Science & Mathematics

Agentic knowledge graph question answering (KGQA) requires large language models (LLMs) to solve complex questions through multi-turn interactions with a knowledge graph (KG). Outcome-supervised reinforcement learning derives verifiable outcome rewards from final answers but uniformly assigns each rollout's outcome-level advantage to all policy-generated tokens, creating a trajectory-to-operation mismatch since KG operations within a rollout can have varying effects on the search process and final answer. To address this, we propose Outcome-Anchored Credit Reallocation (OACR), which employs a training-only KG-state outcome model to estimate outcome-reward changes between adjacent KG search states and converts them into operation credit, from which token-wise weights are derived. These multiplicative weights reallocate token-level update magnitudes while preserving the sign of the outcome-level advantage at every generated token. Across three benchmarks, OACR achieves stronger overall performance than existing KGQA methods while using fewer inference-time LLM calls and tokens.

We introduce radial basis function (RBF) kernels for Gaussian processes that use structured hyperparameter sharing for image-valued inputs. For high-dimensional inputs such as images, a fully anisotropic RBF kernel assigns a separate lengthscale to each input dimension, which can introduce many hyperparameters and may lead to overfitting and poorly calibrated predictive uncertainty when data are limited. We propose structured relevance determination by tying lengthscales across groups of adjacent pixels and within each colour channel. This yields patch-wise and channel-wise constrained anisotropic RBF parametrisations that reduce the number of independently learned lengthscales. We further introduce channel-additive Gaussian processes for multi-channel images and combine them with structured relevance determination, resulting in a parameter-efficient decomposition of the latent function into components defined on channel subsets, enabling some non-local generalisation. The proposed kernels are evaluated on MNIST and a compact binary aircraft-detection dataset of low-resolution RGB satellite image chips. We also show how channel-wise structured relevance determination can be incorporated into convolutional Gaussian processes. We observe improved predictive performance compared to isotropic and fully anisotropic RBF baselines.

Image harmonization methods adjust the colour and lighting of an object pasted into a photograph so that it looks native to its new scene, and they are ranked by average error on one benchmark whose test images are real photographs with one object recoloured. One photograph can yield several such test images, and the benchmark promises that no photograph appears in both the training and the test split. We find that 1,399 photographs do, and the composites built on them are a quarter of the test set. Duplicate checks over file names or bytes miss this, because every composite is a different file. On that quarter the three methods we score end to end read two to five times lower error than on the rest, but most of the gap is composition rather than the sharing: the shared composites come almost entirely from one of the benchmark's four source collections, and inside that collection the gap falls to about one and a half times. An official score is therefore an average over two populations, mixed in a proportion the benchmark does not report. We release a test list of 5,581 composites whose construction identities do not appear in training, with four confirmed near-duplicate pairs disclosed rather than removed, adoptable without retraining at the price of one rescore per checkpoint. We leave open whether the sharing itself changes what a model learns.

Empirical studies of electricity prices routinely state that their models use only information available at the time of the trading decision. For weather-driven forecasts drawn from commercial archives, this condition is harder to meet than it appears, and whether it holds can change over time. We identify three timing pitfalls. A forecast run is labelled by the issue time of its weather model, but becomes available hours later and keeps changing after publication. Auction gates follow local clock time, while archives use UTC. Outturn series are revised after publication without earlier values being kept. Using the timestamps of 128,656 forecast runs from ten weather-model configurations, matched to the day-ahead and first intraday auction gates in Great Britain over 2022-2026, we find that selecting "the latest run issued before the gate" picks a run not yet published at the gate on more than 99% of delivery days for six of the ten configurations at one of the two gates. For GFS at the day-ahead gate, the share is 0.6% in winter and 99.8% in summer. The exposure also shifts as publication delays drift, and an action margin of a few minutes can cost a full six-hour forecast cycle. The wrongly selected inputs differ materially from those available at the gate, but their apparent accuracy gain ranges from -9% to +24% across variables, models, gates and seasons, so its effect cannot be assumed and must be measured. We argue that point-in-time correctness is a dynamic property of the data pipeline, and propose a protocol that audits it from timestamps before any model is fitted.

