arXiv:2606.28933v1 Announce Type: new Abstract: Venture capital (VC) investment decisions face distinct challenges, such as multi-source heterogeneous data, non-stationary time series, and the demand for explainable predictions in high-stakes, low-data settings. To overcome these issues, we introduce \textbf{FinInvest-GTCN}, a Graph-Temporal-Causal Network that redefines the task from content recommendation to quantitative risk-return assessment. This architecture combines a relational graph encoder to capture the investment ecosystem's topology, a multi-scale temporal fusion module to handle long-term dependencies and non-stationarity, and a causal decision head that generates risk-adjusted predictions with interpretable causal attributions. A core innovation is the Meta-Causal Adaptation (MCA) strategy, which facilitates robust fine-tuning for new, data-scarce sectors by aligning updates with causally-plausible structures derived from meta-pretraining. Comprehensive experiments on proprietary VC datasets show that FinInvest-GTCN delivers state-of-the-art results, markedly lowering the primary Risk-Adjusted Mean Squared Error (RA-MSE) to 2.51 from a baseline of 3.05 and boosting the cumulative return of a simulated portfolio by 18.7\%. Ablation studies underscore the essential role of each component, while additional analyses confirm the model's stability, interpretability, and enhanced adaptability. This work pioneers a data-driven, explainable framework for investment decision support.
Science Journals
arXiv:2606.30319v1 Announce Type: new Abstract: Modeling the bidirectional correspondence between external sensory stimuli and internal neural activity has emerged as a critical frontier in neuroscience. However, existing approaches predominantly treat brain encoding and decoding as isolated tasks, relying heavily on unimodal alignment and external priors while overlooking the brain's intrinsic nature as a multimodal integration system. To address these limitations, we propose BrainJanus, the first unified brain model that integrates brain, vision, and language within a single framework. Specifically, we introduce a Unified Brain Tokenizer to quantize continuous neural dynamics into discrete tokens aligned with visual and linguistic representations in a shared Omni space. Building on this, we utilize an All-in-One autoregressive architecture that leverages next-token prediction to enable seamless any-to-any generation, which encompasses image-to-brain and text-to-brain encoding, and brain-to-image and brain-to-text decoding. Extensive experiments demonstrate that BrainJanus achieves superior performance across diverse benchmarks. Furthermore, our framework exhibits zero-shot generalization and preserves interpretable biological topography, highlighting its potential as a general-purpose brain modeling paradigm. The code is available at \href{https://github.com/HaitaoWuTJU/BrainJanus}{GitHub}.
arXiv:2606.29632v1 Announce Type: cross Abstract: Audio-Visual Speech Recognition takes two input modalities, acoustic and visual streams, where visual information from lip movements aids recognition when audio is noisy. Recently, LLM-based AVSR models have emerged as a promising paradigm by connecting pre-trained audio-visual encoders to an LLM, achieving strong results in clean conditions. However, these models are predominantly optimized for clean acoustic conditions, with limited attention to making the LLM backbone robust to noise. No explicit mechanism is employed to produce stable representations under corrupted audio, leading to performance degradation in noisy environments. To address this, we propose VIB-AVSR, which integrates Variational Information Bottleneck layers at targeted positions within the LLM backbone to regularize representations. VIB-AVSR reduces degradation under noisy conditions across multiple SNR levels and noise types, without requiring architectural modifications or additional training data.
arXiv:2606.28994v1 Announce Type: new Abstract: This paper presents new results and breakthrough obtained with the HbHAI techniques (Hash-based Homomorphic Artificial Intelligence) proposed in \cite{filiol0,sepp}. HbHAI is based on a novel class of key-dependent hash functions that naturally preserve most similarity properties, most AI algorithms rely on. It enables to analyse and process data in its cryptographically secure form while using existing native AI algorithms without modification, with unprecedented performances compared to existing homomorphic encryption schemes and most notably compared to the same processing on corresponding plaintext data. Two major results have been obtained further. First we enable to reduce the compression rate up to a factor of 10 thus allowing to process massive datasets while reducing the computation time and the energy footprint in the same order. Second, we show how it is possible to arbitrarily reduce the final validation error of AI-based decision tests by using repetition error-correcting codes.
