arXiv:2607.13527v1 Announce Type: new
Abstract: Recent video generation models (VGMs) have made substantial progress in visual fidelity, yet their ability to follow long, compositional instructions remains insufficiently evaluated. Existing evaluation protocols often rely on prompts that are short and semantically shallow, with limited atomic constraints and weak spatio-temporal dependencies. They also frequently depend on costly human evaluation or handcrafted vision pipelines, while providing little diagnostic insight into which instruction constraints succeed or fail. To address this gap, we propose VGIF-Score, a highly automated and interpretable framework for evaluating instruction following in video generation. VGIF-Score consists of two complementary components: an objective completion branch that parses prompts into a Spatio-Temporal Directed Acyclic Graph (ST-DAG) and performs dependency-aware QA with short-circuit diagnostics, and a subjective satisfaction branch that uses instruction-conditioned AutoRubric to assess cinematography, visual purity, motion smoothness, and physics adherence. Together, these components produce a unified score that captures both objective completion and perceptual satisfaction. We instantiate this framework on VGIF-Bench, a benchmark of 223 long, structurally entangled prompts paired with approximately 4.3K fine-grained evaluation items. Experiments on 14 proprietary and open-source VGMs across more than 3K generated videos show that VGIF-Score provides reliable, interpretable, and diagnostically useful evaluation of video generation instruction following. The code will be available at https://github.com/PRIS-CV/VGIF-SCORE.
Science Journals
arXiv:2607.13554v1 Announce Type: new
Abstract: As quantum computing technology continues to mature, the US National Institute of Standards and Technology (NIST) has outlined a migration timeline for Post-Quantum Cryptography (PQC), recommending the deprecation of certain elliptic curve cryptography (ECC) by 2030. Furthermore, privacy-sensitive application scenarios, such as vehicular communications, require the use of anonymous certificates. However, existing anonymous certificate schemes are still largely based on ECC. Therefore, this study proposes a multivariate cryptography-based anonymous certificate scheme, aiming to design quantum-safe anonymous certificates suitable for privacy-sensitive application services. The proposed multivariate cryptography-based anonymous certificate scheme is supported by rigorous mathematical proofs and illustrated with computational cases.
arXiv:2607.13446v1 Announce Type: new
Abstract: Combinatorial optimization problems are central to many challenges in logistics, finance, engineering, and the life sciences, yet they remain among the most computationally demanding. Many of these problems can be mapped onto the Ising model, in which binary spins interact through a network of couplings, and solutions correspond to low-energy, ideally ground-state, spin configurations. Photonic Ising machines have the potential to be fast and energy-efficient heuristic solvers of optimization problems by leveraging the low latency, high bandwidth, and inherent parallelism of optics. However, current photonic implementations remain limited in scalability, connectivity, reconfigurability, and time-to-solution, preventing their use in many practical applications. In this perspective, we examine the current landscape of photonic Ising machines, discuss the challenges and limitations of existing platforms, and identify the scientific and technological advances needed to realize large-scale systems. These developments could establish photonic Ising machines as useful hardware platforms for practical optimization.
arXiv:2607.13669v1 Announce Type: new
Abstract: Multimodal speaker identification systems typically assume the availability of complete and homogeneous audio-visual modalities during both training and testing, and assume each speaker only speaks a single language. However, in real-world applications, such assumptions often do not hold. Visual or audio information may be missing due to occlusions, camera or microphone failures, or privacy constraints. Multilingual speakers introduce additional complexity due to linguistic variability across languages. These situations constitute substantial challenges for the robustness and generalization capabilities of multimodal speaker identification systems. Aim of the POLY-SIM 2026 challenge is to address these aspects of speaker identification and to provide a standardized setup for the comparison of the proposed solutions.
