arXiv subjects

Yue Wang

Publications and source records attributed to Yue Wang.

At least 379 records · Page 21Linked to original sources

arXiv2025

Symbolic Representation for Any-to-Any Generative Tasks

We propose a symbolic generative task description language and a corresponding inference engine capable of representing arbitrary multimodal tasks as structured symbolic flows. Unlike conventional generative models that rely on large-scale training and implicit neural representations to learn cross-modal mappings, often at high computational cost and with limited flexibility, our framework introduces an explicit symbolic representation comprising three core primitives: functions, parameters, and topological logic. Leveraging a pre-trained language model, our inference engine maps natural language instructions directly to symbolic workflows in a training-free manner. Our framework successfully performs over 12 diverse multimodal generative tasks, demonstrating strong performance and flexibility without the need for task-specific tuning. Experiments show that our method not only matches or outperforms existing state-of-the-art unified models in content quality, but also offers greater efficiency, editability, and interruptibility. We believe that symbolic task representations provide a cost-effective and extensible foundation for advancing the capabilities of generative AI.

cs.LG↗

arXiv2025

OmniRe: Omni Urban Scene Reconstruction

We introduce OmniRe, a comprehensive system for efficiently creating high-fidelity digital twins of dynamic real-world scenes from on-device logs. Recent methods using neural fields or Gaussian Splatting primarily focus on vehicles, hindering a holistic framework for all dynamic foregrounds demanded by downstream applications, e.g., the simulation of human behavior. OmniRe extends beyond vehicle modeling to enable accurate, full-length reconstruction of diverse dynamic objects in urban scenes. Our approach builds scene graphs on 3DGS and constructs multiple Gaussian representations in canonical spaces that model various dynamic actors, including vehicles, pedestrians, cyclists, and others. OmniRe allows holistically reconstructing any dynamic object in the scene, enabling advanced simulations (~60Hz) that include human-participated scenarios, such as pedestrian behavior simulation and human-vehicle interaction. This comprehensive simulation capability is unmatched by existing methods. Extensive evaluations on the Waymo dataset show that our approach outperforms prior state-of-the-art methods quantitatively and qualitatively by a large margin. We further extend our results to 5 additional popular driving datasets to demonstrate its generalizability on common urban scenes.

cs.CV↗

arXiv2025

Sculpting of Exoplanetary Systems Driven by a Misaligned Disk and Stellar Oblateness: Origin of Perpendicular Orbits in HD 3167

A significant proportion of exoplanets have been detected with highly tilted or even polar orbits relative to their host stars' equatorial planes. These unusual orbital configurations are often linked to post-disk secular interactions among multiple bodies. However, many aspects remain elusive. In this study, we investigate the role of disk-induced spin-orbit misalignments in shaping architecture of multi-planet systems, taking into account the combined effect of the host star's oblateness and the full-space disk potential. We demonstrate that large mutual planetary inclinations can arise from a saddle-center bifurcation occurring during the photoevaporation of the disk. This bifurcation triggers an instant, non-adiabatic transition in the planet's libration. Following this process, the orbital evolution diverges into several distinct patterns. Notably, in scenarios involving a near-polar primordial misalignment, the orbit, consistently librating about a coplanar equilibrium axis, can be captured by an orthogonal equilibrium during the decay of the stellar oblateness. However, the orbit will be eventually recaptured by the coplanar equilibrium, aligned or anti-aligned with the orientation of the outer orbit, resulting in either a prograde or retrograde inner-outer orbit configuration. Additionally, general relativity contributes to maintaining eccentricity stability within these dynamic scenarios. Through the proposed mechanism, we can provide a plausible explanation for the unique, near-perpendicular and likely retrograde orbit architecture observed in the HD 3167 system, enhancing our understanding of exoplanetary system dynamics.

astro-ph.EP↗

arXiv2025

Bifurcated Evolutionary Pathways in Multi-planet Systems Driven by Misaligned Protoplanetary Disks

