arXiv:2604.15231v2 Announce Type: replace
Abstract: Vision-language models (VLM) have markedly advanced AI-driven interpretation and reporting of complex medical imaging, such as computed tomography (CT). Yet, existing methods largely relegate clinicians to passive observers of final outputs, offering no interpretable reasoning trace for them to inspect, validate, or refine. To address this, we introduce RadAgent, a tool-using AI agent that generates CT reports through a stepwise and interpretable process. Each resulting report is accompanied by a fully inspectable trace of intermediate decisions and tool interactions, allowing clinicians to examine how the reported findings are derived. In our experiments, we observe that RadAgent improves chest CT report generation over its 3D VLM counterpart, CT-Chat, across three dimensions. Clinical accuracy improves by 5.8 points (35.4% relative) in macro-F1 and 5.1 points (18.6% relative) in micro-F1. Robustness under adversarial conditions improves by 24.7 points (41.9% relative). Furthermore, RadAgent achieves 37.0% in faithfulness, a new capability entirely absent in its 3D VLM counterpart. By structuring the interpretation of chest CT as an explicit, tool-augmented and iterative reasoning trace, RadAgent brings us closer toward transparent and reliable AI for radiology.
Science Journals
arXiv:2603.29400v2 Announce Type: replace
Abstract: State-of-the-art optical wireless positioning (OWP) commonly reaches centimeter-level accuracy by depending on dense multi-light-emitting diodes (LED) infrastructures, photodiode (PD) arrays, or image-sensor receivers, incurring hardware complexity and deployment cost. This paper introduces a single beam-steered LED, single-PD OWP architecture that achieves three-dimensional (3D) localization without receiver rotation, cameras, or PD arrays; the core idea is to steer the transmitter through K known orientations and exploit the resulting received-signal-strength variations at the PD to estimate LED-to-PD direction and distance. We derive a composite Cramer-Rao lower bound and position-error bound (PEB) for the joint observation model, and cast the steering-pattern design as a genetic algorithm that minimizes the PEB over a 3D testbed. We develop both model-based a constrained nonlinear estimator and closed-form direction estimators: a statistically efficient generalized least squares solution, and a lightweight weighted least squares approximation. Simulations demonstrate centimeter-level accuracy for 3D OWP with a single beam-steered LED and a single PD.
arXiv:2604.17625v2 Announce Type: replace
Abstract: This paper introduces a novel methodology for generating fast and memory-efficient video continuations. Our method, dubbed FlowC2S, fine-tunes a pre-trained text-to-video flow model to learn a vector field between the current and succeeding video chunks. Two design choices are key. First, we introduce inherent optimal couplings, utilizing temporally adjacent video chunks during training as a practical proxy for true optimal couplings, resulting in straighter flows. Second, we incorporate target inversion, injecting the inverted latent of the target chunk into the input representation to strengthen correspondences and improve visual fidelity. By flowing directly from current to succeeding frames, instead of the common combination of current frames with noise to generate a video continuation, we reduce the dimensionality of the model input by a factor of two. The proposed method, fine-tuned from LTXV and Wan, surpasses the state-of-the-art scores across quantitative evaluations with FID and FVD, with as few as five neural function evaluations.
arXiv:2604.00142v2 Announce Type: replace
Abstract: We conducted a between-subjects experiment (N=92) comparing three conditions in a calculus learning environment: no self-explanation (control), menu-based self-explanation, and open-ended self-explanation with LLM-generated feedback. All conditions showed positive learning gains within a fixed 60-minute practice session, with no significant between-condition differences in post-test performance. On transfer questions, the open-ended condition produced significantly higher-quality explanations than control on "Not Enough Information" (NEI) problems ($\beta$=+11.9 percentage points, $p$=.030), though the corresponding NEI multiple-choice accuracy advantage was not significant ($p$=.183). Moreover, across all post-test open-ended explanations, the open-ended condition showed a marginally significant advantage ($\beta$=+7.3%, $p$=.057). These findings suggest that LLM-supported open-ended self-explanation can improve explanation quality on NEI transfer problems, with weaker evidence across broader transfer explanation measures. Notably, these effects emerged even though learners in the open-ended condition completed substantially fewer practice problems within the same practice time.
