arXiv:2605.17342v1 Announce Type: new Abstract: Standard RLHF relies on transitive scalar rewards, failing to capture the cyclic nature of human preferences. While some approaches like the General Preference Model (GPM) address this, we identify a theoretical limitation: their implicit formulation entangles hierarchy with cyclicity, failing to guarantee dominant solutions. To address this, we propose the Hybrid Reward-Cyclic (HRC) model, which utilizes game-theoretic decomposition to explicitly disentangle preferences into orthogonal transitive (scalar) and cyclic (vector) components. Complementing this, we introduce Dynamic Self-Play Preference Optimization (DSPPO), which treats alignment as a time-varying game to progressively guide the policy toward the Nash equilibrium. Synthetic data experiments further validate HRC's structural superiority in mixed transitive--cyclic settings, where HRC converges faster and achieves higher accuracy than GPM. Experiments on RewardBench 2 demonstrate that HRC consistently improves over both BT and GPM baselines (e.g., +1.23% on Gemma-2B-it). In particular, its superior performance in the Ties domain empirically validates the model's robustness in handling complex, non-strict preferences. Extensive downstream evaluations on AlpacaEval 2.0, Arena-Hard-v0.1, and MT-Bench confirm the efficacy of our framework. Notably, when using Gemma-2B-it as the base preference model, HRC+DSPPO achieves a peak length-controlled win-rate of 44.75% on AlpacaEval 2.0 and 46.8% on Arena-Hard-v0.1, significantly outperforming SPPO baselines trained with BT or GPM. Our code is publicly available at https://github.com/lab-klc/Hybrid-Reward-Cyclic.
Science Journals
arXiv:2605.18078v1 Announce Type: new Abstract: Multi-agent policy-gradient methods have been shown to converge locally near stable Nash equilibria. Local convergence, however, does not determine which equilibrium is reached. We study this question through basin-entry probability with respect to a target set of equilibria selected by an external criterion, such as payoff dominance. For finite-unroll Meta-MAPG, we show that the update decomposes into ordinary policy gradient plus own-learning and peer-learning corrections, with controlled sampling noise and finite-unroll bias. We identify the peer-learning correction as the main equilibrium-selection mechanism: under a local alignment condition, the probability of entering the certified attraction region of the target stable-Nash set increases, relative to ordinary policy gradient. Because persistent correction may shift zero-update points of the original game, annealing the correction after entering the basin recovers ordinary policy-gradient dynamics and inherits local stable-Nash convergence guarantees. Experiments in Stag Hunt, iterated Prisoner's Dilemma, and preliminary neural-policy coordination environments support this basin-entry view, showing increased entry into cooperative basins under peer-aware updates.
arXiv:2605.10811v2 Announce Type: replace-cross Abstract: This paper develops a joint spectral radius (JSR) framework for analyzing rank-one deflated Q-value iteration (Q-VI) in discounted Markov decision process control. Focusing on an all-ones residual correction, we interpret the resulting algorithm through the geometry of switching systems and, to the best of our knowledge, give the first JSR-based convergence analysis of deflated Q-VI for policy optimization problems. Our analysis reveals that the standard Q-VI switching system model has JSR exactly the discount factor $\gamma\in (0,1)$, since all admissible subsystems share the all-ones vector as an invariant direction. By passing to the quotient space that removes this direction, we obtain a projected switching system model whose JSR governs the relevant error dynamics and may be strictly smaller than $\gamma$. Therefore, the deflated Q-VI admits a potentially sharper convergence-rate characterization than the ambient-space $\gamma$-bound. Finally, we prove that the correction is equivalent to a scalar recentering of standard Q-VI. Hence, the projected trajectory, and therefore the greedy-policy sequence, is unchanged relative to standard Q-VI initialized from the same point. The benefit of deflation is not a change in the induced decision-making problem, but a more precise JSR-based description of the convergence geometry after the redundant all-ones component is removed.