Stellar obliquities, or spin-orbit angles, prevalent in exoplanet systems, can impose important constraints on their formation and evolution histories. Recent studies suggest that primordial misalignments between protoplanetary disks and stellar spin axes may significantly contribute to these obliquities, as those frequently observed in systems hosting hot Jupiters. In this study, we demonstrate that misaligned protoplanetary disks combined with stellar oblateness drive complex dynamical evolution in planetary systems during their disk dispersal stages. Specifically, we identify bifurcated evolutionary pathways in multi-planet systems: systems with low star-disk misalignment angles ($ψ_{\star0}$) undergo smooth, adiabatic evolution, producing nearly coplanar, low-obliquity configurations; in contrast, systems with high misalignment angles typically experience an abrupt, non-adiabatic transition, leading to large-amplitude libration of mutual planetary inclinations and then triggering chaotic eccentricity excitation. This libration and eccentricity excitation process can propagate inward-outward in compact multi-planet systems, forming an excitation chain that can destabilize the entire system. The non-adiabatic transition arises from the dynamical bifurcation-induced effect, which occurs during disk dissipation when $ψ_{\star0}\gtrsim44.6^\circ$ (for one-planet systems). Our framework predicts that surviving typical compact multi-planet systems originating from misaligned disks evolve toward coplanar, low-obliquity configurations, consistent with observations of Kepler multi-planet systems. These results advance our understanding of planetary dynamics in misaligned disks and their evolutionary outcomes.

astro-ph.EP↗

arXiv2025

Redefining Machine Translation on Social Network Services with Large Language Models

The globalization of social interactions has heightened the need for machine translation (MT) on Social Network Services (SNS), yet traditional models struggle with culturally nuanced content like memes, slang, and pop culture references. While large language models (LLMs) have advanced general-purpose translation, their performance on SNS-specific content remains limited due to insufficient specialized training data and evaluation benchmarks. This paper introduces RedTrans, a 72B LLM tailored for SNS translation, trained on a novel dataset developed through three innovations: (1) Supervised Finetuning with Dual-LLM Back-Translation Sampling, an unsupervised sampling method using LLM-based back-translation to select diverse data for large-scale finetuning; (2) Rewritten Preference Optimization (RePO), an algorithm that identifies and corrects erroneous preference pairs through expert annotation, building reliable preference corpora; and (3) RedTrans-Bench, the first benchmark for SNS translation, evaluating phenomena like humor localization, emoji semantics, and meme adaptation. Experiments show RedTrans outperforms state-of-the-art LLMs. Besides, RedTrans has already been deployed in a real-world production environment, demonstrating that domain-specific adaptation, effectively bridges the gap between generic and culturally grounded translation systems.

cs.CL↗

arXiv2025

CodeEditorBench: Evaluating Code Editing Capability of Large Language Models

Large Language Models (LLMs) for code are rapidly evolving, with code editing emerging as a critical capability. We introduce CodeEditorBench, an evaluation framework designed to rigorously assess the performance of LLMs in code editing tasks, including debugging, translating, polishing, and requirement switching. Unlike existing benchmarks focusing solely on code generation, CodeEditorBench emphasizes real-world scenarios and practical aspects of software development. We curate diverse coding challenges and scenarios from five sources, covering various programming languages, complexity levels, and editing tasks. Evaluation of 19 LLMs reveals that closed-source models (particularly Gemini-Ultra and GPT-4), outperform open-source models in CodeEditorBench, highlighting differences in model performance based on problem types and prompt sensitivities. CodeEditorBench aims to catalyze advancements in LLMs by providing a robust platform for assessing code editing capabilities. We will release all prompts and datasets to enable the community to expand the dataset and benchmark emerging LLMs. By introducing CodeEditorBench, we contribute to the advancement of LLMs in code editing and provide a valuable resource for researchers and practitioners.

cs.SE↗

arXiv2025

Grounding 3D Object Affordance with Language Instructions, Visual Observations and Interactions

Grounding 3D object affordance is a task that locates objects in 3D space where they can be manipulated, which links perception and action for embodied intelligence. For example, for an intelligent robot, it is necessary to accurately ground the affordance of an object and grasp it according to human instructions. In this paper, we introduce a novel task that grounds 3D object affordance based on language instructions, visual observations and interactions, which is inspired by cognitive science. We collect an Affordance Grounding dataset with Points, Images and Language instructions (AGPIL) to support the proposed task. In the 3D physical world, due to observation orientation, object rotation, or spatial occlusion, we can only get a partial observation of the object. So this dataset includes affordance estimations of objects from full-view, partial-view, and rotation-view perspectives. To accomplish this task, we propose LMAffordance3D, the first multi-modal, language-guided 3D affordance grounding network, which applies a vision-language model to fuse 2D and 3D spatial features with semantic features. Comprehensive experiments on AGPIL demonstrate the effectiveness and superiority of our method on this task, even in unseen experimental settings. Our project is available at https://sites.google.com/view/lmaffordance3d.