arXiv:2607.13455v1 Announce Type: new
Abstract: High-quality teleoperation datasets are costly to collect, particularly for hard tasks. We observe that many tasks exhibit directional asymmetry: completing the forward hard task is difficult, whereas reversing it by relaxing or disrupting the environment is comparatively easy. This suggests that reversed easy-task trajectories can serve as a scalable supervision signal for the hard task, reducing the cost of manual demonstration collection. However, reversed data can be noisy, and directly training on it may yield suboptimal policies. To enable largely automated acquisition and effective use of reversed data, we propose a teleoperation-cost effective framework for hard policy learning via temporal reversal of easy tasks, consisting of three key components: a closed-loop data collection pipeline that alternates between hard-task and easy-task policies to autonomously reset the environment and generate diverse trajectories; a hierarchical data refinement pipeline that temporally inverts easy-task rollouts and filters low-quality motion using kinematic priors and a critic-guided advantage filter; and an iterative policy learning method that trains the hard-task policy using both initial reversed easy-task demonstrations and the filtered reversed data in a continuous online learning loop. By combining automated collection, hierarchical refinement, and iterative learning, our method enables scalable, reliable training of complex, high-precision manipulation tasks. Across two simulated benchmarks and real-robot experiments, we demonstrate that our method improves hard-task success rates with higher data efficiency and more stable training compared to reversal-based and reinforcement-learning baselines, without requiring extensive hard-task teleoperation.
arXiv:2607.13458v1 Announce Type: new
Abstract: Scene Text Recognition (STR) remains challenging due to the diversity of text appearances, including curvature, rotation, and perspective distortion. Recent Transformer-based approaches perform well but usually rely on one-dimensional positional encodings that ignore the 2D spatial structure of text images. Axial 2D extensions of Rotary Position Embedding (RoPE) exist for vision Transformers, but they assume roughly square, isotropic image content and apply the rotation only within encoder self-attention. Scene text violates both assumptions: crops are markedly anisotropic, and STR models are encoder-decoder, so the decoder must relate its queries to the encoder's 2D layout through cross-attention. We introduce 2D-RoPE-STR, which adapts axial 2D-RoPE to this setting through (1) an anisotropic row/column dimension allocation matched to the aspect ratio of text, and (2) an extension of the rotary coupling into encoder-decoder cross-attention, letting autoregressive decoding steps attend to encoder tokens by their 2D layout, a setting not addressed by prior encoder-only formulations. Both changes are essentially parameter-free and require no architectural redesign beyond the positional-encoding module. We further introduce a diagnostic protocol (a controlled ablation pair isolating only the positional encoding, an image-level net-win disagreement analysis, and encoder attention visualization) that identifies where and why relative 2D position helps: curved, rotated, and perspective-distorted layouts where reading order departs from a straight horizontal line. On six standard benchmarks (IIIT5K, SVT, ICDAR 2013, ICDAR 2015, CUTE80, SVTP), gains concentrate on exactly these irregular layouts, with ablations isolating each design choice against 1D RoPE and 2D sinusoidal and learnable alternatives.
arXiv:2607.13677v1 Announce Type: new
Abstract: Local certification is a framework for verifying global graph properties using only local information. In this model, a prover assigns short labels, called certificates, to the vertices of a graph. Each vertex then exchanges certificates with its neighbors and performs a purely local check to determine whether the graph satisfies the desired property. This line of research has led to efficient certification schemes for a broad range of graph classes, including minor-closed families, topological graph classes, and graphs defined by forbidden subgraphs.
In this paper, we study the local certification of graph connectivity. Prior work by Bousquet, Feuilloley, and Pierron (JPDC 2024) showed that $2$-vertex-connectivity, $2$-edge-connectivity, and $3$-vertex-connectivity admit $O(\log n)$-bit certificates, leveraging structural characterizations such as ear decompositions. We go substantially beyond these cases and investigate general $k$-vertex-connectivity and $k$-edge-connectivity. We develop new approaches that exploit connections between connectivity and combinatorial structures, including branchings, Eulerian subgraphs, and independent spanning trees.