arXiv:2606.29002v1 Announce Type: new Abstract: Numerical simulation of quantum computing hardware and open quantum systems governed by the Lindblad equation is challenging due to the high dimensionality of the density matrix and the need to preserve fundamental physical properties. In our previous work, we developed an arbitrary-order, low-rank, completely positive and trace preserving (CPTP) method for the Lindblad equation with time-dependent Hamiltonians by nested Picard iteration (NPI). In this work, we develop Gregory NPI schemes, which are CPTP schemes constructed by Gregory-type quadrature on equispaced nodes. The methods, which are of order up to nine, substantially reduce the computational cost compared to our previously proposed NPI schemes with Gaussian quadrature rules, while retaining high-order accuracy and structure preservation. We analyze the stability of the resulting scheme for a physics-based test equation. Numerical experiments verify the convergence of the method and demonstrate the effectiveness of the low-rank approximation. We study the performance of a previously constructed CNOT gate for both closed and open quantum systems.
arXiv:2606.29636v1 Announce Type: cross Abstract: An important task in quantum computing is unitary circuit synthesis compatible with physical hardware constraints. This problem has a natural hybrid structure as local single-qubit gates are continuous variables on the Lie group $SU(2)$ while the entangling circuit structure is discrete and hardware-dependent. In this work, we use generative models to perform quantum circuit synthesis incorporating both the natural $SU(2)$ manifold geometry of quantum gates and hardware constraints that determine the overall circuit structure. Our model comprises two components: a circuit skeleton selector that chooses an entangling circuit and a diffusion model that generates quantum gates on the given circuit template by performing diffusion on the curved manifold $\mathrm{SU(2)} \simeq S^3$ itself. We demonstrate this approach with unitary compilation of physically motivated three-qubit Hamiltonian simulation targets such as the Transverse Field Ising Model and the Heisenberg-XXZ Model and show that Lie group diffusion outperforms comparable baselines. The synthesised circuits can also be customised subject to constraints, which we demonstrate by producing circuits with large and small gate rotation angles for the same target unitary evolution. We also investigate the fidelity-complexity frontier of the synthesised gates to demonstrate that the circuit selector learns to select circuits that balance fidelity with complexity rather than collapsing onto the most expansive entangling template. These results demonstrate that Lie group diffusion provides a natural generative framework for hardware-aware quantum circuit synthesis.
arXiv:2606.29804v1 Announce Type: cross Abstract: The discard ZX-calculus, a diagrammatic language for mixed-state quantum mechanics, is used to give a nonperturbative, categorical proof of the Bloch-Nordsieck cancellation of infrared divergences in QED. Soft photons are treated as an open quantum system: the resolved charged particles and hard photons form the system, while photons below a detector resolution form the environment. The reduced hard channel is a completely positive trace-preserving (CPTP) map, and the soft-photon theorem replaces the full S-matrix by a controlled displacement operator whose Feynman-Vernon influence functional satisfies the equal-history normalization ${\cal F}[J,J]=1 $. In the ZX-calculus, this normalization is a single diagrammatic identity: the doubled displacement diagram collapses to the bare wire under the unitarity, cyclicity, and discard rules. The proof therefore serves as a categorical consistency check on the open-system treatment of soft QED given in a companion paper; it confirms that the physical derivation is logically complete and free of hidden assumptions about the infrared limit. For off-diagonal hard-state elements, the same diagram yields the coherent-state overlap, giving a first-principles account of soft-cloud decoherence. The soft-shell coarse graining is then constructed as a CPTP Schur channel whose infinitesimal limit produces the exact Lindblad generator with jump operators determined by the eikonal emission amplitudes. Finally, a local CPTP-certification pipeline is developed for non-Markovian process tensors, enabling constant-time verification of trace preservation in open quantum simulations. The framework bridges categorical quantum semantics, non-equilibrium field theory, and practical open-system compilation.
arXiv:2606.30043v1 Announce Type: cross Abstract: We study the late-time relaxation of a neutral relativistic viscous fluid in $d+1$ dimensions. In the long-wavelength regime, linearized hydrodynamics predicts that the sound mode at momentum $nk$ decays as $e^{-n^2\omega_I t}$. However, nonlinear analysis gives a decay of $e^{-n\omega_I t}$. We derive a closed asymptotic attractor solution in which the frequency of the $n$-th harmonic locks to $n$ times the complex frequency of the fundamental mode. The amplitude envelopes for energy current $J$ obey a simple cascading relation, $J_n=\alpha_J^{\,n-1}J_1^n$, with $\alpha_J$ fixed by the equation of state, the longitudinal viscosity, and the fundamental wavenumber. For conformal fluids, $\alpha_J=1/(8\eta k)$, in agreement with the holographic result of arXiv:2512.07242. The existence of the attractor shows that, even near equilibrium, field powers are not equivalent to amplitude order.