arXiv:2604.00157v2 Announce Type: replace
Abstract: We propose an algorithm to reconstruct explicit polygonal meshes from discretely sampled Signed Distance Function (SDF) data, which is especially effective at recovering sharp features. Building on the traditional Dual Contouring of Hermite Data method, we design and solve a quadratic optimization problem to decide the optimal placement of the mesh's vertices within each cell of a regular grid. Critically, this optimization relies solely on discretely sampled SDF data, without requiring arbitrary access to the function, gradient information, or training on large-scale datasets. Our method sets a new state of the art in surface reconstruction from SDFs at medium and high resolutions, and opens the door for applications in 3D modeling and design.
Polaris: Scaling Up Instruction-Guided Image Generation Towards Millions of Personalized Style Needs
arXiv:2606.01858v1 Announce Type: new
Abstract: Users increasingly expect image generation models to quickly adapt to highly diverse and personalized requirements, such as producing images with distinctive styles or characteristics. Traditional approaches rely on fine-tuning, which is costly and difficult to scale. To cope with these limitations, the community has accumulated a growing library of fine-tuned modules and adapters, where each component targets specific generation needs and collectively serves as a foundation for handling new demands. This naturally raises a question: instead of repeatedly training new models, can we systematically exploit this expanding ecosystem to better fulfill user instructions? To this end, we present Polaris, an intelligent retrieval framework that automatically selects and integrates suitable models from the model library based on a user's instructions. The key insight is that harnessing such a massive and heterogeneous pool requires not only finding the most relevant modules among thousands of candidates, but also aligning them effectively for instruction-driven generation and editing. Polaris addresses this challenge by indexing over 6,500 checkpoints and 75,000 adapters, and retrieving the most relevant components given a user's input and instruction. In doing so, it delivers scalable, controllable, and well-aligned generation -- without any additional training.
arXiv:2604.01562v2 Announce Type: replace
Abstract: Voice cloning is often evaluated in terms of overall quality, but less is known about accent preservation and its perceptual consequences. We compare standard and heavily accented Mandarin speech and their voice clones using a combined computational and perceptual design. Embedding-based analyses showed larger original-clone distances for accented speakers in several speaker-discriminative embedding spaces, but this difference disappeared after normalizing against each speaker's within-original baseline variability. In the perception study, clones are rated as more similar to their originals for standard than for accented speakers, and intelligibility increases from original to clone, with a larger gain for accented speech. These results show that accent variation can shape perceived identity match and intelligibility in voice cloning even when it is not reflected in baseline-normalized speaker-embedding distance, and they motivate treating accent preservation as an explicit component of speaker identity preservation, rather than assuming that it is fully captured by off-the-shelf speaker-discriminative embeddings.
Qwen-VLA: Unifying Vision-Language-Action Modeling across Tasks, Environments, and Robot Embodiments
arXiv:2605.30280v2 Announce Type: replace
Abstract: Embodied intelligence is often studied through specialized models for individual tasks such as manipulation or navigation, resulting in fragmented capabilities and limited generalization across tasks, environments, and robot embodiments. In this work, we study whether heterogeneous embodied decision-making problems can be unified within a single vision-language-action model. We present Qwen-VLA, a unified embodied foundation model that extends Qwen's vision-language modeling stack from perception, understanding, and reasoning to continuous action and trajectory generation through a DiT-based action decoder. Qwen-VLA is trained with a large-scale joint pretraining recipe over diverse data sources, including robotics manipulation trajectories, human egocentric demonstrations, synthetic simulation data, vision-and-language navigation data, trajectory-centric supervision, and auxiliary vision-language data. To support multiple robot platforms, we introduce embodiment-aware prompt conditioning, where robot-specific textual descriptions specify the current embodiment and control convention. We further cast manipulation, navigation, and trajectory prediction into a unified action-and-trajectory prediction framework, enabling transferable visual grounding, spatial reasoning, and continuous action generation across robot morphologies, task families, and environments. Experiments on manipulation, navigation, and trajectory-centric benchmarks show consistent multi-task performance and out-of-distribution generalization under variations in scene layout, background, lighting, object configuration, and robot embodiment. Qwen-VLA-Instruct achieves 97.9% on LIBERO, 73.7% on Simpler-WidowX, 86.1%/87.2% on RoboTwin-Easy/Hard, 69.0% OSR on R2R, 59.6% SR on RxR, 76.9% average OOD success in real-world ALOHA experiments, and 26.6% zero-shot success on DOMINO dynamic manipulation.