For $k$-edge-connectivity, we obtain an $O_k(\log n)$-bit certification scheme and prove a matching $\Omega_k(\log n)$ lower bound for every $k\ge 3$. The lower bound also applies to $k$-vertex-connectivity. For $k$-vertex-connectivity, we obtain $\tilde{O}_k(\sqrt{n})$-bit certificates for every $k$ under a conjecture of Itai and Zehavi. We further show that, for $k=2$, the logarithmic barrier can be broken on sparse graph classes: $2$-edge-connectivity admits constant-size certificates in bounded-expansion graphs, and $2$-vertex-connectivity admits constant-size certificates in bounded-degree graphs. In contrast, for $2$-vertex-connectivity in general graphs, we prove an $\Omega(\log(\log^\ast n))$-bit lower bound.
arXiv:2607.13492v1 Announce Type: new
Abstract: Neural implicit representations have emerged as a powerful paradigm for 3D reconstruction. However, high-fidelity indoor surface reconstruction remains a significant challenge, primarily due to the pronounced \emph{geometric heterogeneity} of indoor scenes. Large texture-less planar regions typically require stronger regularization to suppress high-frequency artifacts, while thin structures demand sharper, more adaptive representations to mitigate the spectral bias of multi-layer perceptrons (MLPs) and prevent over-smoothing. Existing approaches often rely on spatially indiscriminate prior supervision and a scene-global SDF-to-density transformation, which constrains their ability to balance planar smoothness and detail preservation. In this paper, we propose CASA-SDF (Curriculum-Aware Spatial Adaptation for SDF), a unified framework that addresses this challenge via complementary adaptations of supervision and representation capacity. Specifically, Hybrid Spatially-Adaptive Uncertainty Annealing (SAUA) fuses semantic and photometric uncertainties to construct a pixel-wise curriculum for monocular prior supervision. This strategy maintains regularization in reliable regions while attenuating unreliable supervision early in training to enable data-driven photometric refinement. Meanwhile, Curvature-Aware Locally Adaptive Density Transformation (CALADT) progressively modulates the sharpness of the SDF-to-density mapping via a curvature proxy to enhance the representation of thin structures. Extensive experiments on benchmark indoor datasets demonstrate that CASA-SDF improves surface completeness and detail recovery on high-frequency structures, without compromising the stability of planar surfaces.
arXiv:2607.13574v1 Announce Type: new
Abstract: We develop a convergent scheme to train neural networks involving analytic activation functions based on gradient flows. Convergence properties are guaranteed by Lojasiewicz theory. The main advantage of this approach is its simplicity of implementation. The coefficients of the network are approximated by solving a system of ordinary differential equations. We test the method by constructing residual neural network approximations of solutions of parametric problems. The dependence of the solutions of simple ordinary differential equations on a few parameters is correctly reproduced. The solutions of inverse problems involving wave constraints which depend on a few parameters can be reasonably approximated, even in regions in which the problem is severely ill posed.
arXiv:2607.13682v1 Announce Type: new
Abstract: Radiative Gaussian splatting has made sparse-view CT reconstruction fast, but existing methods output point estimates with no notion of where the reconstruction can be trusted. We exploit a property of transmissive X-ray imaging that RGB splatting cannot claim -- projection and voxelization are strictly linear in the per-Gaussian densities -- to equip radiative Gaussians with a variational density posterior whose predictive variance propagates in closed form, exactly, in a single forward pass, in both volume space ($\sigma^2(x)=\sum_i g_i(x)^2 s_i^2$) and projection space ($\mathrm{Var}[I_p]=\sum_i w_{i,p}^2 s_i^2$). We present the first systematic calibration study for Gaussian-splatting CT (Spearman / AUSE / ECE with temperature scaling), showing that the resulting per-voxel uncertainty ranks true reconstruction error on 14 of 15 scenes of the official benchmark across three view budgets -- 9 of 15 additionally meeting our magnitude-calibration target after a single temperature -- while the perturbation-ensemble heuristic of concurrent work, transplanted to voxel space under the same protocol on our development scenes, does not (rank correlation as low as $-0.08$). We then dissect why uncalibrated acquisition scores can nevertheless select acceptable views, identifying three regimes -- flat (isotropic, balanced), pathological (degenerate coverage), and anisotropic -- and showing, in controlled single-scene testbeds, that principled uncertainty earns a measurable premium only in the last, motivating a coverage-gated, maturity-scheduled acquisition policy; the same calibrated posterior further points toward a dose-adaptive stopping rule, whose experimental validation we leave to future work.