arXiv:2606.30169v1 Announce Type: cross Abstract: The Wide Field Imager (WFI), one of the two instruments on ESA's next large X-ray observatory NewAthena, is designed for imaging spectroscopy in the 0.2-15 keV range, combining a large field of view with high count-rate capability. Its focal plane is equipped with back-illuminated DEPFET (Depleted p-channel field-effect transistor) sensors that offer high radiation tolerance and provide near Fano-limited energy resolution. Achieving this performance requires an exceptionally low readout noise, with about 3 electrons ENC expected at beginning of life. Consequently, the devices are highly sensitive to radiation-induced changes in noise behavior. In this work, we investigate the impact of both total non-ionizing dose (TNID) and total ionizing dose (TID) on the relevant noise components, including their temperature dependence. A detector module containing a 64x64-pixel sensor from a flight-production wafer was irradiated with 62.4 MeV protons at the MedAustron accelerator facility in Wiener Neustadt to a total dose equivalent to 2.6 $\cdot$ 10$^9$ 10-MeV-protons/cm$^2$. The detector was fully biased and operated throughout the irradiation and subsequent measurements, maintaining the nominal operating temperature of 213 K. To study short-term annealing behavior at low temperature, a second, identical module was exposed to a comparable proton dose within a much shorter timescale by exploiting the available high beam flux. TID effects were investigated separately by irradiating another device with 17.4 keV Mo-K_alpha X-rays to a total dose of 15 Gy. We report the resulting changes in readout noise, dark current, and threshold voltage, and compare them with results from an earlier irradiation campaign using pre-flight sensors. Implications for the instrument's required operating temperature and its expected end-of-life performance are discussed.
arXiv:2606.30177v1 Announce Type: cross Abstract: Symmetries plays a significant role in understanding the conservation laws in Quantum field theories. Here, we attempted a quadratic type dimensionless gauge transformation to achieve the invariance in QFTs. We have shown the extensive study of invariance of complex scalar, Abelian and Non- Abelian theories and established the conservation laws. We included an explicit graphical analysis to invoke the invariance. This is studied in a physical context, where different field configurations correspond to the same physical state. The necessity of the covariant derivative is studied in detail, highlighting how it ensures consistent transformation under local symmetry operations. The meaning of covariance is clarified as the preservation of the form of physical laws under transformations.
arXiv:2606.29102v1 Announce Type: new Abstract: Jointly learning to segment and classify medical images demands cross-task synergy, yet encoder-sharing architectures limit decoder reconstruction to task-private representations, permanently discarding the boundary cues and semantic priors each branch could supply to the other. This work introduces BTI-Net, which establishes bidirectional communication at every decoder level through two parallel pathways via Task Interaction Modules (TIM). Spatial boundary context is gated into the classification branch, while global semantic priors multiplicatively modulate the decoder, with refined features propagating progressively from coarse semantics to fine boundary detail across all four decoder resolutions. Since cross-task interaction is not equally reliable for every input, Uncertainty Proxy Attention (UPA) gates each TIM output per instance and per level using three signals that capture cross-task alignment, scene complexity, and prediction confidence, without external annotations or additional inference passes. Experiments on three medical benchmarks spanning ultrasound, dermoscopy, and brain MRI demonstrate consistent improvements in segmentation IoU and classification accuracy over both encoder-sharing and decoder-interaction baselines. Ablation confirms adaptive gating contributes +2.36 IoU over fixed bidirectional interaction, and classification accuracy improves by up to +2.26 points over the strongest multi-task baseline. UPA's uncertainty proxies serve as reliable single-pass task-failure signals without the overhead of stochastic sampling. Code: https://github.com/C-loud-Nine/BTI-Net_MTL
arXiv:2604.27538v2 Announce Type: replace Abstract: Automated plant recognition plays a crucial role in biodiversity monitoring and conservation, yet current approaches rely heavily on supervised learning, which is limited by the availability of expert-labeled data. Self-supervised learning (SSL) offers a scalable alternative, but existing methods and training protocols are largely designed for coarse-grained visual tasks and may not transfer well to fine-grained domains such as plant species recognition. In this work, we investigate SSL for plant image representation learning. We show that commonly used augmentations in SSL pipelines - such as Gaussian blur, grayscale conversion, and solarization - are detrimental in the context of plant images, as they remove subtle discriminative cues essential for fine-grained recognition. We instead identify alternative transformations, including affine and posterization, that are better suited to this domain. We further demonstrate that training SimDINOv2 on the iNaturalist 2021 Plantae subset yields significantly stronger representations than training on ImageNet-1K, highlighting the importance of domain-specific data for SSL. Our findings are consistent across both ViT-Base and ViT-Large architectures. Moreover, our models achieve competitive performance and sometimes outperform strong supervised baselines Pl@ntCLEF and BioCLIP on downstream plant recognition tasks in few-shot settings. Overall, our results highlight the critical importance of domain-adapted augmentation strategies and dataset selection in self-supervised learning, and provide practical guidelines for building scalable models for biodiversity monitoring.