arXiv:2604.09487v2 Announce Type: replace
Abstract: Tendon drives paired with soft muscle actuation enable faster and safer robots while potentially accelerating skill acquisition. Still, these systems are rarely used in practice due to inherent nonlinearities, friction, and hysteresis, which complicate modeling and control. So far, these challenges have hindered policy transfer from simulation to real systems. To bridge this gap, we propose a sim-to-real pipeline that learns a neural network model of this complex actuation and leverages established rigid body simulation for the arm dynamics and interactions with the environment. Our method, called Generalized Actuator Network (GenAN), enables actuation model identification across a wide range of robots by learning directly from joint position trajectories rather than requiring torque sensors. Using GenAN on PAMY2, a tendon-driven robot powered by pneumatic artificial muscles, we successfully deploy dynamic but precise goal-reaching, ball-in-a-cup, and table tennis policies, trained entirely in simulation. To the best of our knowledge, this result constitutes the first successful sim-to-real transfer for a four-degrees-of-freedom muscle-actuated robot arm.
arXiv:2604.09877v2 Announce Type: replace
Abstract: At the intersection of computer vision and robotic perception, 4D reconstruction of dynamic scenes connects low-level geometric sensing with high-level semantic understanding. We present Genie 4D, a framework that turns hand-held phone capture into a semantically grounded, action-controllable 4D world model. Genie 4D couples a real-time visual-inertial Gaussian splatting front-end for metric geometry with a feed-forward 4D backbone regularized by frozen DINOv3 features acting as structural priors. The semantic priors suppress identity drift during dynamic tracking, while a short conditional diffusion refiner recovers high-frequency surface detail that regression backbones smooth away. Finally, a lightweight latent-action head exposes the reconstructed 4D state to a Genie-style world model trained with a JEPA-style next-embedding objective, so that the scene can be rolled forward under user actions. On the Point Odyssey and TUM-Dynamics benchmarks, Genie 4D retains the linear time complexity O(T) of feed-forward baselines while improving 3D tracking accuracy (APD) and reconstruction completeness, and it runs interactively on a single consumer GPU (RTX 5090) from iPhone, Mac, Windows, and Linux capture clients. Genie 4D offers a practical, semantic-prior-guided path toward physically grounded world models.
arXiv:2606.01612v1 Announce Type: new
Abstract: Can internal attention patterns in Large Vision Language Models (LVLMs) identify reliable small-object boxes without fine-tuning? In this work, we provide an affirmative answer. Attention structure in LVLMs encodes grounding quality-a lightweight IoU regressor trained solely on attention maps achieves strong IoU prediction (Pearson r > 0.67). This regressor powers the regressor-based variant of our Attention-based Candidate Selection (ACS) framework, called ACS-Learned, which selects the best box from multiple sampled candidates to improve object grounding. By analyzing what the regressor learns, we reveal which transformer layers and heads are most critical and derive ACS-Free: a training-free selector that ranks candidates by attention entropy on these discriminative heads, with no learned component at inference. Experiments on COCO and Objects365 demonstrate up to 19% self-improvement on small object localization, with ACS-Free ranking best among all training-free methods, demonstrating that useful attention structure improves both localization reliability and interpretability in LVLMs.