cs.CV↗

arXiv2025

A hydro-geomechanical porous-media model to study effects of engineered carbonate precipitation in faults

Hydro-geomechanical models are required to predict or understand the impact of subsurface engineering applications as, for example, in gas storage in geological formations. This study puts a focus on engineered carbonate precipitation through biomineralization in a fault zone of a cap-rock to reduce gas leakage from a reservoir. Besides hydraulic properties like porosity and permeability, precipitated carbonates also change the mechanical properties of the rock. We present a conceptual modeling approach implemented into the open-source simulator Dumux and, after verification examples, at hand of a CO2-storage scenario, we discuss impacts of biomineralization on the stress distribution in the rock and potentially altered risks of fault reactivations and induced seismic events. The generic study shows the tendency towards increased stiffness due to precipitated carbonate, which may cause shear failure events to occur earlier than in an untreated setup, while the magnitude of the seismicity is smaller.

cs.CE↗

arXiv2025

Microbial correlation: a semi-parametric model for investigating microbial co-metabolism

The gut microbiome plays a crucial role in human health, yet the mechanisms underlying host-microbiome interactions remain unclear, limiting its translational potential. Recent microbiome multiomics studies, particularly paired microbiome-metabolome studies (PM2S), provide valuable insights into gut metabolism as a key mediator of these interactions. Our preliminary data reveal strong correlations among certain gut metabolites, suggesting shared metabolic pathways and microbial co-metabolism. However, these findings are confounded by various factors, underscoring the need for a more rigorous statistical approach. Thus, we introduce microbial correlation, a novel metric that quantifies how two metabolites are co-regulated by the same gut microbes while accounting for confounders. Statistically, it is based on a partially linear model that isolates microbial-driven associations, and a consistent estimator is established based on semi-parametric theory. To improve efficiency, we develop a calibrated estimator with a parametric rate, maximizing the use of large external metagenomic datasets without paired metabolomic profiles. This calibrated estimator also enables efficient p-value calculation for identifying significant microbial co-metabolism signals. Through extensive numerical analysis, our method identifies important microbial co-metabolism patterns for healthy individuals, serving as a benchmark for future studies in diseased populations.

stat.ME↗

arXiv2025

Low Energy Backgrounds and Excess Noise in a Two-Channel Low-Threshold Calorimeter

We describe observations of low energy excess (LEE) events, background events observed in all light dark matter direct detection calorimeters, and noise in a Transition Edge Sensor based two-channel silicon athermal phonon detector with 375 meV baseline energy resolution. We measure two distinct LEE populations: ``shared'' multichannel events with a pulse shape consistent with substrate athermal phonon events, and sub-eV events that couple nearly exclusively to a single channel with a significantly faster pulse shape. These ``singles'' are consistent with events occurring within the aluminum athermal phonon collection fins. Similarly, our measured detector noise is higher than the theoretical expectation. Measured noise can be split into an uncorrelated component, consistent with shot noise from small energy depositions within the athermal phonon sensor itself, and a correlated component, consistent with shot noise from energy depositions within the silicon substrate's phonon system.

physics.ins-det↗

arXiv2025

Quattro: Transformer-Accelerated Iterative Linear Quadratic Regulator Framework for Fast Trajectory Optimization

Real-time optimal control remains a fundamental challenge in robotics, especially for nonlinear systems with stringent performance requirements. As one of the representative trajectory optimization algorithms, the iterative Linear Quadratic Regulator (iLQR) faces limitations due to their inherently sequential computational nature, which restricts the efficiency and applicability of real-time control for robotic systems. While existing parallel implementations aim to overcome the above limitations, they typically demand additional computational iterations and high-performance hardware, leading to only modest practical improvements. In this paper, we introduce Quattro, a transformer-accelerated iLQR framework employing an algorithm-hardware co-design strategy to predict intermediate feedback and feedforward matrices. It facilitates effective parallel computations on resource-constrained devices without sacrificing accuracy. Experiments on cart-pole and quadrotor systems show an algorithm-level acceleration of up to 5.3$\times$ and 27$\times$ per iteration, respectively. When integrated into a Model Predictive Control (MPC) framework, Quattro achieves overall speedups of 2.8$\times$ for the cart-pole and 17.8$\times$ for the quadrotor compared to the one that applies traditional iLQR. Transformer inference is deployed on FPGA to maximize performance, achieving further up to 20.8$\times$ speedup over prevalent embedded CPUs with over 11$\times$ power reduction than GPU and low hardware resource overhead.