arXiv:2605.01127v2 Announce Type: replace-cross Abstract: Partitioning transportation networks into balanced and spatially coherent traffic zones is a fundamental yet computationally challenging task in intelligent transportation systems. The resulting optimization problem exhibits dense interactions among decision variables and can be formulated as a Quadratic Unconstrained Binary Optimization (QUBO) model. While quantum optimization naturally aligns with such quadratic energy representations, current noisy intermediate-scale quantum hardware imposes limitations on problem size, connectivity, and circuit reliability. This paper proposes an impact-driven hybrid quantum--classical optimization framework for traffic zone partitioning that bridges transportation-scale optimization models and practical gate-based quantum processors. Instead of static geographic decomposition, the method estimates the energy impact of decision variables and selectively assigns quantum computation to influential subproblems while a classical coordination loop maintains global feasibility. The framework is implemented using the Iskay optimizer and evaluated on the IBM Quantum System One backend. Experiments compare direct quantum optimization, classical iterative SubQUBO refinement, and the proposed hybrid approach. Results show that impact-guided decomposition improves convergence behavior and produces more coherent spatial partitions relative to classical refinement, while remaining consistent with hardware constraints. Although the hybrid method does not outperform the best direct quantum solution, it demonstrates a practical pathway toward scalable hybrid optimization for transportation applications under current quantum hardware conditions.
arXiv:2605.17907v1 Announce Type: new Abstract: By sharing intermediate features, collaborative perception extends each agent's sensing beyond standalone limits, but real-world feature modality heterogeneity remains a key barrier to effective fusion. Most existing methods, including direct adaption and protocol-based transformation, typically rely on training adapters for newly emerging feature modalities and often require additional retraining or fine-tuning. Such repeated training is costly and is often infeasible across manufacturers due to model and data privacy constraints, limiting real-world scalability. To address this issue, we propose UniTrans, a universal any-to-any feature modality translation model that instantiates translators on the fly for arbitrary modalities. UniTrans pretrains a bank of translator expert parameters and learns their combination coefficients as a function of source-to-target modality mapping. The mapping is measured in a modality-intrinsic latent space, where an intrinsic encoder extracts modality-specific yet scene-invariant codes from single-frame intermediate features, enabling UniTrans to instantiate translators in a zero-shot manner. Experiments on OPV2V-H and DAIR-V2X demonstrate that UniTrans consistently outperforms state-of-the-art methods in both simulated and real-world settings, enabling efficient any-to-any translation through a universal model. The code is available at https://github.com/CheeryLeeyy/UniTrans.
arXiv:2605.17904v1 Announce Type: new Abstract: Few-Shot Medical Image Segmentation (FSMIS) aims to delineate novel anatomical targets from one or a few annotated support images, addressing the annotation scarcity in medical imaging. Notwithstanding recent advancements, current prototype-based methods are bottlenecked by two coupled limitations: 1) cue entanglement, where a single spatial-domain prototype is forced to summarise organ silhouette, parenchymal texture and boundary appearance simultaneously, so any support-query mismatch on one cue propagates indiscriminately to the others; and 2) topology-blind matching, where cosine similarity measures distance in the ambient Euclidean space and ignores the connectivity of the underlying feature manifold, causing fragmented activations inside low-contrast organs and leakage into neighbouring tissues. To this end, we propose Spectral-Geodesic Prototype Network (SGP-Net), built around a Spectral-Geodesic Prototype Module with two coupled components. A Spectral Prototype Bank (SPB) decomposes support and query features into low-, mid- and high-frequency bands via learnable radial Fourier filters, yielding three disentangled prototypes per class that separately encode shape, texture and boundary cues. A Geodesic Matcher (GM) then replaces cosine similarity with a differentiable heat-diffusion approximation of geodesic distance, propagating matching signals along a feature affinity graph so that on-manifold pixels accumulate consistent responses while off-manifold look-alikes are suppressed. Experiments on three public FSMIS benchmarks demonstrate that SGP-Net achieves competitive performance against recent state-of-the-art methods.