arXiv:2606.02276v1 Announce Type: new
Abstract: Vision-language models (VLMs) trained on paired chest radiographs and radiology reports learn a shared embedding space that can preserve instance-level image-report correspondence. This poses a privacy risk in settings where radiographs and reports are deliberately kept separate after acquisition, such as image-only data sharing or access-controlled reports, because a de-identified image may be re-linked to its original narrative report through cosine similarity alone. We formalized this as image-to-report retrieval and used public paired cohorts, in which the true pairing is known by design, as ground-truth benchmarks to audit the risk rather than as the privacy scenario. Evaluating VLMs of increasing clinical specialization on 406,241 paired examples from 126,804 patients across MIMIC-CXR (43,793 held-out pairs) and external CheXpert Plus (29,296 pairs), we found that re-linkage rose systematically with specialization: the strongest VLM retrieved the correct report at 15 times chance at a candidate pool of N = 100, 50 times chance at N = 10,000, and well above chance at full-database scale. The signal persisted under pathology-matched hard negatives that removed disease-label shortcuts, indicating correspondence beyond broad diagnostic categories. To reduce it without retraining, we froze both encoders and applied differentially private optimization only to the projection heads defining the alignment layer (epsilon = 0.34, delta = 6x10-6). This reduced Recall@1 by 61.8% at N = 10,000 on MIMIC-CXR and transferred to CheXpert Plus without retraining, while image-side utility was largely preserved: macro AUROC for linear-probe classification across 14 labels shifted only from 79.63% to 79.43%. Targeted DP finetuning of the shared alignment layer can substantially reduce cross-modal re-linkage without materially degrading the image representations that make these models clinically useful.
arXiv:2605.30935v2 Announce Type: replace-cross
Abstract: We use boson sampling as part of a gradient-free variational algorithm (the Binary Bosonic Solver) to solve a minimum dominating set problem and compare these results to a number of exact and heuristic classical algorithms. The boson sampling has been performed on the physical PT-2 time-bin interferometer from ORCA Computing. The PT-2 device has been tested here using both a single- and double-loop configuration and the results are compared based on the best found solution and the overall run time. With the parameters used in this experiment, the boson sampler is outperformed by the classical methods, but we hypothesise that this is due to insufficient samples and iterations. We classically simulate boson sampling in a single-loop configuration to break down the runtime for individual algorithmic components, allowing for estimates of when boson sampling may outperform classical methods. This study recommends a watching brief on boson sampling as the complexity of the interferometer is improved and the loss in the hardware is reduced allowing for better performance from the associated algorithms.
arXiv:2604.10645v2 Announce Type: replace
Abstract: There is a pressing need for better development methods and tools to keep up with the growing demand and increasing complexity of new software systems. New types of user interfaces, the need for intelligent components, sustainability concerns, etc. bring new challenges that we need to handle. In the last years, model-driven engineering (MDE), including its latest incarnation, i.e. low/no-code development, has been key to improving the quality and productivity of software development, but models themselves are becoming increasingly complex to specify and manage. At the same time, we are witnessing the growing popularity of vibe coding approaches that rely on Large Language Models (LLMs) to transform natural language descriptions into running code at the expense of potential code vulnerabilities, scalability issues and maintainability concerns.
While many may think vibe coding will replace model-based engineering, in this paper we argue that, in fact, the two approaches can complement each other and provide altogether different development paths for different types of software systems, development scenarios, and user profiles. In this sense, we introduce the concept of \textit{vibe-driven model-based engineering} as a novel approach to integrate the best of both worlds (AI and MDE) to accelerate the development of reliable complex systems. We outline the key concepts of this new approach and highlight the opportunities and open challenges it presents for the future of software development.
arXiv:2604.10716v3 Announce Type: replace
Abstract: Existing Point Cloud Networks (PCNs) have proven to achieve great success in many point cloud tasks such as object part segmentation, shape classification, and so on. The most popular point-based PCNs are usually composed of two sequential steps: Data Structuring (DS) and Feature Computation (FC). In this paper, we first describe an important characteristic of the PCN-specific DS step that has not been addressed in existing PCN accelerators: the spatial locality resulting from overlapping points of the gathered point subsets. Using algorithm-hardware co-design, L-PCN (Locality-aware PCN) proposes two novel techniques to exploit this characteristic to reduce the large amount of repetitive operations in the overall PCN. The first of which is a point cloud partitioning technique, Octree-based Islandization. Using Octree-based adjacency gathering, a point cloud is partitioned into islands in L-PCN, where the point subsets inside the same island exhibit a strong spatial correlation. After partitioning, L-PCN performs the rest of PCN steps at the granularity of islands. The second method of L-PCN is scheduling the intra-island computation with a Hub-based Scheduling to exploit the intra-island data reuse by dynamically caching, updating, and reusing the repeated data. The two methods are implemented in an Islandization Unit, which can be seamlessly integrated into standard PCN workflow. Our evaluation shows that based on our methods for exploiting spatial locality, L-PCN achieves a theoretical reduction in feature fetching ranging from 55.2% to 93.8% and in feature computation ranging from 45.4% to 80.6% during the PCN process. For experimentation, prototype L-PCN accelerators are implemented on the Intel Arria 10 GX FPGA. Experimental results prove that with the Islandization Unit as a plug-in, state-of-the-art PCN accelerators can achieve an additional speedup ranging from 1.2x to 3.2x.
