Searcharxiv⌕ Search

arXiv subjects

Hao Zhang

Publications and source records attributed to Hao Zhang.

At least 181 records · Page 10Linked to original sources
arXiv2026

ProCUA-SFT Technical Report

Training computer-use agents (CUAs) -- models that interact with graphical desktops through screenshots and keyboard/mouse actions -- requires large-scale, diverse trajectory data collected in full desktop environments. The largest public resource, AgentNet (22.5K human trajectories), leads to negative transfer when used for supervised fine-tuning (SFT): continuing training UI-TARS 7B on AgentNet causes OSWorld success rate to fall from 26.3% to 8-10%. We present ProCUA-SFT, a dataset of 3.1M step-level SFT samples distilled from 93K synthetic trajectories across 2,484 application combinations. The dataset is produced by a fully automated pipeline that (i) synthesizes grounded tasks on live desktops seeded with real-world content -- 912 spreadsheets from SpreadsheetBench, approximately 10K permissively-licensed presentations from Zenodo10K, and multi-application OSWorld configs -- and (ii) verifies each task's feasibility through binary precondition checking before rollout. A single VLM (Kimi-K2.5) serves as goal generator, precondition judge, and trajectory executor, eliminating planner-actor capability gaps. Each trajectory is expanded into step-prefix samples that exactly reproduce the context layout seen at inference time. Fine-tuning UI-TARS 7B on ProCUA-SFT for one epoch yields 45.0% on OSWorld -- an 18.7 percentage-point improvement over the base model and over 35% above AgentNet-trained counterparts. A subset of ProCUA was incorporated into the training data for the Nemotron 3 Nano Omni model, contributing to its computer-use capabilities.

cs.LG↗
arXiv2026

Mutual Distillation of Dual-Foundation Models for Semi-Supervised PET/CT Segmentation

Organ segmentation from PET/CT is critical for quantitative analysis and radiotherapy planning in oncology. To ease the high annotation cost of PET/CT segmentation, semi-supervised learning (SSL) provides a practical and effective solution for developing deep models with limited labeled data. Recent developments in visual foundation models have demonstrated remarkable adaptability with improved efficiency. In this work, we propose a mutual distillation framework that seamlessly exploits both structural and functional foundation models, which act as modality-specific generalists for distilling knowledge from structural CT and metabolic PET imaging. By bridging the gap between the task-specific precision of student models and the segmentation priors of generalist foundation models, we propose \textbf{MuDuo}, a mutual distillation framework that synergistically leverages SAM-Med3D for CT and SegAnyPET for PET to distill their knowledge into a lightweight student network. Our approach eliminates the need for manual prompts while maximizing the utility of unlabeled data for automatic segmentation, achieving state-of-the-art performance on the AutoPET dataset with only 5 labeled cases. Our source code is available at https://github.com/Wu-beining/MuDuo.

cs.CV↗
arXiv2026

Flex4DHuman: Flexible Multi-view Video Diffusion for 4D Human Reconstruction

We present Flex4DHuman, a multi-view video diffusion model that transforms a monocular or sparse multi-view video of a dynamic subject into synchronized dense multi-view videos using only relative camera-pose conditioning. Unlike prior human-centric methods that rely on skeletons, depth maps, normals, or rendered target-view geometry, Flex4DHuman requires no explicit geometry priors and instead conditions generation through relative camera-pose positional encoding. The generated videos can be directly ingested by downstream reconstruction pipelines to create dynamic 4D Gaussian splats. Built on the Wan 2.1 1.3B text-to-video model, Flex4DHuman preserves the backbone architecture and encodes camera and view information through a five-axis positional encoding that extends spatio-temporal RoPE with view indices and continuous SE(3) relative camera geometry. A three-stage curriculum progressively trains the model for pose following, flexible reference-to-target view generation, and temporal rollout. To support temporal rollout, we train with clean historical target-view tokens. We also add multi-view captions to enable test-time text control. Combined with an off-the-shelf 4D Gaussian Splatting stage, our framework lifts monocular static-camera videos into dynamic 4D Gaussian splats. Experiments on DNA-Rendering and ActorsHQ show that Flex4DHuman surpasses prior state-of-the-art methods, while the same formulation generalizes to animal categories after mixed human-animal training. These capabilities make Flex4DHuman a practical step toward scalable 4D content creation from casual monocular videos for simulation, gaming, AR/VR, and video re-shooting.