Visual autoregressive models produce convincing images but can misassign attributes and spatial relations. Searching multiple generation paths can improve composition, yet completing every candidate is costly. We introduce ATLAS, a training-free framework that uses the frozen generator's internal attention to guide search before final images are available. Within-prompt diagnostics identify attention-derived scores that predict final compositional preferences on Infinity, with category-dependent transfer to Switti. ATLAS uses these on-the-fly signals to progressively concentrate computation on promising trajectories. It maintains multiple coarse alternatives, prunes candidates without decoding at intermediate scales, and reserves image-space evaluation for a final choice among partial trajectories. ATLAS scales effectively on both backbones, achieving higher mean scores on the evaluated T2I-CompBench and GenEval categories as more computation is devoted to search. At the largest tested budget, the targeted T2I-CompBench mean improves by over 10% relative to each backbone. Separate profiles show over 50% less generation time than completing and evaluating all candidates at equal initial counts, alongside lower peak allocated GPU memory. Relative time savings are larger at the higher tested candidate count. Together, these results support scalable compositional search: additional sampling expands exploration, while attention-guided selection limits continuation cost without parameter updates or gradient-based optimization.

We study the mixing time of the single-site Glauber dynamics for sampling proper \(q\)-colorings on sparse Erdős-Rényi random graphs \(\mathcal{G}(n, d/n)\). We prove that, whenever \(q \ge (1 + o_d(1))d\), Glauber dynamics mixes in polynomial time with high probability over \(\mathcal{G}(n, d/n)\) for all sufficiently large integer \(n\). This improves the previous bound \(q = (α^* + o_d(1))d\) where \(α^* = 1.7632...\) is the unique solution of \(x = \exp(1/x)\) on \([1, \infty)\) by Efthymiou, Hayes, Štefankovič, and Vigoda (SODA, 2018) and asymptotically matches the uniqueness threshold on infinite regular trees. Our proof has three main ingredients. First we establish logarithmic bounds on the spectral and coupling independence constants of the Gibbs distribution by extending the tree analysis of Chen, Liu, Mani, and Moitra (J. ACM, 2026). Second, we extend the entropy-factorization framework for two-spin systems on random graphs, developed by Bezáková, Galanis, Goldberg, and Štefankovič (TALG, 2024), to proper colorings by introducing a buffer around high-degree vertices. Finally, we compare the resulting heat-bath block dynamics with the single-site Glauber dynamics.

Explicitly modeling periodicity has proven to be an efficient approach for time series forecasting, where the residual, obtained after removing the periodic component from the time series, is typically treated as unstructured noise. However, in this work, we show that such residuals still exhibit structured, \textit{phase-dependent} deviations, as supported by both empirical observations and theoretical analysis. This suggests that residuals should not be treated merely as unstructured noise, but instead as \textit{phase-conditioned signals} whose variations arise in both direction and magnitude. Motivated by this perspective and inspired by phase and amplitude modulation in classical signal processing, we propose \textit{Paloma}, a simple yet effective framework for modeling residual deviations. Specifically, Paloma comprises two complementary modules: \textit{a Phase Rotation module}, which performs phase-conditioned rotations to capture directional changes in the feature space, and \textit{an Amplitude Scaling module}, which applies phase-conditioned affine transformations to model magnitude variations. We further abstract the two modules into a general-purpose plugin, termed the \textit{Paloma technique}, which can be readily integrated into existing forecasting architectures to modulate input sequences in a phase-aware manner, enabling backbone models to capture phase-dependent variations in both direction and magnitude. Extensive experiments on twelve datasets demonstrate that Paloma achieves state-of-the-art and robust forecasting performance. Additional results show that the Paloma technique consistently improves a wide range of baseline models, validating its effectiveness as a general-purpose component. Our Code is available at \url{https://github.com/TSTS13/Paloma}.

