arXiv subjects

Zhen Luo

Publications and source records attributed to Zhen Luo.

At least 19 recordsLinked to original sources

arXiv2026

DreamTraj: Generating 6-DoF Object Trajectories by Reading Unrendered Video Diffusion Latents

Accurate prediction of object trajectories during manipulation is essential for closing the perception-action loop. Progress is limited on two fronts: available datasets lack fine-grained language-to-motion annotations, and existing predictors either rely on privileged inputs such as video, depth, or CAD models, or recover motion from fully generated videos through costly, error-prone perception pipelines. We close the supervision gap with the MOVE dataset, 5,038 object-centric egocentric trajectories, each paired with a fine-grained natural-language instruction rather than a coarse verb-noun label. We further propose DreamTraj, which predicts a 6-DoF object trajectory from a single RGB image and a task instruction, requiring no video, depth, or CAD model at inference: rather than generating a video, it reads motion from the internal representations of a frozen image-to-video diffusion model at an early denoising step. A lightweight flow-matching Reader decodes query-key attention tracks and pooled hidden states into relative 6-DoF poses. To our knowledge, this is the first approach to directly decode object 6-DoF trajectories from intermediate video diffusion representations rather than generated pixels. DreamTraj sets a new state of the art on both translation and rotation against forecasters that consume multi-frame or privileged inputs, and runs 4.6x faster than generate-then-extract pipelines.

cs.CV↗

arXiv2026

A Versatile Analytical Model for Fast and Accurate Determination of Feedline-Coupled Resonators for Superconducting Qubit Readout

Superconducting quantum chips commonly utilize quarter-wavelength ({\lambda}/4) transmission line resonators as readout circuits. An analytical model for the accurate determination of resonance frequencies and coupling Q-factors of feedline-coupled superconducting resonators is introduced. The model leverages four-port microwave network analysis, integrating boundary conditions and conformal mapping techniques to compute even- and odd-mode impedances in edge-coupled coplanar waveguide (CPW) structures. Its versatility allows application to both planar and 3-D heterogeneous architectures, making it a powerful tool for resonator design. To validate the model, a test chip with {\lambda}/4 resonators of varying geometries is fabricated and measured in a cryogenic environment. Comparisons with finite element method (FEM) simulations and experimental measurements confirm the model's accuracy, with resonance frequencies and coupling Q-factors aligning closely across configurations. This proposed model facilitates the design of superconducting resonators in readout circuits for more effective, scalable, and adaptable quantum computing architectures.

quant-ph↗

arXiv2026

Code-as-Room: Generating 3D Rooms from Top-Down View Images via Agentic Code Synthesis

Designing realistic and functional 3D indoor rooms is essential for a wide range of applications, including interior design, virtual reality, gaming, and embodied AI. While recent MLLM-based approaches have shown great potential for 3D room synthesis from textual descriptions or reference images, text-based methods struggle to capture precise spatial information, and existing image-conditioned agents suffer from instability and infinite looping when tasked with holistic room generation from top-down views. To address these limitations, we propose Code-as-Room, an MLLM-based agentic framework equipped with a structured execution harness, which represents 3D rooms with Blender codes. Given a top-down room image, the framework parses the reference image to extract scene elements and their spatial relationships, and synthesizes executable Blender code for geometry, materials, and lighting in a principled, multi-stage pipeline. A cross-stage memory module is maintained throughout to mitigate context forgetting inherent to existing agent-based frameworks. We further introduce a dedicated benchmark for code-based 3D room synthesis, encompassing various evaluation protocols. Based on our benchmark, comprehensive comparisons against existing agent-based methods are conducted to validate the effectiveness of our proposed execution harness.

cs.CV↗

arXiv2026

STABLE: Simulation-Ready Tabletop Layout Generation via a Semantics-Physics Dual System

Generating simulation-ready tabletop scenes from task instructions is an intriguing and promising research direction in the field of Embodied AI. However, existing task-to-scene generation methods rely exclusively on large language models (LLMs) to predict scene layouts, inevitably yielding object collisions or floating due to LLMs' inherent limitations in 3D spatial reasoning. In this paper, we present STABLE, a semantics-physics dual-system tailored for simulation-ready tabletop scene generation. STABLE consists of two complementary modules: (i) a Semantic Reasoner, a fine-tuned LLM trained on a structured tabletop scene dataset to generate coarse layouts from input task instructions, and (ii) a Physics Corrector, a physics-aware flow-based denoising model that outputs pose updates to refine layouts, which ensures the physical plausibility of scenes while preserves semantic alignment with task instructions. STABLE adopts a progressive generation paradigm: by alternating between the Semantic Reasoner and Physics Corrector, it incrementally expands the scene from task-critical objects to background objects. Experiments demonstrate that STABLE successfully generates simulation-ready tabletop scenes that strictly conform to task instructions and significantly enhances the physical validity of scenes over prior art.