arXiv:2607.13692v1 Announce Type: new
Abstract: Connected and automated vehicles (CAVs) are expected to increasingly rely on 5G and future 6G ultra-reliable and low-latency communication (URLLC) services to support safety-critical and time-sensitive applications. Since wireless link conditions can vary rapidly in urban vehicular environments, proactively adapting service parameters based on future channel conditions is essential to maintain service continuity and reliability. In this paper, we investigate the use of machine learning (ML) techniques for channel quality prediction in vehicular URLLC scenarios. Specifically, we evaluate deep neural network (DNN) and long short-term memory (LSTM) models to forecast future channel conditions and enable proactive service adaptation with minimized performance degradation. The analysis is conducted using realistic simulations combining the SUMO traffic simulator and the Sionna-RT ray-tracing framework in a real urban environment reconstructed from OpenStreetMap data. Results show that ML-based prediction significantly outperforms approaches relying solely on past channel measurements and achieves performance close to the ideal case in which future channel conditions are perfectly known in advance. These findings demonstrate the potential of ML-driven prediction techniques to enhance the reliability and robustness of URLLC services for connected vehicular systems.
arXiv:2607.13542v1 Announce Type: new
Abstract: Topological structuring of light inevitably leverages on optical coherence to ensure that the imparted spatial phases are preserved, requiring highly coherent sources or coherence engineering embedded in the design. Now we show that thermal light can be spatially engineered to carry optical topologies in the form of Skyrmions. Such topologies are immune to time averaged decoherence, a fact we leverage on in reverse to create metasurface mediated incoherent topologies from a thermal source. The pristine nature of our measured Skyrmions validates the approach, while simulations reveal how coherence management in the metasurface design would further enhance the functionality. Remarkably, the generation stage inherits robustness from the topology, remaining immune to material and fabrication defects. Our work reports the first topologies from purely thermal light, opening a path to exploiting topology in ubiquitous everyday light sources.
arXiv:2607.13606v1 Announce Type: new
Abstract: Dynamic wetting plays a fundamental role in the dynamics of droplets and bubbles at solid surfaces by influencing contact line motion and interfacial evolution. In this work, three representative wetting-controlled benchmarks, namely droplet splashing, bubble coalescence at solid surfaces, and bubble dynamics under shear flow, are investigated using a three-dimensional volume-of-fluid framework coupled with a recently developed dynamic wetting model based on contact line velocity reconstruction method [19]. The model is first validated against experimental observations and literature data for droplet splashing and bubble coalescence. It accurately reproduces the transient contact line evolution, splashing morphology, and coalescence dynamics. In particular, dynamic wetting suppresses the premature bubble detachment predicted by static wetting models and yields substantially improved agreement with experimental observations. In shear flow, contact angle hysteresis and contact line dissipation strongly influence bubble deformation, sliding, and detachment. These results demonstrate that accurate treatment of dynamic wetting is essential for predicting wetting-controlled droplets and bubbles involving rapid contact line motion, strong interfacial deformation, and topology changes.
arXiv:2607.13703v1 Announce Type: new
Abstract: We investigate conditional invertible neural networks (cINNs) as probabilistic inverse-dynamics models for multirotor control. For a planar X8 coaxial multicopter, we learn $p(u \mid s_t, c_t)$ from an incremental nonlinear dynamic inversion (INDI) teacher using rational-quadratic spline coupling and invertible linear mixing. Open-loop reproduction reaches $R^2 = 0.944$, mean CRPS 0.0915, and log-probability-error correlation $\rho = -0.60$. Over 15 closed-loop scenarios, position RMSE matches INDI (9.7 vs. 9.5 m), with 47 percent tracking acceptably; failures separate into attitude divergence under aggressive steps and phase lag under high-frequency references, isolating command bandwidth and data coverage as dominant failure mechanisms.