Conditional-flow text-to-speech (TTS) models can achieve high synthesis quality with relatively few sampling steps, but collapsing the remaining trajectory to a single update can still cause substantial quality degradation. We propose MixiSpeech, a progressive state distillation framework that converts a multi-step conditional-flow acoustic model into a one-step generator while preserving its architecture and speaker conditioning. Rather than training the one-step model directly, MixiSpeech progressively reduces the global sampling budget through a 10-4-2-1 curriculum, with each student trained to match local teacher-integration endpoints using a masked state-matching objective. We instantiate the framework on a 710-speaker Vietnamese Matcha-TTS model trained from scratch on PhoAudiobook. On 100 shared test text-speaker pairs, direct one-step inference substantially degrades synthesis quality, obtaining 1.6846 UTMOS22-Strong and 6.21% WER compared with 2.2923 and 4.65% for the 10-step teacher. In contrast, the distilled one-step model achieves 2.2678 UTMOS22-Strong, 4.63% WER, and 2.83% CER, recovering most of the quality lost at the one-step operating point while requiring only a single acoustic vector-field evaluation. End-to-end inference time decreases from 0.0662 s for the 10-step teacher to 0.0312 s for MixiSpeech, corresponding to a 2.12 measured speedup. These results show that progressive state distillation can make one-step conditional-flow TTS practical without relying on a large multi-step sampling budget. Project page: https://mixispeech.solanai.us/

Turning a moving-camera perspective video into a 360° video requires more than just generating content outside the input frame: observations revealed over time must be preserved, unseen regions completed, and the resulting scene kept consistent as the camera viewpoint changes. Existing methods assign these different requirements to a single conditional video model, requiring them to be jointly learned from panoramic video data. We instead present a modular, 3D-driven framework that distributes these three responsibilities across specialized components, all connected through a shared scene representation. Input observations are reconstructed explicitly in 3D, while a pretrained panoramic image model completes unobserved content from a selected panoramic render. This generated content is lifted into the shared 3D scene, where it remains spatially anchored across camera viewpoints. Without requiring any additional panoramic-video training, our framework achieves state-of-the-art input-view fidelity, perceptual quality, and geometric consistency on a static-scene subset of the Argus evaluation set. These results support our decomposed, 3D-driven formulation as a promising alternative to direct video generation in this setting.

Reflections, glare, transparent structures, and material-dependent appearance variations can introduce ambiguity into RGB-based visual perception in vehicle-relevant environments. Polarization provides complementary reflection- and material-sensitive information, but its acquisition requires dedicated sensing hardware. This paper presents RGB-P Wild, a real-world dataset containing 10,000 paired RGB and four-angle linear-polarization image sets, together with PolarVis, a diffusion-based framework for recovering polarization representations from a single RGB image. PolarVis combines hierarchical RGB feature extraction, diffusion-based feature refinement, four angle-specific decoders, and multi-scale attention recalibration to reconstruct polarization intensity images at $0^\circ$, $45^\circ$, $90^\circ$, and $135^\circ$. On RGB-P Wild, PolarVis achieves a normalized-domain MSE of 0.0465, a PSNR of 27.83 dB, and an SSIM of 0.8597. Compared with the released PolarAnything model under the adopted evaluation protocol, PolarVis obtains an AoLP error of $25.66^\circ$ and a DoLP MAE of 0.0404, compared with $46.03^\circ$ and 0.1084, respectively. Cross-dataset evaluation on vehicle-mounted imagery further examines transfer beyond the training domain. In downstream evaluation, a frozen PCDNet achieves AP50/AP50:95 of 86.3%/59.1% on 990 RGBP-Car test images using PolarVis-generated polarization, compared with 87.0%/59.8% using measured polarization. These results indicate that RGB-derived polarization retains useful polarimetric information for the evaluated perception tasks, while remaining distinct from calibrated physical polarization measurements.

Visual-inertial odometry systems are often constrained by the assumption that sensors are rigidly mounted, which limits their adaptability in practical scenarios involving structural motion. To address this limitation, this paper investigates time-varying camera-IMU extrinsic calibration. First, a dynamic camera-IMU extrinsic calibration method based on the Denavit-Hartenberg convention is proposed by incorporating the robot kinematic model. Second, a two-step initialization strategy is developed to efficiently estimate the initial joint angles, providing a reliable starting point for subsequent extrinsic parameter optimization and enabling online estimation of timevarying camera-IMU extrinsic parameters. Simulation experiments demonstrate that the proposed framework can effectively accommodate variations in camera-IMU extrinsic parameters while maintaining competitive localization accuracy.