arXiv:2605.17903v1 Announce Type: new Abstract: We automatically generate feedback causal fuzzy cognitive maps (FCMs) from text by teaching large-language-model agents to break the text into overlapping chunks of text. Convex mixing of these chunk FCMs gives a representative cyclic FCM knowledge graph. The text chunks can have different levels of overlap. The chunk FCMs still mix to form a new FCM causal knowledge graph. The mixing technique scales because it uses light computation with sparse causal chunk matrices. The mixing structure allows an operator-level type of Bayesian inference that produces "de-chunked" or posterior-like FCMs from the mixed FCM. These de-chunked FCMs are useful in their own right and allow further iterations of Bayesian updating. We demonstrate these mixing techniques on the essay text of Allison's "Thucydides Trap" model of conflict between a dominant power such as the United States and a rising power such as China. The FCM dynamical systems predict outcomes as they equilibrate to fixed-point or limit-cycle attractors. Seven out of 8 FCM knowledge graphs predicted a type of war when we stimulated them by turning on and keeping on the concept node that stands for the rising power's ambition and entitlement. Gemini 3.1 LLMs served as the chunking AI agents.
arXiv:2605.18508v1 Announce Type: new Abstract: Programmatic reinforcement learning (PRL) offers an interpretable alternative to deep reinforcement learning by representing policies as human-readable and -editable programs. While gradient-based methods have been developed to optimize continuous relaxations of programs, they face a significant performance drop when converting the continuous relaxations back into discrete programs. Post-hoc discretization can discard optimized branches and parameters in a program, which results in a collapse of policy expressivity and lowered task performance, leading in turn to a need for additional fine-tuning. To overcome these limitations, we propose Differentiable Discrete Programmatic Reinforcement Learning (DiPRL), a method that learns programmatic policies that become nearly discrete during training, avoiding a separate post-hoc fine-tuning stage. We first analyze the inherent risks of performance drop introduced by post-hoc discretization of gradient-based methods. Then, we introduce programmatic architecture entropy regularization, which enables smooth, differentiable training that encourages convergence toward a discrete program. DiPRL maintains the efficiency of gradient-based optimization while mitigating the risks of post-hoc discretization. Our experiments across multiple discrete and continuous RL tasks demonstrate that DiPRL can achieve strong performance via interpretable programmatic policies.
arXiv:2603.20904v5 Announce Type: replace-cross Abstract: Spectral gaps, Kramers escape rates, and position-dependent relaxation timescales are dynamical invariants encoded in the infinitesimal generator $\Lop$ of a stochastic flow. We show that weak projection of the governing It\^{o} SDE onto temporal test functions produces an endogeneity bias of order $O(T\,\dt^{3/2})$ that grows with the observation window and cannot be eliminated by additional data. Projecting instead onto spatial Gaussian kernels removes the bias exactly: $\mathcal{F}_{t_n}$-measurability and the tower property guarantee unbiased regression rows at every step. The resulting framework jointly identifies the drift $b(x)$ and diffusion $a(x)$ from a single sparse regression, producing an explicit symbolic enerator amenable to spectral analysis. Validation on three benchmark systems yields coefficient errors below 5%, stationary-density total-variation distances below 0.01, and autocorrelation functions that faithfully reproduce true relaxation timescales.
arXiv:2509.14462v2 Announce Type: replace-cross Abstract: The Schelling model is a prototype for agent-based modeling in social systems. We produce a comprehensive analysis of Schelling model rule variants by classifying the space of macroscopic outcomes using phase diagrams. Among 54 rule variants, only 3 phase diagram classes are found, characterized by the number of phase transitions. This classification scheme is found to be robust to the use of sociological and percolation-inspired measures of segregation. The statistical and dynamic drivers of these transitions are elucidated by analyzing the roles of vision, movement criteria, vacancies, the initial state, and rivalry. Schelling's original step function dictating satisfaction is found to be pathological at high thresholds, producing coordination failures as satisfactory sites become increasingly rare. This comprehensive classification gives new insight into the drivers of transitions in the Schelling model and creates a basis for studying more complex Schelling-like models.
arXiv:2509.10153v2 Announce Type: replace-cross Abstract: Over the past decade, autophoretic colloids have emerged as a prototypical system for studying self-propelled motion at microscopic scales, with promising applications in microfluidics, micromachinery, and therapeutics. Their motion in a viscous fluid hinges on their ability to induce surface slip flows that are spatially asymmetric from self-generated solute gradients. Here, we demonstrate theoretically that a straight elastic filament with homogeneous surface chemical properties -- which is otherwise immotile -- can spontaneously achieve self-propulsion by experiencing a buckling instability that serves as the symmetry-breaking mechanism. Using efficient numerical simulations, we characterize the nonlinear dynamics of the elastic filament and show that, over time, it attains distinct swimming modes such as a steadily translating "U" shape and a metastable rotating "S" shape when semiflexible, and an oscillatory state when highly flexible. Our findings provide physical insight into future experiments and the design of reconfigurable synthetic active colloids.