arXiv:2607.13589v1 Announce Type: new
Abstract: Boron neutron capture therapy (BNCT) requires knowledge of patient-specific $^{10}$B concentration for accurate dose estimation, yet no established method provides real-time boron-sensitive information during irradiation. Backscattered thermal neutrons carry a $^{10}$B-dependent intensity modulation through the $^{10}$B(n,$\alpha$)$^{7}$Li reaction, documented in BNCT treatment rooms for three decades but not yet developed as a measurement signal. This paper uses Monte Carlo simulation to assess the feasibility of backscattered thermal neutrons as a measurement channel for $^{10}$B concentration. A thin $^{nat}$LiF-converter detector placed at the beam exit captures the composite forward-plus-backscatter field; differential imaging against a $^{10}$B-free baseline isolates the $^{10}$B-dependent component, quantified by the fractional reduction in the $^{6}$Li capture rate, termed Relative Detector Signal Reduction (RDSR). In homogeneous phantoms, RDSR shows linear concentration dependence ($R^2 = 0.997$) with a practical depth limit of approximately 6 cm. Edge-response analysis yields a diffusion-limited FWHM of 32-176 mm over 1-5 cm depth, with weak concentration dependence. In a voxelized patient phantom across 12 boron configurations, the $^{6}$Li capture cross-section provides intrinsic thermal neutron energy selectivity that preferentially weights the band where $^{10}$B absorption is concentrated. Region-of-interest integration achieves counting-statistics sensitivity below 10 ppm; the systematic detection floor (~22-28 ppm at $\pm$1% baseline uncertainty) identifies baseline-reference precision as the dominant constraint. The modeled detector produces limited dose perturbation (+11.6% treatment-time increase). These results establish the physical basis for a boron-sensitive backscattered neutron measurement concept in BNCT.
arXiv:2607.13929v1 Announce Type: new
Abstract: Financial observations are continuous, heterogeneous, and noisy, whereas decoder-only next-token models are usually built around discrete symbolic inputs. We introduce Vector-Input Autoregressive Inference for Ordinal-Return Modeling (VAIOM), a decoder-only Transformer for probabilistic next-return modeling on one-hour foreign-exchange bars. VAIOM separates input representation from output likelihood: continuous multivariate financial-event vectors preserve numerical structure at the input, while a categorical distribution over the next volatility-normalized return bucket supports cross-entropy training and likelihood evaluation. The selected 0.9M Hybrid Continuous Input model combines continuous event features with categorical asset metadata, a Mixture-of-Market-States return head, Gap, volatility-regime, and Ordinal auxiliary objectives, and full-sequence supervision. Models and preprocessing are fit using pre-2024 Train data; models are selected on 2024H2 Validation and evaluated without refitting on two 2025 Test periods. Across three independent training seeds, every model outperforms fixed single-bar LightGBM baseline in both Test halves. For the canonical checkpoint, paired gains over LightGBM are 0.029 and 0.043 bits per event. Validation experiments show that continuous input improves over discrete-token input under the same categorical return objective, full-sequence supervision improves over last-position training, and auxiliary representation shaping together with a mixture-structured return head improves return likelihood in controlled comparisons. A supporting capacity study finds that the smallest evaluated complete architecture rung achieves the strongest Validation likelihood on the present corpus.
arXiv:2607.13306v1 Announce Type: new
Abstract: Standard Maxwellian plasmas exhibit a mathematical \textit{rigidity}, possessing insufficient degrees of freedom to support electrostatic double layers (DLs) and yielding only soliton solutions. This study investigates the hypothesis that the formation of DLs is a generic consequence of breaking this structural rigidity through parametric perturbation. By introducing two independent continuous control parameters, $\delta_1$ and $\delta_2$, into the electron distribution, we demonstrate that DLs are a structural property of any plasma model that relaxes the strict Maxwellian constraint. Through a Gardner small-amplitude expansion, we analytically prove that a perturbation must modify both the quadratic and cubic density coefficients to decouple the nonlinear structure and generate physical, supersonic double layers, deriving small-amplitude acoustic-limit threshold conditions of $\delta_1 > 1$ and $\delta_2 > 7/3$. We show that these theoretical boundaries broaden for large-amplitude, nonlinear structures. By mapping the exact existence regions of DLs in phase space, we demonstrate how higher-order terms relax the weak-amplitude limits, confirming that the Maxwellian state represents a singular point where the DL solution collapses.