Reinforcement Learning with Verifiable Rewards (RLVR) can improve reasoning in large language models, but specialized non-English domains expose a data mismatch. Raw English domain text is often available, while target-language RLVR tasks with verifiable rewards are scarce. We introduce code-switched task synthesis for cross-lingual RLVR, a data-centric approach that derives target-language and code-switched RLVR task variants from otherwise unverifiable English domain text. Using fill-in-the-middle multiple-choice QA as a seed task format, we synthesize automatically verifiable tasks from domain passages and reshape them into cross-lingual variants. These variants preserve the same evidence-answer relation but change how English and target-language evidence are presented during RLVR. On Korean medical benchmarks and cybersecurity benchmarks across four target languages, code-switched training outperforms matched monolingual and bilingual-mixture baselines on average target-language performance while maintaining comparable English performance. Additional analyses provide evidence of better target-language input understanding and stronger cross-lingual alignment in both model outputs and internal representations. These results suggest that code-switched training helps target-language inputs access domain reasoning learned more strongly in English.

This paper studies LiDAR-assisted RGB semantic segmentation, where LiDAR point-cloud features improve dense pixel-wise predictions in the RGB image plane rather than 3D point labels or detections. Existing 2D fusion methods often project point clouds into shallow depth/range maps and apply spatially uniform fusion, discarding rich 3D structure and ignoring the range-dependent reliability of outdoor LiDAR. We propose RAHF-Net, a Range-Aware Heterogeneous Fusion Network. Its Cylindrical-to-Perspective (C2P) module projects pretrained cylindrical voxel features into the image plane, preserving structured 3D semantic priors. A Range-Aware Heterogeneous Fusion (RAHF) module then uses a soft depth-derived range mask to perform LiDAR-guided geometric enhancement in reliable near-field regions and visual-context enhancement in sparse far-field regions. On KITTI-360, RAHF-Net achieves 65.76 mIoU, outperforming representative RGB-only and RGB-LiDAR baselines, including CMX by 1.45 points. Experiments on DELIVER further demonstrate improved robustness under adverse weather, illumination degradation, and sensor corruption.

For practical motion generation, it is essential to handle multimodality (multiple actions can be correct for the same observation) while maintaining low inference cost and strong generalization from limited demonstrations. We introduce an attentive mixture-density policy trained with the Energy Score that represents future visuomotor trajectories as explicit probability distributions with a single forward pass. Concretely, we output Gaussian mixture parameters for joint commands (and optionally attention points) and optimize them with the Energy Score (computed as a sum of 1D CRPS under a diagonal covariance assumption) instead of the negative log-likelihood (NLL) to avoid MDN singularities and gradient-scale instabilities. Our architecture couples explicit spatial attention with mixture-density outputs, enabling robust multimodal behavior selection under visual noise and small-data regimes. On an 8-DOF manipulator, the method generates distinct avoidance trajectories and stabilizes learning in obstacle avoidance. Moreover, in a randomized moving-object grasping task, where spatiotemporal multimodality and fast timing decisions are required, the proposed model outperforms Diffusion Policy by 15-25% under several unseen conditions, demonstrating superior generalization and real-time feasibility.

Large language models (LLMs) have achieved strong performance across diverse reasoning tasks, yet it remains unclear whether this performance reflects an understanding of underlying logical structure or a reliance on shallow semantic cues. A key indicator of such understanding is whether models treat logically equivalent inputs consistently, producing the same predictions despite differences in expression. Through systematic evaluation on curated data, we show that even strong LLMs often fail this test: they do not consistently preserve predictions across logically equivalent inputs and generalize poorly to unseen logical forms. To address this limitation, we propose LoGIcal STructure-guided reasoning (LoGIST), a framework that guides LLM reasoning with explicit logical structure. LoGIST maps each input instance to a decision diagram, a directed acyclic graph that captures the underlying logical structure, and encodes this graph into a logical embedding that conditions the LLM's reasoning process. Across multiple training settings, LoGIST reduces inconsistency under logical equivalence and improves generalization to unseen logical forms, suggesting that logical invariance is a useful target for building more robust and generalizable logical reasoning in LLMs.