arXiv:2604.27767v2 Announce Type: replace Abstract: Population protocols are a model of distributed computation in which a collection of indistinguishable finite-state agents interact randomly in pairs to decide a predicate of their initial configuration. The agents decide by achieving a stable consensus on whether the predicate holds or not. It is known that population protocols can decide exactly the predicates expressible in Presburger arithmetic. Recently, Lossin et al. have introduced a notion of protocol robustness against adversarial crash failures. They show that all atomic Presburger predicates can be decided by robust protocols, and ask whether the same holds for every Presburger predicate. We make progress towards settling this question by proving that all predicates expressible in monadic Presburger arithmetic have robust protocols. In addition, we analyze the cost of robustness in terms of state complexity. We study the ratio between the number of states of the smallest robust protocol for a given predicate and the smallest protocol for it. We show that the cost of robustness is at least double exponential in the size of the predicate, and prove that the robust protocols by Lossin et al. for threshold predicates x >= k have optimal state complexity.
arXiv:2506.20771v2 Announce Type: replace Abstract: We propose a latent score-based generative AI framework for learning stochastic, non-local closure models and constitutive laws in nonlinear dynamical systems of computational mechanics. This work addresses a key challenge of modeling complex multiscale dynamical systems without a clear scale separation, for which numerically resolving all scales is prohibitively expensive, e.g., for engineering turbulent flows. While classical closure modeling methods leverage domain knowledge to approximate subgrid-scale phenomena, their deterministic and local assumptions can be too restrictive in regimes lacking a clear scale separation. Recent developments of diffusion-based stochastic models have shown promise in the context of closure modeling, but their prohibitive computational inference cost limits practical applications in many real-world settings. This work addresses this limitation by jointly training convolutional autoencoders with conditional diffusion models in latent space, significantly reducing the dimensionality of the sampling process while preserving essential physical characteristics. Numerical results demonstrate that the joint training approach helps discover a proper latent space that not only guarantees small reconstruction errors but also ensures good performance of the diffusion model in the latent space. When integrated into numerical simulations, the proposed stochastic modeling framework via latent conditional diffusion models achieves significant computational acceleration while maintaining comparable predictive accuracy to standard diffusion models in physical space.
arXiv:2606.29877v1 Announce Type: new Abstract: The broadband gain characteristics of Co:MgF$_2$ were investigated to assess its potential as a gain medium for ultrashort-pulse amplification around the 2 $\mu$m spectral region. Single-pass gain measurements performed using femtosecond seed pulses revealed broadband amplification in the 1.5-2.4 $\mu$m region. The temporal dynamics and spectra of the gain were experimentally characterized and utilized for numerical simulations to assess the feasibility of Co:MgF$_2$ as a broadband gain medium for ultrashort pulses. The results indicate its potential for broadband amplification in future short-wave infrared to mid-infrared ultrafast laser systems, particularly when combined with coherent waveform synthesis or post-compression techniques.
arXiv:2606.29878v1 Announce Type: new Abstract: Predictive models are increasingly embedded in operational decision-making, yet standard explanation methods typically explain forecasts rather than the decisions those forecasts induce. This distinction is important in predict-then-optimize systems: large forecast changes may leave the optimizer's action unchanged, while small changes can alter the selected decision and its realized value. We propose Decision Value Attribution (DVA), a Shapley-based framework for attributing the value of a fixed prediction--optimization pipeline. The framework defines cooperative games whose payoff is the downstream decision value, allowing the players to be information sources, optimization or design parameters, or both. We present three variants: InfoDVA attributes value to features, DesignDVA attributes value to operational configurations, and Decision-Value Interactions (DVI) quantifies how information and design jointly create value. We further distinguish post-DVA, which evaluates decisions using realized outcomes, from pre-DVA, which evaluates decisions under the model's full prediction. This separation turns attribution into a decision-level diagnostic of whether the model's operational beliefs align with realized performance. The resulting attributions are expressed in the units of the operational objective and decompose the gain or loss relative to a baseline. Case studies in electricity storage arbitrage and emergency medical service coverage show that predictive explanations can be poor proxies for operational value, that DVA can guide targeted information-control interventions, and that optimization configurations determine when predictive information is decision-relevant.