arXiv:2607.13607v1 Announce Type: new
Abstract: Algorithmic collusion among pricing algorithms has raised concerns about sustained supra-competitive prices and their implications for social welfare. Existing work has largely focused on the probability that reinforcement-learning algorithms converge to cooperative strategies, typically under the assumption that exploration vanishes over time. Motivated by the observation that algorithms deployed in practice are likely to continue exploring in order to remain adaptive to changing environments, we study learning dynamics under constant exploration. In this setting, the relevant question is no longer whether an algorithm converges to a particular strategy profile, but rather what fraction of time the algorithms spend playing cooperative strategies. Even in the benchmark case of the repeated Prisoner's Dilemma with one-period memory, this yields high-dimensional stochastic learning dynamics, for which a complete analytic treatment is intractable. We show that cooperative strategies can be dominant in this time-averaged sense and derive a boundary predicting when such dominance arises, based on the expected dynamics of the Q-learning process. Extensive simulations show that this boundary is a strong predictor for non-defection-dominated behaviour under epsilon-greedy Q-learning.
arXiv:2607.13326v1 Announce Type: new
Abstract: Public communication of science has become a central component in the relationship between science and society. However, the media exposure of research staff has given rise to new forms of hostility, especially in digital environments. The study Experiences of researchers who interact with the media and social networks in Spain [Science Media Centre Spain, 2024] investigates - via a survey (N=237) - the incidence and typology of these attacks in the Spanish context. More than half of the research staff (51.05%) reported experiencing negative incidents, with a higher prevalence among women (56.9%) than men (46.2%). The attacks differ by gender: women face more challenges regarding their scientific capacity and sexist remarks, whereas men are more frequently targeted over their professional integrity. These dynamics reveal structural gender biases that affect the wellbeing and legitimacy of female scientists, emphasising the need for institutional policies with a gender perspective.
arXiv:2607.13369v1 Announce Type: new
Abstract: We present xChk, a reference identity provider for Bring Your Own Identity (BYOI): users enroll via heterogeneous proofs (government KYC, corporate SSO, WebAuthn/FIDO2, professional networks, live verification, longitudinal activity, behavioral signals) and disclose them as portfolio claims in standard OAuth 2.0 / OpenID Connect (OIDC) tokens, while each relying party applies its own sufficiency policy - the IdP transports claims and may evaluate an RP-supplied evidence policy for consent, but does not adjudicate access. Enrollment depth varies by modality (some paths are user-initiated; org KYB and officer binding are operator-assisted).
xChk also supports human-in-the-loop attestation for high-risk actions: humans can initiate attestations directly (browser UI / POST /api/attestations), and AI agents acting under those principals can trigger the same gateway via scope-gated authorize/attest - hash-chained human approvals on a shared verification graph (humans via OIDC; agents via API keys). A production deployment at https://in.xchk.io ships both initiation paths with bilateral RP evaluation at consent; one documented relying party (https://crabbyed.com, Appendix B) exercises Login with xChk.
arXiv:2607.13372v1 Announce Type: new
Abstract: Discourse data are the primary empirical basis of grammar writing in field linguistics, but producing interlinearized text is notoriously expensive - on the order of one hour of work per minute of recording. For endangered languages, where the time remaining to verify analyses with native speakers is itself limited, automating parts of the interlinearization workflow has direct documentary value. We implement a full neural annotation pipeline (morpheme segmentation, POS tagging, glossing) for Irabu Ryukyuan using deliberately small, transparent BiLSTM-CRF models, and evaluate it under a realistic hard constraint: approximately one hour of fully annotated discourse as the entire supervised resource. Two factors of the annotation itself are manipulated: its richness (with or without a POS tier) and its quantity (training budgets from 6 to 47 minutes). Gold POS improves grammatical glossing by +4.4 (SD 0.7) points (significant in all 5 seeds), and the gain grows as data shrink (+11.6 points at a quarter of the data); a POS tier more than halves the amount of glossed data needed to reach a given accuracy. In a fully automatic pipeline this gain is not yet realized: the tagger still errs on 12% of morphemes, and an incorrect POS misleads the glossing model more than no POS at all. The value is latent rather than lost: degrading gold POS with controlled noise shows the gain returning as tagger accuracy rises, with break-even near our tagger's current 88% and +1.6 to +3.2 points recovered at 92-96%. We conclude with a concrete recommendation for documentation practice: annotate quadrilinearly - text, POS, gloss, translation.