arXiv:2506.21499v2 Announce Type: replace-cross Abstract: Ultrasound Coherent Plane-Wave Compounding (CPWC) enhances image contrast by combining echoes from multiple steered transmissions. While increasing the number of steering angles generally improves image quality, it significantly reduces frame rate and may introduce blurring artifacts in fast-moving targets. In addition, compounded images remain susceptible to noise, particularly when acquired using a limited number of transmissions. In this work, we propose a lightweight physics-aware zero-shot denoising framework for low-angle CPWC ultrasound imaging that improves image quality without requiring external training datasets or clean reference images. The proposed approach partitions the available steering angles into two disjoint subsets, each used to reconstruct compounded images with different angle-dependent artifacts and noise characteristics. These reconstructed images are then used as pseudo-pairs within a self-supervised residual learning framework to train a lightweight convolutional neural network directly on the test sample. Because the underlying tissue structures remain consistent across the subsets while the incoherent artifacts vary with steering angle selection, the proposed physics-aware pairing strategy enables the network to distinguish anatomical information from inconsistent noise and artifacts. Unlike supervised approaches, the proposed method does not require domain-specific fine-tuning or paired datasets, making it adaptable across different anatomical regions and acquisition settings. Furthermore, the proposed framework employs an efficient architecture composed of only two convolutional layers, enabling fast and computationally inexpensive training.
arXiv:2605.18004v1 Announce Type: new Abstract: Randomized linear algebra (RLA) algorithms are a modern class of numerical linear algebra techniques that play an essential role in scientific computing and machine learning, with broad and growing adoption. However, their discovery remains mostly a manual process that requires deep expert knowledge and inspiration. While Reinforcement Learning (RL) offers a pathway to automation, standard approaches struggle with sparse reward landscapes and vast search spaces inherent to high-performing RLA algorithms. In this paper, we present RL4RLA, a general RL framework that automates the discovery of interpretable, symbolic RLA algorithms. Unlike black-box approaches, our method builds explicit algorithms from basic linear algebra primitives, ensuring verifiable and implementable representations. To enable efficient discovery, we introduce: (1) a numerical curriculum that progressively increments problem difficulty to encode inductive bias specific to the RLA domain; (2) Monte Carlo Graph Search, which optimizes exploration by identifying and merging equivalent partial algorithms. We demonstrate that RL4RLA rediscovers state-of-the-art methods, including sketch-and-precondition solvers, Randomized Kaczmarz, and Newton Sketch, and can be targeted to produce algorithms optimized for specific trade-offs between accuracy, speed, and stability. Code is available at https://github.com/Tim-Xiong/RL4RLA.
arXiv:2502.02463v3 Announce Type: replace-cross Abstract: While Bayesian inference provides a principled framework for reasoning under uncertainty, its widespread adoption is limited by the intractability of exact posterior computation, necessitating the use of approximate inference. However, existing methods are often computationally expensive, or demand costly retraining when priors change, limiting their utility, particularly in sequential inference problems such as real-time sensor fusion. To address these challenges, we introduce the Distribution Transformer -- a novel architecture that can learn arbitrary distribution-to-distribution mappings. Our method can be trained to map a prior to the corresponding posterior, conditioned on some dataset -- thus performing approximate Bayesian inference. Our novel architecture represents a prior distribution as a (universally-approximating) Gaussian Mixture Model (GMM), and transforms it into a GMM representation of the posterior. The components of the GMM attend to each other via self-attention, and to the datapoints via cross-attention. We demonstrate that Distribution Transformers both maintain flexibility to vary the prior, and significantly reduces computation times-from minutes to milliseconds-while achieving log-likelihood performance on par with or superior to existing approximate inference methods across tasks such as sequential inference, quantum system parameter inference, and Gaussian Process predictive posterior inference with hyperpriors.