cs.CV↗

arXiv2026

A Compact Broadband Purcell Filter for Superconducting Quantum Circuits in a 3D Flip-Chip Architecture

Fast and high-fidelity qubit readout requires strong coupling between the readout resonator and the feedline. However, such coupling unavoidably enhances qubit decay through the Purcell effect. We present a four-pole broadband Purcell filter implemented on a 3D flip-chip platform to overcome this trade-off. The filter provides a flat 1 GHz passband centered at 7.68 GHz and achieves more than 45 dB suppression at typical qubit frequencies. We demonstrate the filter's compatibility with multiplexed readout using a test chip that integrates six floating readout resonators strongly coupled within the passband. The chip is fabricated using a 150 nm Niobium (Nb) thin-film process and characterized at 20 mK in a cryogenic measurement setup. We also develop an analytical model that accurately captures the filter response and determines the resonance frequencies and external quality factors of the floating resonators directly from their physical geometry, enabling rapid circuit synthesis and design optimization. The proposed design is compact and fabrication-tolerant, making it a practical solution for large-scale superconducting quantum processors.

quant-ph↗

arXiv2026

Bridging the Compression-Precision Paradox: A Hybrid Architecture for Clinical EEG Report Generation with Guaranteed Measurement Accuracy

Automated EEG monitoring requires clinician-level precision for seizure detection and reporting. Clinical EEG recordings exceed LLM context windows, requiring extreme compression (400:1+ ratios) that destroys fine-grained temporal precision. A 0.5 Hz error distinguishes absence epilepsy from Lennox-Gastaut syndrome. LLMs lack inherent time-series comprehension and rely on statistical associations from compressed representations. This dual limitation causes systems to hallucinate clinically incorrect measurement values. We separate measurement extraction from text generation. Our hybrid architecture computes exact clinical values via signal processing before compression, employs a cross-modal bridge for EEG-to-language translation, and uses parameter-efficient fine-tuning with constrained decoding around frozen slots. Multirate sampling maintains long-range context while preserving event-level precision. Evaluation on TUH and CHB-MIT datasets achieves 60% fewer false alarms, 50% faster detection, and sub-clinical measurement precision. This is the first system guaranteeing clinical measurement accuracy in automated EEG reports.

cs.LG↗

arXiv2026

UltraEval-Audio: A Unified Framework for Comprehensive Evaluation of Audio Foundation Models

The development of audio foundation models has accelerated rapidly since the emergence of GPT-4o. However, the lack of comprehensive evaluation has become a critical bottleneck for further progress in the field, particularly in audio generation. Current audio evaluation faces three major challenges: (1) audio evaluation lacks a unified framework, with datasets and code scattered across various sources, hindering fair and efficient cross-model comparison;(2) audio codecs, as a key component of audio foundation models, lack a widely accepted and holistic evaluation methodology; (3) existing speech benchmarks are heavily reliant on English, making it challenging to objectively assess models' performance on Chinese. To address the first issue, we introduce UltraEval-Audio, a unified evaluation framework for audio foundation models, specifically designed for both audio understanding and generation tasks. UltraEval-Audio features a modular architecture, supporting 10 languages and 14 core task categories, while seamlessly integrating 24 mainstream models and 36 authoritative benchmarks. To enhance research efficiency, the framework provides a one-command evaluation feature, accompanied by real-time public leaderboards. For the second challenge, UltraEval-Audio adopts a novel comprehensive evaluation scheme for audio codecs, evaluating performance across three key dimensions: semantic accuracy, timbre fidelity, and acoustic quality. To address the third issue, we propose two new Chinese benchmarks, SpeechCMMLU and SpeechHSK, designed to assess Chinese knowledge proficiency and language fluency. We wish that UltraEval-Audio will provide both academia and industry with a transparent, efficient, and fair platform for comparison of audio models. Our code, benchmarks, and leaderboards are available at https://github.com/OpenBMB/UltraEval-Audio.

cs.SD↗

arXiv2025

Stability studies on subtractively-fabricated CMOS-compatible superconducting transmon qubits