The impact of objective interactions on the performance of massive objective optimization algorithms
arXiv:2607.13377v1 Announce Type: new
Abstract: Many-objective optimization has been a field of interest over the past two decades and several evolutionary optimization algorithms have been introduced to tackle these problems; yet two fundamental questions remain underexplored: (i) What happens when the number of objectives grows beyond the typical many-objective regime of about fifteen and becomes massive? (ii) How do problem characteristics, such as the nature of interactions between objectives, influence algorithmic performance? To answer these questions we employ a diagnostic benchmark suite that allows control over problem characteristics and can be scaled to extremely high objective counts. Using this framework we evaluate several state-of-the-art evolutionary algorithms including NSGA-II, NSGA-III, MOEA/D and lexicase selection across a range of dimensionalities and diagnostic problem landscapes. Our experiments reveal that problem characteristics significantly affect algorithm performance. In particular, the nature of interactions between objectives appears important. These results highlight the importance of understanding these properties before selecting an algorithm for a specific problem. We also show that lexicase selection, an algorithm originally designed for genetic programming, compares favorably with state-of-the-art many-objective optimization algorithms while avoiding the dependence on predefined reference directions.
arXiv:2607.13420v1 Announce Type: new
Abstract: Clicks on homepage marketing blocks are driven by a dual-mechanism of content interest and access habits. However, habitual clicks often create Pseudo-Positives in marketing slots, where position advantage masks mediocre content quality, leading to biased recommendation ecosystems. We propose a framework called Orthogonal Disentanglement of Access habits (OrDA) to purify interest signals. OrDA utilizes a dual-tower structure with a gated allocation layer to adaptively route features and minimize interference. To ensure rigorous separation, we employ orthogonal regularization to constrain the latent interest and habit manifolds to be geometrically perpendicular. OrDA performs causal intervention (do-calculus) during inference to rank items solely by purified interest scores. Empirical online evaluations on large-scale datasets demonstrate that OrDA effectively eliminates access-habit bias, outperforming state-of-the-art methods in predictive accuracy. Online AB test 5.64% shows user click-through rates (UCTR) improvement on the Zhima homepage marketing block, Zhima rent-floor recommendation.
arXiv:2607.13451v1 Announce Type: new
Abstract: Simulating deformable objects is essential for a wide range of robotic manipulation applications, yet accurately predicting their dynamics remains challenging. We propose Physics-Guided Residual Dynamics (PGRD), a hybrid simulation framework that combines the advantages of physics-based and learning-based approaches. Specifically, PGRD combines an optimizable spring-mass simulator as a backbone with a learned neural network that predicts residual corrections to the physics-based predictions. We adopt a velocity-based formulation to ensure stable simulation and a sliding-window transformer architecture to capture temporal dependencies. We show that PGRD produces more accurate results than both purely physics-based and learning-based methods on a set of diverse real-world deformable objects. We further demonstrate the utility of PGRD in two applications: manipulation planning via Model Predictive Control, including a language-conditioned setting with a generated goal image; and interactive simulation via action-conditioned video prediction by 3D Gaussian Splatting.
arXiv:2607.13479v1 Announce Type: new
Abstract: Estimating the full shape of a deformable object is especially challenging when vision is unavailable: in the dark, inside an opaque bag, behind the manipulating hand, or under heavy self-occlusion. Touch is the natural sensor in these settings, but touches are sparse and local. We present a single topology-agnostic estimator that reconstructs the full mesh of a deformable object from only a few touches and no vision, using one permutation-invariant cross-attention architecture that handles a 1D rope, a 2D cloth, and a 3D volumetric soft body. The learned estimator reduces reconstruction error by roughly two-thirds relative to non-learned geometric mesh completion and a Gaussian-process surface baseline, and it outperforms a simpler global-pool set encoder, with the gap growing as more touches are observed. We then show that the estimator's deep-ensemble uncertainty can be used to learn where to touch next, which lowers error further and beats both random touching and a Gaussian-process active baseline at sparse budgets. This gain is modest on average but grows with self-occlusion and on the error tail. When vision is also available, where to touch barely matters, motivating the vision-free setting we study.