arXiv:2310.20389v2 Announce Type: replace-cross Abstract: Diffusion Tensor Cardiac Magnetic Resonance (DT-CMR) is the only in vivo method to non-invasively examine the microstructure of the human heart. Current research in DT-CMR aims to improve the understanding of how the cardiac microstructure relates to the macroscopic function of the healthy heart as well as how microstructural dysfunction contributes to disease. To get the final DT-CMR metrics, we need to acquire diffusion weighted images of at least 6 directions. However, due to DWI's low signal-to-noise ratio, the standard voxel size is quite big on the scale for microstructures. In this study, we explored the potential of deep-learning-based methods in improving the image quality volumetrically (x4 in all dimensions). This study proposed a novel framework to enable volumetric super-resolution, with an additional model input of high-resolution b0 DWI. We demonstrated that the additional input could offer higher super-resolved image quality. Going beyond, the model is also able to super-resolve DWIs of unseen b-values, proving the model framework's generalizability for cardiac DWI superresolution. In conclusion, we would then recommend giving the model a high-resolution reference image as an additional input to the low-resolution image for training and inference to guide all super-resolution frameworks for parametric imaging where a reference image is available.
arXiv:2605.17406v1 Announce Type: new Abstract: Side-channel attacks exploit unintended information leakage from system behavior and continue to pose serious privacy risks in modern platforms. Despite extensive prior work, side-channel analysis remains largely manual and fragmented, typically assuming predefined target events and a fixed set of known channels. As systems and applications grow increasingly complex, several fundamental questions remain unanswered: which user or system events are sensitive in practice, how side channels associated with these events can be systematically discovered without exhaustive manual effort, and how their leakage can be analyzed at scale without prohibitive data collection and model training costs. To address these questions, we present SCAgent, an automated framework for side-channel risk analysis. To identify sensitive targets beyond manually specified events, SCAgent performs agent-driven system exploration guided by LLM-based semantic reasoning. To systematically discover side channels while mitigating the risk of LLM hallucination, it reasons over system documentation and incorporates explicit verification to enforce semantic consistency, threat-model feasibility, and per-channel usability. To enable scalable analysis under limited data, SCAgent adopts a few-shot learning paradigm based on foundation models, avoiding the need to train bespoke models for each channel--event pair. To bridge the gap between raw time-series side-channel signals and tabular foundation models, SCAgent further introduces a time-shift--robust feature extraction layer that enables effective downstream analysis. We instantiate SCAgent on iOS as a first step, focusing on OS-level side channels observable by unprivileged applications. Our evaluation spans standard benchmarks such as foreground app and website fingerprinting, as well as newly identified sensitive in-app activities in popular applications.
arXiv:2512.07245v2 Announce Type: replace Abstract: Textual explanations make image classifier decisions transparent by describing the prediction rationale in natural language. Large vision-language models can generate captions but are designed for general visual understanding, not classifier-specific reasoning. Existing zero-shot explanation methods align global image features with language, producing descriptions of what is visible rather than what drives the prediction. We propose TEXTER, which overcomes this limitation by isolating decision-critical features before alignment. TEXTER identifies the neurons contributing to the prediction and emphasizes the features encoded in those neurons -- i.e., the decision-critical features. It then maps these emphasized features into the CLIP feature space to retrieve textual explanations that reflect the model's reasoning. A sparse autoencoder further improves interpretability, particularly for Transformer architectures. Extensive experiments show that TEXTER provides more faithful and interpretable explanations than existing methods. The code is available at \url{https://github.com/tttt-0814/TEXTER}.
arXiv:2512.06238v2 Announce Type: replace Abstract: Directed information and its causally conditioned variations are often used to measure causal influences between random processes. In practice, these quantities must be measured from data. Non-asymptotic error bounds for these estimates are known for sequences over finite alphabets, but less is known for real-valued data. This paper examines the case in which the data are sequences of Gaussian vectors. We provide an explicit formula for causally conditioned directed information rate based on optimal prediction and define an estimator based on this formula. We show that our estimator gives an error of order $O\left(N^{-1/2}\log(N)\right)$ with high probability, where $N$ is the total sample size.