arXiv:2604.26197v3 Announce Type: replace
Abstract: Large Language Model (LLM) agents are increasingly used in real-world products, where personalized and context-aware user interactions are essential. A central enabler of such capabilities is the agent's long-term semantic memory system, which extracts implicit and explicit signals from noisy longitudinal behavioral data, stores them in a structured form, and supports low-latency retrieval. Building industrial-grade long-term memory for LLM agents raises five challenges: scalability, low-latency retrieval, privacy constraints, adaptability, and observability. We introduce the Hierarchical Long-Term Semantic Memory (HLTM) framework, which organizes textual data into a schema-aligned memory tree that captures semantic knowledge at multiple levels of granularity, enabling scalable ingestion, privacy-aware storage, low-latency retrieval, and transparent provenance; HLTM further incorporates an adaptation mechanism to generalize across diverse use cases. Extensive evaluations on LinkedIn's Hiring Assistant show that HLTM improves answer correctness by more than 5% and retrieval F1 by more than 10%, while significantly advancing the Pareto frontier between query and indexing latency. HLTM has been fully deployed in LinkedIn's Hiring Assistant to power core personalization features in production hiring workflows.
arXiv:2605.00161v2 Announce Type: replace
Abstract: Diffusion language models (DLMs) are an attractive alternative to autoregressive models because they promise sublinear-time, parallel generation, yet practical gains remain elusive as high-quality samples still demand hundreds of refinement steps. In continuous domains, consistency training along the probability-flow ODE is a popular recipe to accelerate diffusion. For discrete diffusion, no analogous sample-space ODE exists, making direct adaptation ill-defined. We argue that the right discrete substitute is the exact posterior bridge, the closed-form conditional law linking any two noise levels, which is available for broad corruptions including masked and uniform diffusion. Building on this observation, we introduce Multi-Path Discrete Consistency (MPDC), a new principle that trains a denoiser to be path-invariant in expectation across these stochastic bridges, and instantiate it as the Consistent Diffusion Language Model (CDLM), a single-stage training framework that does not require an already trained teacher model. Our CDLM objective recovers masked diffusion, continuous consistency models, and progressive or discrete distillation as analytic limits or empirical approximations of one common view. Empirically, CDLM establishes a new state of the art on both conditional and unconditional text-generation, consistently outperforming strong base discrete diffusion models and often even multi-stage distilled baselines across sampling budgets, with the largest gains in the few-step regime. Together, these results position CDLM as a principled and scalable foundation for the next generation of fast, high-fidelity discrete generative modeling.
arXiv:2605.00310v2 Announce Type: replace
Abstract: Super-resolution (SR) techniques have made major advances in reconstructing high-resolution images from low-resolution inputs. The increased resolution provides visual enhancement and utility for monitoring tasks. In particular, SR has been increasingly developed for satellite-based Earth observation, with applications in urban planning, agriculture, ecology, and disaster response. However, existing SR studies and benchmarks typically use fidelity metrics such as PSNR or SSIM, whereas the true utility of super-resolved images lies in supporting downstream tasks such as land cover classification, biomass estimation, and change detection. To bridge this gap, we introduce GeoSR-Bench, a downstream task-integrated SR benchmark dataset to evaluate SR models beyond fidelity metrics. GeoSR-Bench comprises spatially co-located, temporally aligned, and quality-controlled image pairs from about 36,000 locations across diverse land covers, spanning resolutions from 500m to 0.6m. To the best of our knowledge, GeoSR-Bench is the first SR benchmark that directly connects improved image resolution from SR models with downstream Earth monitoring tasks, including land cover segmentation, infrastructure mapping, and biophysical variable estimation. Using GeoSR-Bench, we benchmark GAN, transformer, neural operator, and diffusion-based SR models on perceptual quality and downstream task performance. We conduct experiments with 270 settings, covering 2 cross-platform SR tasks, 9 SR models, 3 downstream task models, and 5 downstream tasks for each SR task. The results show that improvements in traditional SR metrics often do not correlate with gains in task performance, and the correlations can be negative, indicating that these metrics provide limited guidance for selecting superior models for downstream tasks. This reveals the need to integrate downstream tasks into SR model development and evaluation.