cs.CV↗
arXiv2026

GeoStream: Toward Precise Camera Controlled Streaming Video Generation

Accurate interactive camera control is essential for video-based world models, but most existing approaches learn camera motion implicitly, leading to inaccurate control under out-of-distribution trajectories. Explicit geometric conditioning improves controllability, but existing methods are non-autoregressive and rely on a static 3D cache built from an initial frame, which becomes ineffective once the viewpoint moves beyond the original frustum. We propose GeoStream, a framework that enables precise metric-scale camera control in autoregressive streaming video generation. Our method maintains a self-refreshing 3D cache that is periodically updated online from the model's own outputs: we estimate depth from the most recently generated frame, unproject to 3D, and reproject into the target view to produce point reprojections as geometric conditioning for subsequent synthesis. By the same principle, the conditioning seen during training is also rendered from the student's own generated frames, yielding a fully on-policy distillation that naturally aligns the train and inference conditioning distributions. Unlike prior work that uses off-policy condition noising, our approach trains the model against the exact error distribution it encounters at inference, mitigating both standard autoregressive drift and the second-order geometric feedback loop that arises when the cache itself is derived from generated outputs. Quantitative and qualitative results show that our approach substantially improves camera controllability.

cs.CV↗
arXiv2026

GRAPE: Guided Parameter-Space Evolution for Compact Adversarial Robustness

Adversarial Training (AT) improves neural network robustness, but most methods train a fixed parameter space from the start. This paper asks whether the order in which parameters become optimizable can affect the final robust solution, even when the final architecture or computation budget is controlled. We propose GRAPE, Guided Parameter-Space Evolution, a training framework for compact adversarial robustness. GRAPE combines parameter-space stabilization with progressive hidden expansion: it stabilizes robust optimization in the currently exposed space, gradually releases new optimizable dimensions, and uses an adversarial spectral utilization score to guide newly released capacity toward high-pressure modules. In contrast to fixed-structure AT, GRAPE treats robust model learning as a process of progressive parameter-space exposure and evolution. Under the standard $\ell_\infty$ threat model on CIFAR-10, with fixed-structure ResNet-18 AT as a controlled reference, GRAPE improves PGD-20 robust accuracy from 51.70% to 56.94% at a nearly matched computation budget with a FLOPs ratio of 1.009x, while reducing parameter count by about 21.4%. A sequential grow variant with the same final ResNet-18 architecture reaches 56.52% PGD-20 robust accuracy, indicating that the gain is not only due to final architecture differences but also to the parameter-space exposure path. These results suggest that guided parameter-space evolution can yield compact and robust parameter configurations under matched computation.

cs.LG↗
arXiv2026

World Tracing: Generative Pixel-Aligned Geometry Beyond the Visible

Image-to-3D methods often trade off faithfulness and completeness: depth estimators are anchored to input pixels but stop at the visible surface, while image-to-3D models generate complete shapes that are often misaligned with the input. We introduce World Tracing, a generative pixel-aligned geometry representation that predicts 3D points aligned with observed pixels while completing geometry beyond the visible surface. For each input pixel, World Tracing predicts an ordered stack of camera-space 3D points, where the first layer represents the visible surface and subsequent layers represent front-to-back intersections with occluded surfaces. We instantiate this representation with a world-tracing diffusion transformer, WT-DiT, which treats multiple geometry layers as separate denoising tokens coupled through factorized and global attention. WT-DiT is trained with pixel-space flow matching and a mixed noise schedule that balances visible-surface reconstruction with occluded-geometry generation. World Tracing achieves strong performance on visible-surface reconstruction and complete geometry generation across object, scene, and dynamic benchmarks, outperforming both depth predictors and image-to-3D generators. It also preserves 2D-to-3D correspondence, enabling text-driven 3D scene editing, geometry-conditioned novel-view video synthesis, and training-free integration with textured-mesh generators.

cs.CV↗
arXiv2026

VL-DINO: Leveraging CLIP Vision-Language Knowledge for Open-Vocabulary Object Detectio

Vision-language models like CLIP can provide rich semantic priors for open-vocabulary object detection. However, jointly integrating both textual and visual knowledge into detection architectures remains challenging. In this paper, we propose VL-DINO, an open-vocabulary detector that enhances DINO through more effective exploitation of CLIP's vision-language knowledge. Specifically, a Query-guided Positive Sample Construction (QPSC) module is first developed to construct additional high-quality positive samples, enabling the vanilla DINO framework to better accommodate mixed training across heterogeneous data sources while providing more vision-language alignment signals, thereby incorporating richer textual knowledge during training. A Visual Semantic Encoder (VSE) module is then introduced to distill CLIP visual knowledge into backbone-extracted features, producing fused features for subsequent encoder refinement. Based on the fused features, an Object-Region Semantic Alignment (ORSA) module extracts object-centric region features and aligns them with the corresponding textual embeddings, further incorporating textual cues. In the zero-shot setting, VL-DINO-T and VL-DINO-L achieve 36.3 and 38.1 AP on the LVIS benchmark, respectively, consistently outperforming prior advanced approaches. Extensive experiments demonstrate the effectiveness and competitive performance of the proposed design.