arXiv:2512.06194v2 Announce Type: replace Abstract: In the process industries, MPC (Model Predictive Control) is typically implemented as a two-stage controller with a Linear Program (LP) steady-state optimizer that generates economically optimal targets for the MPC algorithm. Abnormal behaviors in industrial LP optimizers are often difficult to rationalize, especially when a large number of manipulated variables (MVs) and controlled variables (CVs) are involved. We introduce a novel, post-hoc LP explainability method by recasting the role of shadow prices in the LP solution as an attribution mechanism for MV-CV relationships. The core idea is that the shadow price of a constrained CV is not just an intrinsic property of the LP solution, but can be split into contributions from individual unconstrained MVs and resolved into one-to-one MV-CV pairings using a linear sum assignment algorithm. The proposed MV-CV pairing framework serves as a practical explainability tool for online LP-MPC systems, enabling practitioners to diagnose suboptimal constraints and verify alignment of the controller's behavior with its original design.
arXiv:2605.18477v1 Announce Type: new Abstract: Tropical cyclone (TC) inner-core surface wind vectors underpin intensity forecasting and storm-surge prediction, yet direct observations remain scarce: routine aircraft reconnaissance is confined to the North Atlantic and Eastern Pacific and, even there, samples each storm only episodically. CYGNSS is the only satellite that penetrates heavy precipitation to measure inner-core surface winds, but delivers directionless scalar wind speeds and is assimilated by no operational analysis system. Here we show that the full 10 m vector wind field inside the TC inner core can be reconstructed globally at 1.5 km resolution from sparse CYGNSS scalar observations alone, by generalising score-based diffusion assimilation to a nonlinear observation operator and injecting three TC boundary-layer constraints; we further propose a CYGNSS-intrinsic Observation Coverage Sufficiency (OCS) criterion that flags reliable reconstructions without external references. Applied to 4,955 snapshots of 249 TCs across all six active basins (2020-2022), the reconstructions reduce systematic Vmax bias against IBTrACS best-track by ~79% and ~75% relative to ERA5 and CCMP. Independent Tail Doppler Radar validation (47 storms) yields a wind speed RMSE of 6.9 m/s on the 23 coverage-sufficient cases (7.5 m/s overall); ablation across the full sample shows that the physical constraints cut wind-direction RMSE by 60% without degrading speed accuracy. The framework further supports joint assimilation of heterogeneous observations: adding only 11 dropsonde vectors to CYGNSS for TC FIONA (2022) reduces the cross-eye profile RMSE by 42%, outlining a practical pathway for fusing CYGNSS with SFMR, SAR and scatterometer data. The result is a globally consistent, observation-anchored kilometre-scale description of TC inner-core vector winds across all six active basins, including those without routine aircraft reconnaissance.
arXiv:2605.17528v1 Announce Type: new Abstract: Large Language Models (LLMs) generate realistic synthetic data but offer no guarantee that their outputs respect the causal mechanisms governing the target domain. We introduce CausalSynth, a framework that decouples causal structure generation from semantic realization, yielding synthetic data that is both causally valid and linguistically rich. The framework operates in three phases. First, a Structural Causal Model (SCM) - a tuple of structural equations defined over a directed acyclic graph (DAG) generates causal skeletons, i.e., variable assignments that satisfy the Global Markov Property of the governing DAG, via ancestral sampling. Second, an LLM acts as a constrained \emph{realizer}, a conditional translator that maps each skeleton to a high-dimensional observation such as a clinical note or a transaction log. Third, an Iterative Consistency Verification module detects structural violations through deterministic extraction and feeds targeted corrections back to the LLM, forming a closed-loop refinement process. We identify the Semantic Backdoor problem the systematic tendency of LLMs to override imposed causal facts with pre-training priors -- and prove that our iterative mechanism reduces the resulting selection bias relative to standard rejection sampling. On three causal benchmarks (ASIA, ALARM, and MIMIC-Struct), CausalSynth preserved conditional independencies with false-positive rates near the nominal $\alpha=0.05$ level and achieved realizability rates above 96% with 70B-parameter LLM backbones. The framework additionally supports principled interventional and counterfactual generation through noise retention and graph mutilation.