arXiv:2606.29167v1 Announce Type: new Abstract: Finding dense correspondences between 3D shapes is a fundamental yet unresolved challenge, especially in real-world environments. These environments present severe challenges, including the lack of time and sufficient samples for training, the prevalence of uncurated extreme-high resolution data with topological distortions, and the need to handle diverse 3D representations. In this paper, we present ATM, a zero-shot framework that requires no correspondence-specific training and robustly addresses these issues at once through an articulate-then-match paradigm. Rather than relying on intrinsic geometric properties, we leverage powerful pretrained vision foundation models and parametric shape priors to estimate parametric shape models from multi-view renderings, and systematically ground these estimations via multi-view geometric consistency. By mapping diverse inputs into a shared canonical parametric space, we inherently establish robust coarse correspondences that bypass topological noise, which are then refined into precise dense mappings via spectral refinement. Operating purely on test-time optimized parametric reconstructions, ATM requires no correspondence training data, is naturally immune to connectivity artifacts, and seamlessly handles diverse 3D modalities, including meshes, point clouds, and 3D Gaussians. Extensive experiments demonstrate that our method achieves strong results on non-isometric benchmarks (average geodesic errors of 2.4-TOPKIDS, 3.8-SMAL), reducing errors by 73% and 37% respectively compared to the baseline URSSM. Furthermore, it exhibits unprecedented robustness on in-the-wild raw scans of up to 200k vertices per shape while maintaining near-constant computation time and consistent superior accuracy.
arXiv:2606.29209v1 Announce Type: new Abstract: We present AnyBody, a unified whole-body humanoid controller driven by an arbitrary subset of body keypoints chosen at deploy time. Prior physics-based trackers either rely on expensive full-body motion capture and error-prone trajectory retargeting, which bottleneck scalable data collection and policy learning, or decompose upper- and lower-body control into separate hierarchical representations, sacrificing the coordinated whole-body motions that loco-manipulation requires. We close this gap by learning a single latent motion representation that any keypoint subset can address. To achieve this, we first train a privileged teacher tracker on a large unstructured motion corpus and distill it online into a deterministic encoder-decoder student whose latent space is a unit sphere. We then train a transformer keypoint encoder that admits any subset of body keypoints through masked self-attention, aligning it to the privileged latent. Additionally, we treat the frozen decoder as a motor prior and specialize downstream tasks with a lightweight residual corrector in the latent space. We demonstrate the effectiveness of AnyBody by tracking large-scale human motions from arbitrary keypoint subsets, free-form control, flexibly teleoperating, and learning downstream behaviors including locomotion, in-air writing, and obstacle-reach.
arXiv:2606.29213v1 Announce Type: new Abstract: OCR systems, ranging from classical engines to specialised OCR vision-language models (OCR-VLMs) and frontier multimodal LLMs, report strong results on English and Chinese document benchmarks, yet their behaviour on Indic scripts is largely uncharacterised. We benchmark ten systems on Devanagari (Hindi): classical EasyOCR; open VLMs (Qwen2.5-VL-3B, Qwen3-VL-8B, olmOCR-7B); specialised OCR-VLMs (DeepSeek-OCR, Unlimited-OCR); and frontier closed models (Gemini 2.5 Flash, Claude Opus 4.7, GPT-5.5, Mistral OCR), across four synthetic degradation conditions and 300 real printed scans. We report four findings. First, on clean rendered text all ten cluster within chrF++ 91 to 98, so synthetic text does not separate them. Second, under degradation the specialised OCR-VLMs are the most fragile: DeepSeek-OCR suffers rare but catastrophic repetition failures (outputs up to 71 the reference length) that wreck its corpus mean even though its median is the best of any system, which is why we report median and catastrophic-rate instead of the mean. Third, on real scans nine of the ten systems collapse (EasyOCR falls from chrF++ 93.6 to 58.3) and the field spreads across a 76-point range, so synthetic renders badly overstate Devanagari quality. Fourth, strong English OCR does not predict Indic OCR: GPT-5.5 drops to chrF++ 58.5 (tying classical EasyOCR) and olmOCR-7B, the model behind olmOCR-Bench, falls to 40.5, while the open Qwen3-VL-8B (75.2, runnable on a single 24 GB GPU) beats GPT-5.5 and approaches Mistral; Gemini and Claude lead at 86.3 and 82.2. An error taxonomy separates surface errors (numerals, punctuation) from structural ones (conjuncts, matras, nukta), and a byte-level (ByT5) post-corrector improves a cheap engine on its own error distribution (chrF++ +1.2 to +1.5) but does not transfer across engines. We release the benchmark, code, and models.