eess.SY↗

arXiv2025

Enabling Continuous THz Band Coverage via Precise Electron Beam Tailoring in Free-electron Lasers

High-power, continuously tunable narrowband terahertz (THz) sources are essential for advancing nonlinear optics, THz-driven material dynamics, and ultrafast spectroscopy. Conventional techniques typically impose a trade-off between pulse energy and frequency tunability. Here, we introduce a novel free-electron laser approach that overcomes these limitations by pre-modulating a relativistic electron beam with a frequency-beating laser pulse and leveraging bunch compression along with collective effects to enhance microbunching. Experimental results demonstrate that this technique generates narrowband THz emission with continuous frequency tunability from 7.8 to 30.8THz, achieving pulse energies up to 385μJ while maintaining spectral bandwidths between 7.7% and 14.7%. Moreover, the method exhibits exceptional robustness and scalability, highlighting its unique ability to bridge the long-standing THz gap and offering a promising solution for diverse cutting-edge scientific applications.

physics.acc-ph↗

arXiv2025

Distributed Resource Allocation for Human-Autonomy Teaming under Coupled Constraints

This paper studies the optimal resource allocation problem within a multi-agent network composed of both autonomous agents and humans. The main challenge lies in the globally coupled constraints that link the decisions of autonomous agents with those of humans. To address this, we propose a reformulation that transforms these coupled constraints into decoupled local constraints defined over the system's communication graph. Building on this reformulation and incorporating a human response model that captures human-robot interactions while accounting for individual preferences and biases, we develop a fully distributed algorithm. This algorithm guides the states of the autonomous agents to equilibrium points which, when combined with the human responses, yield a globally optimal resource allocation. We provide both theoretical analysis and numerical simulations to validate the effectiveness of the proposed approach.

eess.SY↗

arXiv2025

HW-NAS-Bench:Hardware-Aware Neural Architecture Search Benchmark

HardWare-aware Neural Architecture Search (HW-NAS) has recently gained tremendous attention by automating the design of DNNs deployed in more resource-constrained daily life devices. Despite its promising performance, developing optimal HW-NAS solutions can be prohibitively challenging as it requires cross-disciplinary knowledge in the algorithm, micro-architecture, and device-specific compilation. First, to determine the hardware-cost to be incorporated into the NAS process, existing works mostly adopt either pre-collected hardware-cost look-up tables or device-specific hardware-cost models. Both of them limit the development of HW-NAS innovations and impose a barrier-to-entry to non-hardware experts. Second, similar to generic NAS, it can be notoriously difficult to benchmark HW-NAS algorithms due to their significant required computational resources and the differences in adopted search spaces, hyperparameters, and hardware devices. To this end, we develop HW-NAS-Bench, the first public dataset for HW-NAS research which aims to democratize HW-NAS research to non-hardware experts and make HW-NAS research more reproducible and accessible. To design HW-NAS-Bench, we carefully collected the measured/estimated hardware performance of all the networks in the search spaces of both NAS-Bench-201 and FBNet, on six hardware devices that fall into three categories (i.e., commercial edge devices, FPGA, and ASIC). Furthermore, we provide a comprehensive analysis of the collected measurements in HW-NAS-Bench to provide insights for HW-NAS research. Finally, we demonstrate exemplary user cases to (1) show that HW-NAS-Bench allows non-hardware experts to perform HW-NAS by simply querying it and (2) verify that dedicated device-specific HW-NAS can indeed lead to optimal accuracy-cost trade-offs. The codes and all collected data are available at https://github.com/RICE-EIC/HW-NAS-Bench.

cs.LG↗

arXiv2025

UGNA-VPR: A Novel Training Paradigm for Visual Place Recognition Based on Uncertainty-Guided NeRF Augmentation

Visual place recognition (VPR) is crucial for robots to identify previously visited locations, playing an important role in autonomous navigation in both indoor and outdoor environments. However, most existing VPR datasets are limited to single-viewpoint scenarios, leading to reduced recognition accuracy, particularly in multi-directional driving or feature-sparse scenes. Moreover, obtaining additional data to mitigate these limitations is often expensive. This paper introduces a novel training paradigm to improve the performance of existing VPR networks by enhancing multi-view diversity within current datasets through uncertainty estimation and NeRF-based data augmentation. Specifically, we initially train NeRF using the existing VPR dataset. Then, our devised self-supervised uncertainty estimation network identifies places with high uncertainty. The poses of these uncertain places are input into NeRF to generate new synthetic observations for further training of VPR networks. Additionally, we propose an improved storage method for efficient organization of augmented and original training data. We conducted extensive experiments on three datasets and tested three different VPR backbone networks. The results demonstrate that our proposed training paradigm significantly improves VPR performance by fully utilizing existing data, outperforming other training approaches. We further validated the effectiveness of our approach on self-recorded indoor and outdoor datasets, consistently demonstrating superior results. Our dataset and code have been released at \href{https://github.com/nubot-nudt/UGNA-VPR}{https://github.com/nubot-nudt/UGNA-VPR}.