Developing fault-tolerant quantum processors with error correction demands large arrays of physical qubits whose key performance metrics (coherence times, control fidelities) must remain within specifications over both short and long timescales. Here we investigated the temporal stability of subtractively fabricated CMOS-compatible superconducting transmon qubits. During a single cooldown and over a period of 95 hours, we monitored several parameters for 8 qubits, including coherence times $T_1$ and $T_2^*$, which exhibit fluctuations originating primarily from the interaction between two-level system (TLS) defects and the host qubit. We also demonstrate that subtractively-fabricated superconducting quantum devices align with the theoretical predictions that higher mean lifetimes $T_1$ correspond to larger fluctuations. To assess long-term stability, we tracked two representative qubits over 10 cooldown cycles spanning more than one year. We observed an average total downward shift in both qubit transition frequencies of approximately 61 MHz within the thermal cycles considered. In contrast, readout resonator frequencies decreased only marginally. Meanwhile, $T_1$ exhibits fluctuations from cycle to cycle, but maintains a stable baseline value.

quant-ph↗

arXiv2025

ArtiWorld: LLM-Driven Articulation of 3D Objects in Scenes

Building interactive simulators and scalable robot-learning environments requires a large number of articulated assets. However, most existing 3D assets in simulation are rigid, and manually converting them into articulated objects is extremely labor- and cost-intensive. This raises a natural question: can we automatically identify articulable objects in a scene and convert them into articulated assets directly? In this paper, we present ArtiWorld, a scene-aware pipeline that localizes candidate articulable objects from textual scene descriptions and reconstructs executable URDF models that preserve the original geometry. At the core of this pipeline is Arti4URDF, which leverages 3D point cloud, prior knowledge of a large language model (LLM), and a URDF-oriented prompt design to rapidly convert rigid objects into interactive URDF-based articulated objects while maintaining their 3D shape. We evaluate ArtiWorld at three levels: 3D simulated objects, full 3D simulated scenes, and real-world scan scenes. Across all three settings, our method consistently outperforms existing approaches and achieves state-of-the-art performance, while preserving object geometry and correctly capturing object interactivity to produce usable URDF-based articulated models. This provides a practical path toward building interactive, robot-ready simulation environments directly from existing 3D assets. Code and data will be released.

cs.CV↗

arXiv2025

SemanticForge: Repository-Level Code Generation through Semantic Knowledge Graphs and Constraint Satisfaction

Large language models (LLMs) have transformed software development by enabling automated code generation, yet they frequently suffer from systematic errors that limit practical deployment. We identify two critical failure modes: \textit{logical hallucination} (incorrect control/data-flow reasoning) and \textit{schematic hallucination} (type mismatches, signature violations, and architectural inconsistencies). These errors stem from the absence of explicit, queryable representations of repository-wide semantics. This paper presents \textbf{SemanticForge}, which introduces four fundamental algorithmic advances for semantically-aware code generation: (1) a novel automatic reconciliation algorithm for dual static-dynamic knowledge graphs, unifying compile-time and runtime program semantics; (2) a neural approach that learns to generate structured graph queries from natural language, achieving 73\% precision versus 51\% for traditional retrieval; (3) a novel beam search algorithm with integrated SMT solving, enabling real-time constraint verification during generation rather than post-hoc validation; and (4) an incremental maintenance algorithm that updates knowledge graphs in $O(|\Delta R| \cdot \log n)$ time while maintaining semantic equivalence.

cs.SE↗

arXiv2025

MesaTask: Towards Task-Driven Tabletop Scene Generation via 3D Spatial Reasoning

The ability of robots to interpret human instructions and execute manipulation tasks necessitates the availability of task-relevant tabletop scenes for training. However, traditional methods for creating these scenes rely on time-consuming manual layout design or purely randomized layouts, which are limited in terms of plausibility or alignment with the tasks. In this paper, we formulate a novel task, namely task-oriented tabletop scene generation, which poses significant challenges due to the substantial gap between high-level task instructions and the tabletop scenes. To support research on such a challenging task, we introduce MesaTask-10K, a large-scale dataset comprising approximately 10,700 synthetic tabletop scenes with manually crafted layouts that ensure realistic layouts and intricate inter-object relations. To bridge the gap between tasks and scenes, we propose a Spatial Reasoning Chain that decomposes the generation process into object inference, spatial interrelation reasoning, and scene graph construction for the final 3D layout. We present MesaTask, an LLM-based framework that utilizes this reasoning chain and is further enhanced with DPO algorithms to generate physically plausible tabletop scenes that align well with given task descriptions. Exhaustive experiments demonstrate the superior performance of MesaTask compared to baselines in generating task-conforming tabletop scenes with realistic layouts. Project page is at https://mesatask.github.io/

cs.CV↗

arXiv2025

OptiScene: LLM-driven Indoor Scene Layout Generation via Scaled Human-aligned Data Synthesis and Multi-Stage Preference Optimization

