUC points at CRF 40 (paired, single seed). A self-audit of our own negative found four defects biased against the frequency hypothesis, and pre-specified re-tests repairing all four showed the deficit to be a recipe artifact, not an architecture failure: the baseline recipe recovered 3.96 points over the matching shipped-recipe variant. The frequency path made no detectable difference: discriminative alone (standalone validation AUC 0.91-0.98 late in training) but of no marginal value under this fusion, at two feature widths of one 4.0 M trunk, every seed-pooled interval for the intra-dataset compression contrasts including zero; on the single held-out manipulation tested, the fair variants sat below the plain backbone. The adversarial branch, as specified, added nothing and degraded its own conditioning estimator; at the fair recipe it is untested. Robustness under single-pass H.264 re-encoding came instead from data diversity: real constant-rate-factor variants beat synthetic JPEG augmentation by 7.3 points (single runs, non-overlapping intervals). The evidence is FaceForensics++-family, GAN-era and single-codec. Match controls on training recipe as well as capacity, and buy compression robustness with codec diversity before architecture.

Distributed deep neural networks (DNNs) for dense perception tasks such as semantic segmentation execute an encoder DNN on edge devices, and a decoder DNN typically on a large-scale cloud platform with a particular constraint on transmission bitrate. Recent works employ source codecs to enable bitrate-efficient transmission between the edge device and the cloud. However, as these approaches are typically bound to a particular type of source codec and alternative network architectures are often not explored, this results in a suboptimal rate-distortion (RD) trade-off in the low-bitrate regime. In this work, we propose two novel source codecs that enable extremely low bitrates, while improving RD performance. We demonstrate the effectiveness of our proposed source codecs by achieving state-of-the-art performance in distributed semantic segmentation at below 0.2 (0.03) bits per pixel, measured using the mean intersection-over-union metric on ADE20K (Cityscapes).

This paper introduces a framework that integrates the dynamic stiffness matrix (DSM) with physics-informed neural networks (PINN). The DSM-PINN embeds physical constraints within the model and demonstrates robustness, particularly when addressing limited datasets across diverse investigations. In this approach, deep neural network outputs approximate the displacement fields of element nodes. Unlike the finite element method (FEM), the element shape functions are homogeneous solutions to the governing partial differential equation, forming the basis of the exact dynamic stiffness matrix, thereby avoiding high-order derivative terms. This matrix also serves as a frequency-domain spectral element, resulting in a strong-form PINN. The loss function is produced by connecting neural networks with dynamic stiffness matrices. We focus on utilising PINNs to resolve eigenvalue problems by employing the Wittrick-Williams algorithm, which overcomes the challenge of neural networks failing to converge to higher-order eigenvalues. Additionally, the frequency domain-PINN method is used to analyse structural dynamic responses under moving and impulsive loads, addressing the limitation of neural networks in handling complex numbers. Theoretical convergence stability of the suggested approach is also analysed even DSM is an indefinite matrix after implementing the boundary condition. The numerical results validate the practicality and efficacy of the recommended approach.

Probability calibration aligns model confidence with predictive accuracy, enabling clinicians to identify unreliable segmentation regions. This alignment breaks down under domain shift, where artifacts and unseen protocols produce confident errors. Existing post-hoc methods adapt the correction at test time, conditioning on predictive entropy, the logit pattern, or augmentation response, but each proxy is read from the terminal prediction, the very quantity that shift corrupts. This motivates reliability evidence beyond the terminal prediction, which categorical diffusion provides in two ways. First, a generative shape prior keeps a capacity-limited reference intact when appearance is corrupted, so its disagreement with the primary segmentor highlights primary-model errors. Second, every reverse step yields a class distribution, separating persistent disagreement from transient discrepancy. Aggregated over the trajectory, this disagreement correlates with Dice at 0.788, against 0.521 for a matched discriminative control. We therefore propose CARD (Calibration via Agreement in Reverse Diffusion), which maps the temporal aggregate of this disagreement to a temperature field applied per pixel across all classes, so that confidence changes while the segmentation does not. Across cardiac, prostate and brain MRI shifts, CARD lowers calibration error in 45 of 49 comparisons against the strongest baseline in each setting.