cs.CV↗

arXiv2025

Fantastic Copyrighted Beasts and How (Not) to Generate Them

Recent studies show that image and video generation models can be prompted to reproduce copyrighted content from their training data, raising serious legal concerns about copyright infringement. Copyrighted characters (e.g., Mario, Batman) present a significant challenge: at least one lawsuit has already awarded damages based on the generation of such characters. Consequently, commercial services like DALL-E have started deploying interventions. However, little research has systematically examined these problems: (1) Can users easily prompt models to generate copyrighted characters, even if it is unintentional?; (2) How effective are the existing mitigation strategies? To address these questions, we introduce a novel evaluation framework with metrics that assess both the generated image's similarity to copyrighted characters and its consistency with user intent, grounded in a set of popular copyrighted characters from diverse studios and regions. We show that state-of-the-art image and video generation models can still generate characters even if characters' names are not explicitly mentioned, sometimes with only two generic keywords (e.g., prompting with "videogame, plumber" consistently generates Nintendo's Mario character). We also introduce semi-automatic techniques to identify such keywords or descriptions that trigger character generation. Using this framework, we evaluate mitigation strategies, including prompt rewriting and new approaches we propose. Our findings reveal that common methods, such as DALL-E's prompt rewriting, are insufficient alone and require supplementary strategies like negative prompting. Our work provides empirical grounding for discussions on copyright mitigation strategies and offers actionable insights for model deployers implementing these safeguards.

cs.CV↗

arXiv2025

EVolSplat: Efficient Volume-based Gaussian Splatting for Urban View Synthesis

Novel view synthesis of urban scenes is essential for autonomous driving-related applications.Existing NeRF and 3DGS-based methods show promising results in achieving photorealistic renderings but require slow, per-scene optimization. We introduce EVolSplat, an efficient 3D Gaussian Splatting model for urban scenes that works in a feed-forward manner. Unlike existing feed-forward, pixel-aligned 3DGS methods, which often suffer from issues like multi-view inconsistencies and duplicated content, our approach predicts 3D Gaussians across multiple frames within a unified volume using a 3D convolutional network. This is achieved by initializing 3D Gaussians with noisy depth predictions, and then refining their geometric properties in 3D space and predicting color based on 2D textures. Our model also handles distant views and the sky with a flexible hemisphere background model. This enables us to perform fast, feed-forward reconstruction while achieving real-time rendering. Experimental evaluations on the KITTI-360 and Waymo datasets show that our method achieves state-of-the-art quality compared to existing feed-forward 3DGS- and NeRF-based methods.

cs.CV↗

arXiv2025

CarPlanner: Consistent Auto-regressive Trajectory Planning for Large-scale Reinforcement Learning in Autonomous Driving

Trajectory planning is vital for autonomous driving, ensuring safe and efficient navigation in complex environments. While recent learning-based methods, particularly reinforcement learning (RL), have shown promise in specific scenarios, RL planners struggle with training inefficiencies and managing large-scale, real-world driving scenarios. In this paper, we introduce \textbf{CarPlanner}, a \textbf{C}onsistent \textbf{a}uto-\textbf{r}egressive \textbf{Planner} that uses RL to generate multi-modal trajectories. The auto-regressive structure enables efficient large-scale RL training, while the incorporation of consistency ensures stable policy learning by maintaining coherent temporal consistency across time steps. Moreover, CarPlanner employs a generation-selection framework with an expert-guided reward function and an invariant-view module, simplifying RL training and enhancing policy performance. Extensive analysis demonstrates that our proposed RL framework effectively addresses the challenges of training efficiency and performance enhancement, positioning CarPlanner as a promising solution for trajectory planning in autonomous driving. To the best of our knowledge, we are the first to demonstrate that the RL-based planner can surpass both IL- and rule-based state-of-the-arts (SOTAs) on the challenging large-scale real-world dataset nuPlan. Our proposed CarPlanner surpasses RL-, IL-, and rule-based SOTA approaches within this demanding dataset.

cs.RO↗