arXiv:2606.29971v1 Announce Type: new Abstract: A growing body of work suggests that the reasoning capabilities of large language models are largely latent in their base form, with post-training primarily amplifying rather than introducing them. However, this evidence comes mainly from mathematical and coding benchmarks, leaving the boundary conditions of that claim largely unexplored, namely which cognitive tasks can be recovered through elicitation and where that recovery fails. To investigate this, we introduce NeuReasoner, a theory-grounded elicitation instrument. At each step, an orchestrator pairs a Neuro Lens, inspired by functional specificity, with a Cognitive Lens, drawn from the Erotetic Theory of Reasoning, and integrates their outputs through internal modularization of a single model, without external tools. We evaluate NeuReasoner on CogBench, a suite of behavioral tasks from cognitive psychology, alongside standard mathematical and coding benchmarks, measuring both its improvement over vanilla inference and its ability to match a model's post-trained thinking mode. At sufficient scale, NeuReasoner matches or exceeds thinking-mode baselines on arithmetic reasoning, code generation, Bayesian reasoning, and reward learning; these gains persist against self-consistency and iterative-refinement baselines matched to NeuReasoner's per-decision call budget. Using NeuReasoner allows us to find clear boundaries: risk-taking and decision making under uncertainty remains hard to recover through elicitation alone, and model scale interacts with elicitation in both directions: widening its advantage on some cognitive signatures while erasing it on others. Overall, through NeuReasoner as a modular, interpretable, theory-grounded elicitation instrument, we empirically map where reasoning elicitation succeeds and fails, beyond the mathematical and coding benchmarks where prior claims have rested.
arXiv:2405.00742v2 Announce Type: replace Abstract: Mitigating cybersecurity risk in electric vehicle (EV) charging demand forecasting plays a crucial role in the safe operation of collective EV chargings, the stability of the power grid, and the cost-effective infrastructure expansion. However, existing methods either suffer from the data privacy issue and the susceptibility to cyberattacks or fail to consider the spatial correlation among different stations. To address these challenges, a federated graph learning approach involving multiple charging stations is proposed to collaboratively train a more generalized deep learning model for demand forecasting while capturing spatial correlations among various stations and enhancing robustness against potential attacks. Firstly, for better model performance, a Graph Neural Network (GNN) model is leveraged to characterize the geographic correlation among different charging stations in a federated manner. Secondly, to ensure robustness and deal with the data heterogeneity in a federated setting, a message passing that utilizes a global attention mechanism to aggregate personalized models for each client is proposed. Thirdly, by concerning cyberattacks, a special credit-based function is designed to mitigate potential threats from malicious clients or unwanted attacks. Extensive experiments on a public EV charging dataset are conducted using various deep learning techniques and federated learning methods to demonstrate the prediction accuracy and robustness of the proposed approach.
arXiv:2606.30019v1 Announce Type: new Abstract: Music-driven dance video generation aims to synthesize expressive human motion that is temporally aligned with music while maintaining high visual fidelity. Despite recent progress, existing methods still face two key limitations: the lack of large-scale, high-quality dance video datasets, and the absence of principled frameworks for integrating music as a complementary conditioning signal into Video Generation Foundation Models. To address these limitations, we introduce CIPE-Dance, a large-scale Internet-sourced dance video dataset with choreography-informed text annotations, constructed via a progressive expert pipeline. To the best of our knowledge, CIPE-Dance is the largest dataset for dance video generation to date, comprising 300k high-quality clips over 400 hours and covering diverse dancers, environments, and dance genres. We further propose OmniDance, a framework-level recipe for integrating music into a TI2V foundation model without sacrificing its original controllability or visual fidelity. Motivated by the complementary roles of text as low-frequency semantics and music as high-frequency temporal dynamics, OmniDance co-designs a depth-aware specialization architecture, an anchored easy-to-hard curriculum learning strategy, and a modality-specialized time-dependent CFG strategy, enabling unified TI2V, MI2V, and MTI2V generation. Extensive experiments on CIPE-Dance demonstrate that OmniDance achieves state-of-the-art performance across all three tasks and exhibits robust multimodal integration capability. Project is available at https://github.com/AMAP-ML/OmniDance.