Informal settlements represent a major urban challenge in rapidly expanding cities, yet their identification from Earth Observation (EO) data remains difficult because of their heterogeneous appearance and incomplete official inventories. This work presents a multi-sensor deep learning (DL) framework for slum-likelihood mapping in Córdoba, Argentina, integrating high-resolution PlanetScope multispectral (MS) imagery, COSMO-SkyMed (CSK) Synthetic Aperture Radar (SAR) data, and medium-resolution PRISMA hyperspectral (HS) observations. The problem is formulated as a patch-level classification task using the official Registro Nacional de Barrios Populares (ReNaBaP) inventory as reference, and the models are evaluated through four geographically partitioned folds. SAR-only and MS-only baselines, their configurations with PRISMA HS support, and early fusion (EF), middle fusion (MF), and late fusion (LF) strategies are systematically compared. Results show that LF+HS provides the best overall balance between classification performance and spatial selectivity, while PRISMA contributes complementary spectral information alongside the higher-resolution MS and SAR representations. Beyond the standard evaluation against ReNaBaP, an external municipal vulnerability layer is used to interpret detections outside the official polygons, showing that several apparent false positives overlap broader vulnerable urban areas. Thermal analysis further shows that ReNaBaP settlements exhibit significantly higher surface temperatures than their immediate surroundings during a heatwave event, indicating localised surface-heat amplification. Taken together, these results suggest that multi-sensor EO fusion can support both the mapping of ReNaBaP settlements and the interpretation of broader urban vulnerability patterns.

Scalable Vector Graphics (SVGs) power much of the modern visual ecosystem, yet state-of-the-art generative models focus almost entirely on rasterized images. We explore whether inference-time methods can unlock SVG generation capabilities in off-the-shelf vision-language models (VLMs). We systematically evaluate a constrained iterative refinement harness that combines visual feedback, structured editing, and constrained decoding to characterize the capabilities and limitations of current VLMs for SVG generation. Across multiple VLMs and generation settings, we find that constrained decoding improves compilation success rates, while iterative refinement reveals a deficit in visual reasoning and self-correction. Our results highlight both the promise and current limitations of using inference-time methods to adapt general-purpose VLMs for SVG generation.

We exhibit a binary linear $[50,40]_2$ code of covering radius $2$, so $\ell_2(10,2)\le 50$, one column below the Kaikkonen–Rosendahl length $51$ that has stood since 2003 and that still seeds the $R=2$ family of Davydov–Marcugini–Pambianco (arXiv:2511.02542). The new matrix admits a $(2,0)$-partition into ten blocks, so Construction $\mathrm{QM}_2^2$ propagates it to exhaustively verified codes of lengths $815$ and $1631$ at $r=18$ and $r=20$, and to the family $n=51\cdot 2^{r/2-5}-1$ of asymptotic density $2601/2048$. The matrices, verifiers, and source are at https://github.com/wustep/maths, pin problems/covering/share/2026-08-24/ at commit 736a38f.

Publicly-acceesible face-manipulation tools have made deepfake creation accessible to non-expert users. Against these, existing defenses are mostly post-hoc, detecting only after forgery has occurred, and operating on still images rather than videos. Research is lacking in i) the proactive protection of published facial videos against black-box manipulation tools, and in (ii) understanding its perceptual effect on human viewers. We introduce TaintedPixels, a proactive video-protection method built around an asymmetric visibility trade-off: the embedded watermark should remain inconspicuous in the published video but become obvious once a downstream tool manipulates the video. TaintedPixels injects structured periodic perturbations into the blue channel of facial regions and refines them under stripe-visibility, color-cast, and video-level LPIPS budgets, with lightweight motion-adaptive deployment. We believe TaintedPixels is the first proactive defense designed specifically against black-box manipulation tools rather than image-level pipelines or specific surrogate generators. Across three publicly available off-the-shelf video manipulation tools and two off-the-shelf detectors, TaintedPixels attains the highest forgery fake rate while keeping perturbations small (LPIPS = 0.0042). Our non-expert human study, conducted on a diverse set of 300 video stimuli spanning different lighting conditions, backgrounds, and skin tones, shows that protected source videos draw a 3.26% suspicion rate, while forgeries from protected sources are identified as fake much more often than forgeries from unprotected sources (90.72% vs. 56.71%). This validates the effectiveness of TaintedPixels.