Automatic indoor layout generation has attracted increasing attention due to its potential in interior design, virtual environment construction, and embodied AI. Existing methods fall into two categories: prompt-driven approaches that leverage proprietary LLM services (e.g., GPT APIs) and learning-based methods trained on layout data upon diffusion-based models. Prompt-driven methods often suffer from spatial inconsistency and high computational costs, while learning-based methods are typically constrained by coarse relational graphs and limited datasets, restricting their generalization to diverse room categories. In this paper, we revisit LLM-based indoor layout generation and present 3D-SynthPlace, a large-scale dataset that combines synthetic layouts generated via a 'GPT synthesize, Human inspect' pipeline, upgraded from the 3D-Front dataset. 3D-SynthPlace contains nearly 17,000 scenes, covering four common room types -- bedroom, living room, kitchen, and bathroom -- enriched with diverse objects and high-level spatial annotations. We further introduce OptiScene, a strong open-source LLM optimized for indoor layout generation, fine-tuned based on our 3D-SynthPlace dataset through our two-stage training. For the warum-up stage I, we adopt supervised fine-tuning (SFT), which is taught to first generate high-level spatial descriptions then conditionally predict concrete object placements. For the reinforcing stage II, to better align the generated layouts with human design preferences, we apply multi-turn direct preference optimization (DPO), which significantly improving layout quality and generation success rates. Extensive experiments demonstrate that OptiScene outperforms traditional prompt-driven and learning-based baselines. Moreover, OptiScene shows promising potential in interactive tasks such as scene editing and robot navigation.

cs.CV↗

arXiv2025

Wafer-Scale Characterization of Al/AlxOy/Al Josephson Junctions at Room Temperature

Josephson junctions (JJs) are the key element of many devices operating at cryogenic temperatures. Development of time-efficient wafer-scale JJ characterization for process optimization and control of JJ fabrication is essential. Such statistical characterization has to rely on room temperature techniques since cryogenic measurements typically used for JJs are too time consuming and unsuitable for wafer-scale characterization. In this work, we show that from room temperature capacitance and current-voltage measurements, with proper data analysis, we can independently obtain useful parameters of the JJs on wafer-scale, like oxide thickness, tunnel coefficient, and interfacial defect densities. Moreover, based on detailed analysis of current vs voltage characteristics, different charge transport mechanisms across the junctions can be distinguished. We exemplary demonstrate the worth of these methods by studying junctions fabricated on 200 mm wafers with an industrially scale-able concept based on subtractive processing using only CMOS compatible tools. From these studies, we find that our subtractive fabrication approach yields junctions with quite homogeneous average oxide thickness across the full wafers, with a spread of less then 3$\,$%. The analysis also revealed a variation of the tunnel coefficient with oxide thickness, pointing to a stoichiometry gradient across the junctions' oxide width. Moreover, we estimated relatively low interfacial defect densities in the range of 70 - 5000$\,$defects/cm$^2$ for our junctions and established that the density increased with decreasing oxide thickness, indicating that the wet etching process applied in the JJs fabrication for oxide thickness control leads to formation of interfacial trap state

quant-ph↗

arXiv2025

Boron-assisted synthesis of compositionally complex amorphous oxides via short-range-order-constrained generative design

Engineering short-range atomic order in amorphous materials offers a promising yet still underexplored route to high-performance solids. Here, we establish a boron-assisted amorphization strategy through ApolloX, a theory-guided, short-range-order-constrained generative framework for identifying low-energy amorphous configurations in compositionally complex multimetal BOx systems. Using FeCoNiMoBOx as a representative model platform, ApolloX predicts an ensemble of candidate amorphous configurations across systematically varied boron contents. Ab initio molecular dynamics simulations based on these configurations show that increasing boron content suppresses atomic diffusion and disfavors crystallization, with the stabilization of BO3-centered local motifs emerging as a key structural feature associated with enhanced amorphization propensity. Guided by these predictions, we synthesize three representative FeCoNiMoBOx compositions with distinct boron contents and use synchrotron-based scattering and electron microscopy to verify compositional fidelity, structural homogeneity, and the targeted amorphous features, thereby experimentally validating the boron-regulated structural evolution predicted by theory. Beyond this representative system, the same strategy is extended to a broader library of multimetal BOx amorphous compositions spanning diverse metal combinations and boron loadings, demonstrating that the boron-assisted route is not limited to a single FeCoNiMoBOx family but is broadly transferable across compositionally complex amorphous oxides. Overall, our results establish boron incorporation as a practical design variable for tuning short-range order and amorphization in multicomponent oxides, and provide a general framework for the theory-guided discovery of compositionally complex amorphous materials with tunable properties.