arXiv:2606.30564v1 Announce Type: new Abstract: Modern vehicles are cyber-physical, networked systems that may contain valuable digital traces for accident reconstruction, crime investigation, warranty analysis, and cybersecurity incident response. However, digital vehicle forensics (DVF) remains less mature than computer, mobile, and cloud forensics because relevant data is distributed across in-vehicle components, mobile devices, manufacturer back ends, third-party services, and physical evidence. This article addresses this gap through a structured synthesis of academic literature, standards, and practitioner-oriented sources. First, we define DVF as the identification, preservation, acquisition, verification, interpretation, and reporting of vehicle-related digital evidence under safety, legal, privacy, and forensic-soundness constraints. Second, we formalize the DVF triage problem as the selection and correlation of evidence sources subject to volatility, accessibility, safety, integrity, and authorization constraints. Third, we explain how eight characteristics were derived from the literature and case material: multiple users, massively networked, cyber-physical system, dependencies between components, functional data, safety implications, accessibility, and limited abstraction. Finally, we add an adversarial perspective and a characteristic-driven triage procedure that helps investigators prioritize evidence sources while documenting assumptions, limitations, and failure cases. The resulting contribution is not an algorithmic performance claim; it is a reproducible conceptual framework for understanding, planning, and communicating DVF investigations.
arXiv:2606.30026v1 Announce Type: new Abstract: Audiovisual arts encompass diverse creative disciplines, including cinema, visual arts, stage performance, and game design, where artistic meaning arises from deliberate combinations of visual, auditory, and narrative elements (e.g., fear amplified through claustrophobic framing, or grief conveyed through silence and lingering close-ups). True artistic understanding extends beyond recognizing what is depicted to reasoning about why it is expressed through particular creative choices. Despite the strong progress of multimodal large language models (MLLMs), this critical aspect of artistic understanding remains underexplored, as existing benchmarks largely measure perceptual recognition while overlooking reasoning about creative intent. To address this gap, we introduce Musebench, a comprehensive benchmark designed to evaluate MLLMs on nuanced artistic understanding. It comprises 4,016 questions spanning cinematic arts, static visual arts, stage performing arts, and game arts, distilled from over 10K candidate video essays that pair professional commentary with visual demonstration. To capture the open-ended nature of artistic analysis at scale, the benchmark combines single-select and variable-option multi-select questions. All questions are generated and refined through a four-phase iterative pipeline combining shortcut filtering, adversarial distractors, and expert validation. Comprehensive zero-shot evaluation of 28 state-of-the-art MLLMs reveals that even the best-performing model achieves only 48.29% accuracy, substantially below human expert performance of 87.18%, exposing a significant gap in current models' creative domain expertise.
arXiv:2606.30595v1 Announce Type: new Abstract: Semantic communication (SemCom) aims to preserve semantic meaning and task-oriented information beyond conventional message recovery over wireless channels. The adoption of SemCom in shared-access wireless networks introduces new vulnerabilities for multi-user semantic inference. This paper considers a SemCom system for two transmitters communicating with a common receiver over a multiple access channel. Each transmitter maps source information into latent semantic representations, while the receiver jointly reconstructs and classifies the semantic information for both transmitters. A selective over-the-air backdoor (Trojan) attack is presented in which an adversary transmits a low-power trigger waveform over the air and injects it into the shared received signal during training. By transmitting the trigger again during testing, this stealthy, low-power attack selectively manipulates the semantic inference for one transmitter while minimally affecting the inference of the other transmitter. To mitigate this vulnerability, a trigger-aware defense mechanism is developed to preserve correct semantic labels under trigger-contaminated wireless observations. The results demonstrate both the vulnerability of shared-access SemCom systems to selective over-the-air backdoor attacks and the effectiveness of trigger-aware robust training for semantic protection.