Language-model agents increasingly tackle long-horizon tasks in interactive environments, yet their evaluation commonly relies on task-level success rates by reducing an entire execution trajectory to whether the task passes an official verifier. This binary score hides partial progress and is particularly limited for procedural agent skill evaluations, since a skill can alter execution without changing the final outcome. While checklists provide finer-grained evaluation by scoring individual task requirements, costly manual authoring and unreliable automatic generation make trustworthy evaluation difficult to scale. To address these challenges, we introduce Grounded Checklist Partial Credit (GCPC), a human-governed and LLM-instantiated partial-credit evaluation of agent trajectories. Humans define reusable rules once, from which an LLM instantiates a task-specific checklist grounded in the task instruction and official verifier. To keep judgment tied to evidence, a judge scores each item from execution log evidence alone and abstains when evidence is missing. A separate scripted step then applies the official verifier outcome to the score. Across a 4,455-trajectory, deduplicated SkillsBench evaluation population, GCPC better discriminates official PASS and FAIL outcomes than holistic judging on the shared subset (AUC 0.689 vs. 0.619). Human evaluation on 96 trajectories from 12 tasks shows that GCPC aligns more closely with human assessments of progress. Applied to 1,946 matched with/without-skill pairs, GCPC exposes the effects hidden by pass@1: among 879 pairs whose binary outcome does not change, 20.9% improve by more than 0.10 while 18.7% regress by the same margin. The GCPC pipeline also transfers to Terminal-Bench and SWE-bench, demonstrating applicability beyond skill-conditioned evaluation.

Tree cover maps are a fundamental remote sensing product, used to derive ecological insights about the landscape and are essential to change detection, vegetation mapping and fire monitoring programs. However, comprehensive tree cover mapping requires reliable and high-quality imagery, free of cloud and weather defects to ensure accurate model outputs. Deep learning approaches can generate high quality maps with minimal human intervention but require large amounts of human annotated data to be successful. In this work we propose a framework consisting of methods that aim to improve the data efficiency and robustness of deep learning models using data fusion techniques to segment woody vegetation defined as vegetation over the height of 2m across the state of New South Wales, Australia. To improve robustness against varying image quality, we propose an image composition method that normalizes the imagery and removes defects, whilst also minimizing the reliance on individual image quality by proposing a prediction fusion method. The two methods resulted in an error reduction of 38.2% and 53.6% respectively compared to single-source imagery. To address deep learning approaches' limitation of requiring large amounts of data, we apply label transfer to multiple sources of imagery as a form of data augmentation to improve data efficiency. Learning from multiple image sources was shown to be the biggest improvement in performance, resulting in an error reduction between 28.1% to 76.2% across the different validation experiments, whilst reducing the standard deviation of performance across image dates by a factor of 13.

In many reinforcement learning (RL) domains, environments are connected by prerequisite relations, such as difficulty-increasing edits or parameter increments, which induce a directed acyclic curriculum graph (DAG). Although this structure is often exploited only implicitly, explicitly modeling it can improve training. We introduce PATH, a curriculum-learning framework that performs active learning over the curriculum graph. PATH first expands coverage by sampling diverse curriculum paths and then reallocates training toward regions that remain unmastered. Experiments across diverse environments show that PATH explicitly leverages the graph structure to achieve strong robustness and generalization.

Compositional generalization is usually evaluated through model accuracy. We instead ask which structural or lexical identifications make held-out COGS examples admissible from the structures observed in training. Sentences are represented as functors from syntactic addresses to lexical tokens, and selective collapses induce Kan extensions that propagate observed associations. Across 21 COGS generalization types, admissibility follows distinct identification profiles, while residual failures separate unsupported structural templates. These data-side diagnoses characterize what the training corpus licenses under specified identifications, without training a predictive model.

Efficiency of skyline algorithms is highly influenced by the underlying data characteristics. Traditionally, optimization efforts have focused on minimizing the total number of tuple-pair dominance checks to improve query performance. However, in practice, a dominance check between two tuples does not necessarily require evaluating dominance relationships for each and every preference attribute of the data and this creates a disconnect between dominance checks optimization and query execution performance. In this paper, we argue that skyline algorithms need to optimize total per-attribute dominance checks, along with per-tuple dominance checks and that, for both of these goals, the ordering of the attributes (or variates) can have a substantial impact on the efficiency of skyline computation. Based on this premise, we present several strategies for identifying an effective variate order to minimize redundant attribute comparisons. Extensive experiments on both synthetic and real-world datasets, and on both scalar and SIMD architectures, confirm the effectiveness of the proposed approach in reducing computational overhead and improving skyline query performance.