arXiv:2605.00394v3 Announce Type: replace
Abstract: We present Mesh Field Theory (MeshFT) and its neural realization, MeshFT-Net: a structure-preserving framework for mesh-based continuum physics that cleanly separates the physics' topological structure from its metric structure. Imposing minimal physical principles (locality, permutation equivariance, orientation covariance, and energy balance/dissipation inequality), we prove a reduction theorem for mesh-based physics. Under these conditions, the physical dynamics admit a local factorization into a port-Hamiltonian form: the conservative interconnection is fixed uniquely by mesh topology, whereas metric effects enter only through constitutive relations and dissipation. This reduction clarifies what must be fixed and what should be learned, directly informing MeshFT-Net's design. Across evaluations on analytic and realistic datasets, physics-consistency tests, and out-of-distribution validation, MeshFT-Net achieves near-zero energy drift and strong physical fidelity (correct dispersion and momentum conservation) along with robust extrapolation and high data efficiency. By eliminating non-physical degrees of freedom and learning only metric-dependent structure, MeshFT provides a principled inductive bias for stable, faithful, and data-efficient learning-based physical simulation.
arXiv:2605.00941v4 Announce Type: replace
Abstract: Flow matching has become a leading framework for generative modeling, but quantifying the uncertainty of its samples remains an open problem. Existing approaches retrain the model with auxiliary variance heads, maintain costly ensembles, or propagate approximate covariance through many integration steps, trading off training cost, inference cost, or accuracy. We show that none of these trade-offs is necessary. By extending Tweedie's formula from the denoising setting to the flow matching interpolant, we derive an exact, closed-form expression for the posterior covariance at every point along the generative trajectory. The result depends on a single quantity, namely the divergence of the learned velocity field, which can be computed post-hoc on any pre-trained flow matching model, requiring no retraining and no architectural modification. For one-step generators such as MeanFlow, the same formula yields the end-to-end generation uncertainty in a single forward pass, eliminating the multi-step variance propagation required by all prior methods. Experiments on MNIST confirm that the resulting per-pixel uncertainty maps are semantically meaningful, concentrating on digit boundaries where inter-sample variation is highest, and that the scalar uncertainty score tracks actual prediction error, all at roughly $10^4 \times$ less total compute than ensembling or Monte Carlo dropout.
arXiv:2604.17415v3 Announce Type: replace
Abstract: Reward-based fine-tuning steers a pretrained diffusion or flow-based generative model toward higher-reward samples while remaining close to the pretrained model. Although existing methods are derived from different perspectives, we show that many can be written under a common framework, which we call reward score matching (RSM). Under this view, alignment becomes score matching against a value-guided target, and the main differences across methods reduce to the construction of the value-guidance estimator and the effective optimization strength across timesteps. This unification clarifies the bias-variance-compute tradeoffs of existing designs, and distinguishes core optimization components from auxiliary mechanisms that add complexity without clear benefit. Guided by this perspective, we develop simpler, more efficient redesigns across representative differentiable and black-box reward alignment tasks. Overall, RSM turns a seemingly fragmented collection of reward-based fine-tuning methods into a smaller, more interpretable, and more actionable design space. Code is available at https://github.com/jaylee2000/rsm
arXiv:2605.00998v2 Announce Type: replace
Abstract: Tree tensor network states (TTNSs) combined with the density matrix renormalization group (DMRG) are emerging as powerful tools for vibrational and vibronic structure simulations in molecules with strong coupling and fluxionality. In this Perspective, we discuss how TTNS methods enable accurate, full-dimensional computations of thousands of eigenstates for molecular systems ranging from quartic-force-field benchmarks to molecules with strong vibronic coupling and protonated water clusters as large as the 33-dimensional Eigen ion, H$_3$O$^+$$\cdot$(H$_2$O)$_3$. We emphasize the close connection and interoperability between DMRG-based TTNS methods and the multilayer multiconfiguration time-dependent Hartree method (ML-MCTDH), which share the same underlying ansatz. We also highlight practical challenges of predictive simulations, including robust error estimation, convergence of observables such as infrared intensities, and optimization of tensor network tree structures. Finally, we outline recent advances toward direct targeting of excited states and discuss opportunities for broader applications in molecular spectroscopy and quantum dynamics.