arXiv:2605.18467v1 Announce Type: new Abstract: Recent diffusion-based methods have achieved impressive progress in video content manipulation. However, they typically ignore the accompanying audio, leaving the audio disjointed from the edited results. In this paper, we propose InstructAV2AV, the first end-to-end framework for instruction-guided audio-video joint editing. We first develop a scalable data synthesis pipeline and construct InsAVE-80K, the first large-scale audio-video editing dataset with high-quality source-to-target pairs. With this data foundation, we adapt an audio-video generation backbone to leverage its robust priors. We concatenate the audio-video input with noisy latent codes to anchor the source context, propose the source-instruction gated attention to improve instruction following and content preservation, and introduce a two-stage training strategy to effectively transfer these pre-trained priors. Extensive experiments demonstrate that InstructAV2AV outperforms state-of-the-art methods across 11 metrics spanning three aspects on two evaluation sets, highlighting its potential for controllable content creation. Project page: https://hjzheng.net/projects/InstructAV2AV/.
arXiv:2605.18466v1 Announce Type: new Abstract: Segmenting vocal tract articulators in real-time MRI (rtMRI) is a challenging dynamic image segmentation problem characterized by low contrast, rapid motion, and limited spatial resolution. However, while rtMRI acquisitions may provide synchronized acoustic signals, existing methods discard this information, and the few multimodal approaches that incorporate audio cannot be deployed when audio is unavailable. We propose a three-stage framework that leverages acoustic and phonological supervision during training while requiring only the rtMRI image at inference: phonological representations are converted into spatial bounding-box priors for articulator localization, visual and acoustic encoders are aligned via dual-level cross-modal contrastive pretraining, and the learned representations are fused through a cross-attention decoder, effectively transferring multimodal knowledge into a single-modality inference pipeline. Evaluated on 75-Speaker~Annot-16 and USC-TIMIT datasets, our method outperforms existing unimodal and multimodal methods, demonstrating that multimodal supervision provides transferable benefits for precise and clinically deployable vocal tract segmentation.
arXiv:2501.12709v2 Announce Type: replace-cross Abstract: Federated learning enables decentralized, privacy-preserving training but remains vulnerable to privacy leakage in the quantum era. Quantum federated learning (QFL) offers a promising path towards enhanced security and efficiency. However, a practical and experimentally validated QFL protocol utilizing near-term quantum techniques to address data privacy has been lacking. Here we present QuNetQFL, a QFL protocol implemented on quantum networks, in which local model updates are masked with distributed quantum secret keys, offering information-theoretic security during aggregation. We experimentally validate the protocol on a four-client quantum network and benchmark its performance using the generated keys on quantum and real-world datasets. Adding a single quantum client significantly improves global accuracy for classifying multipartite entangled and non-stabilizer quantum datasets. For language tasks, we apply QuNetQFL to sentiment analysis by federated fine-tuning of a hybrid classical-quantum language model, achieving comparable and robust performance in simulation and on real quantum hardware. Large-scale simulations further demonstrate scalability to 200 clients for handwritten-digit recognition, with rapid convergence and a $75\%$ reduction in communication cost via model compression. Our work establishes a practical and scalable route to quantum-secure federated learning for the emerging quantum internet.
arXiv:2605.18423v1 Announce Type: new Abstract: As autonomous systems grow more advanced, objective metrics to evaluate their ethical and legal compliance are critical for informing end users of their limitations and ensuring accountability of those who misuse them. Current ethical embodied AI frameworks remain mostly qualitative, focusing on system design (through safety guardrails or targeted red teaming), and the realized guardrails often directly disallow unsafe behavior without providing the user with an override or interpretable reason. Instead, there is a need for computable metrics through rigorous testing that allow a user to determine the applicability of the system to the task. To address this gap, we introduce the Reference Ethical Benchmark for Autonomy Readiness (REBAR), a quantitative test and evaluation framework for autonomous systems. REBAR maps operating metrics into a computable Autonomy Readiness Level (ARL) rubric that can quantify ethical performance. Key innovations of the framework include a neuro-symbolic Large Language Model (LLM) approach to calculate and explain the ethical difficulty of scenarios, LLM-driven at-scale generation of test instances, and a versatile, photorealistic simulation environment. By evaluating white-box autonomy solutions through this rigorous testing pipeline, REBAR delivers an objective and repeatable benchmark score, bridging the gap between abstract principles and verifiable, accountable autonomy.