cond-mat.mtrl-sci↗

arXiv2025

RoboReflect: A Robotic Reflective Reasoning Framework for Grasping Ambiguous-Condition Objects

As robotic technology rapidly develops, robots are being employed in an increasing number of fields. However, due to the complexity of deployment environments or the prevalence of ambiguous-condition objects, the practical application of robotics still faces many challenges, leading to frequent errors. Traditional methods and some LLM-based approaches, although improved, still require substantial human intervention and struggle with autonomous error correction in complex scenarios. In this work, we propose RoboReflect, a novel framework leveraging large vision-language models (LVLMs) to enable self-reflection and autonomous error correction in robotic grasping tasks. RoboReflect allows robots to automatically adjust their strategies based on unsuccessful attempts until successful execution is achieved. The corrected strategies are saved in the memory for future task reference. We evaluate RoboReflect through extensive testing on eight common objects prone to ambiguous conditions of three categories. Our results demonstrate that RoboReflect not only outperforms existing grasp pose estimation methods like AnyGrasp and high-level action planning techniques ReKep with GPT-4V but also significantly enhances the robot's capability to adapt and correct errors independently. These findings underscore the critical importance of autonomous self-reflection in robotic systems while effectively addressing the challenges posed by ambiguous-condition environments.

cs.RO↗

arXiv2024

InfiniteWorld: A Unified Scalable Simulation Framework for General Visual-Language Robot Interaction

Realizing scaling laws in embodied AI has become a focus. However, previous work has been scattered across diverse simulation platforms, with assets and models lacking unified interfaces, which has led to inefficiencies in research. To address this, we introduce InfiniteWorld, a unified and scalable simulator for general vision-language robot interaction built on Nvidia Isaac Sim. InfiniteWorld encompasses a comprehensive set of physics asset construction methods and generalized free robot interaction benchmarks. Specifically, we first built a unified and scalable simulation framework for embodied learning that integrates a series of improvements in generation-driven 3D asset construction, Real2Sim, automated annotation framework, and unified 3D asset processing. This framework provides a unified and scalable platform for robot interaction and learning. In addition, to simulate realistic robot interaction, we build four new general benchmarks, including scene graph collaborative exploration and open-world social mobile manipulation. The former is often overlooked as an important task for robots to explore the environment and build scene knowledge, while the latter simulates robot interaction tasks with different levels of knowledge agents based on the former. They can more comprehensively evaluate the embodied agent's capabilities in environmental understanding, task planning and execution, and intelligent interaction. We hope that this work can provide the community with a systematic asset interface, alleviate the dilemma of the lack of high-quality assets, and provide a more comprehensive evaluation of robot interactions.

cs.RO↗

arXiv2024

LLplace: The 3D Indoor Scene Layout Generation and Editing via Large Language Model

Designing 3D indoor layouts is a crucial task with significant applications in virtual reality, interior design, and automated space planning. Existing methods for 3D layout design either rely on diffusion models, which utilize spatial relationship priors, or heavily leverage the inferential capabilities of proprietary Large Language Models (LLMs), which require extensive prompt engineering and in-context exemplars via black-box trials. These methods often face limitations in generalization and dynamic scene editing. In this paper, we introduce LLplace, a novel 3D indoor scene layout designer based on lightweight fine-tuned open-source LLM Llama3. LLplace circumvents the need for spatial relationship priors and in-context exemplars, enabling efficient and credible room layout generation based solely on user inputs specifying the room type and desired objects. We curated a new dialogue dataset based on the 3D-Front dataset, expanding the original data volume and incorporating dialogue data for adding and removing objects. This dataset can enhance the LLM's spatial understanding. Furthermore, through dialogue, LLplace activates the LLM's capability to understand 3D layouts and perform dynamic scene editing, enabling the addition and removal of objects. Our approach demonstrates that LLplace can effectively generate and edit 3D indoor layouts interactively and outperform existing methods in delivering high-quality 3D design solutions. Code and dataset will be released.

cs.CV↗

arXiv2024

Local existence of classical solution to the chemotaxis-shallow water system with vacuum in $\mathbb{R}^2$

In this paper, we consider the chemotaxis-shallow water system in $\mathbb{R}^2$. We establish the local existence of classical solution without assuming the initial height is small or has a small perturbation near a constant. The far field behavior of the height is a constant which could be either vacuum or non-vacuum. The initial data is allowed vacuum and the spatial measure of the set of vacuum can be arbitrarily large.

math.AP↗