arXiv:2605.14661v2 Announce Type: replace
Abstract: Fluid antenna is a new reconfigurable antenna technology that can dynamically adjust the positions or ports of radiating elements and therefore provides a new degree of freedom for wireless communications. However, the associated port selection is a challenging large-scale combinatorial optimization problem and difficult to solve. Existing manually designed heuristic algorithms are not only labor-intensive, but cannot achieve satisfactory performance. In this paper, we propose a novel paradigm that leverages large language models (LLMs) for automated design of optimization algorithms for fluid antenna systems without manual hyperheuristic tuning. Specifically, we study the problem of maximizing the minimum signal-to-interference-plus-noise ratio (SINR) in the downlink to ensure fairness among users by optimizing port selection and beamforming. We investigate two LLM-enabled algorithm optimization strategies. The first is to optimize the crossover and mutation operations to enhance the performance of the well-known genetic algorithm and the second is to design AutoPort, a new heuristic from scratch by LLM, to solve the optimization problem. Simulation results verify that the proposed method can achieve near-optimal performance and significant improvement over the conventional genetic algorithm and the deep learning approach.
arXiv:2605.14709v2 Announce Type: replace
Abstract: Recent unified models integrate multimodal understanding and generation within a single framework. However, an "understanding-generation gap" persists, where models can capture user intent but often fail to translate this semantic knowledge into precise pixel-level manipulation. This gap results in two bottlenecks in anything-to-image task (X2I): the attention entanglement bottleneck, where blind planning struggles with complex prompts, and the visual refinement bottleneck, where unstructured feedback fails to correct imperfections efficiently. In this paper, we propose a novel framework that empowers unified models to autonomously switch between generation strategies based on instruction complexity and model capability. To achieve this, we construct a hierarchical data pipeline that constructs execution paths across three adaptive modes: direct generation for simple cases, self-reflection for quality refinement, and multi-step planning for decomposing complex scenarios. Building on this pipeline, we contribute a high-quality dataset with over 50,000 samples and implement a two-stage training strategy comprising SFT and RL. Specifically, we design step-wise reasoning rewards to ensure logical consistency and intra-group complexity penalty to prevent redundant computational overhead. Extensive experiments demonstrate that our method outperforms existing baselines on X2I, achieving superior generation fidelity among simple-to-complex instructions. The code is released at https://github.com/WeChatCV/Interleaved_Visual_Reasoner.
arXiv:2605.15511v2 Announce Type: replace
Abstract: Graph Neural Networks (GNNs) have become the dominant framework for inductive graph-level learning. Yet most benchmarks focus on the regime $n \gg p$, where the number of graphs $n$ greatly exceeds the number of nodes per graph $p$. This overlooks biological domains such as omics, which operate in the opposite $n \ll p$ regime, characterized by large graphs of genes, transcripts, or proteins across few patient samples. This raises the question: \textit{how do GNNs perform in this low-sample, high-node omics setting?} We introduce \texttt{OgBench} (Omics-Graph Bench), the first benchmarking platform for graph-level prediction in the $n \ll p$ regime characteristic of omics data. We provide a standardized, end-to-end modular infrastructure from raw omics data to families of featured graphs with varied structural properties. We benchmark classical GNNs, as well as GNNs designed for large graphs and omics applications, alongside MLPs and machine learning baselines to establish reference performances. Our results show that widely used GNNs often do not outperform simple MLPs and classical baselines. These findings challenge the prevailing assumption that graph structure inherently adds value in this domain, fostering a critical reassessment of current learning paradigms. Ultimately, by exposing these limitations, OgBench provides the open-source ecosystem necessary for the community to develop and validate novel architectures explicitly tailored for biological graphs. The code is available at https://github.com/geometric-intelligence/ogbench.