cs.CV↗
arXiv2026

Learning high-dimensional quantum entanglement through physics-guided neural networks

High-gain spontaneous parametric down-conversion (SPDC) produces bright squeezed vacuum with rich high-dimensional entanglement, but its output is inherently multimodal and non-perturbative, making the full modal characterization a major computational bottleneck. We propose a physics-guided deep neural network that reconstructs the source's modal fingerprint: the high-dimensional correlation signature across radial and azimuthal indices. We designed a FiLM-modulated convolutional architecture that predicts the joint (m,l) distribution, and training is driven by a hybrid loss that couples data-driven metrics (JSD, KL, MSE, Wasserstein) with a soft orbital-angular-momentum (OAM) conservation term, providing an essential inductive bias toward physically consistent solutions. Across gain regimes, our method achieves high-fidelity reconstruction with average JSD of 1.96e-3, WEMD of 1.54e-3, and KL divergence of 7.85e-3, delivering an approximate 128-fold speedup over full numerical simulation and more than 30% accuracy gains over U-Net baselines. These results demonstrate that physics-guided learning, via a soft OAM-conservation regularizer and physically generated training targets, enables rapid and data-efficient modal characterization. Compared with traditional numerical simulation, our mesh-free method has demonstrated good generalization with limited or contaminated training data and has enabled fast "online" prediction of the quantum dynamics of a high-dimensional entanglement system for real-world experimental implementation.

quant-ph↗
arXiv2026

MaterialClusterGS: Palette-Based Material Decomposition and Physically-Based Relighting with 2D Gaussian Splatting

We present MaterialClusterGS, a palette-based material decomposition framework for 2D Gaussian Splatting that enables physically based relighting and material editing. Existing Gaussian inverse rendering methods typically assign independent BRDF parameters to individual primitives. While flexible, this local fitting strategy makes material recovery highly under-constrained: shadows, indirect illumination, geometric errors, and visibility residuals can be absorbed into thousands of slightly different local material estimates. Meanwhile, recent palette-based appearance methods operate solely in RGB space without modeling physical materials or illumination. To bridge this gap, we represent scene materials using a compact global palette of shared BRDF prototypes assigned via a continuous spatial material field. Without shared material structure, editing one region does not propagate consistently to others of the same material, making per-primitive decompositions impractical for editing. We jointly optimize the material field, palette prototypes, and environment lighting under a physically based rendering objective. The resulting framework recovers compact, spatially coherent attributes directly usable for material editing, relighting, and transfer.

cs.GR↗
arXiv2026

Wearable Single-Lead ECG Detects Fine-Grained Structural Heart Disease Through Echo-Report Supervision

Structural heart disease (SHD) is a primary driver of heart failure and cardiovascular mortality, yet early detection remains constrained by the limited accessibility of echocardiography. While single-lead electrocardiogram (ECG) is ubiquitous through wearables, existing AI screening models often depend on 12-lead inputs, generalize poorly across institutions, or require massive, condition-specific labeled datasets. Recent work has demonstrated the feasibility of contrastive pre-training between single-lead ECGs and echocardiography reports within a single health system. Here, we present AnyECG-Echo, a framework that advance this paradigm toward clinical translation through three key developments: (1) evaluation in a geographically independent external cohort (n = 16,621); (2) diagnostic coverage of 13 fine-grained SHD subtypes spanning myocardial, chamber, valvular, and great-vessel pathologies; and (3) dual-axis mechanistic interpretability combining electrophysiology-grounded Shapley attribution with emergent correlations to quantitative measurements. Across validation cohorts totaling n = 25,222, the model demonstrated high AUROC for high-impact subtypes, including reduced left ventricular systolic function (AUROC 0.866-0.924), global heart enlargement (0.877-0.931), and mitral stenosis (0.836-0.906). Furthermore, we successfully validated the alignment of model outputs with established medical physiological traits, thereby enhancing interpretability. Notably, we discovered that AnyECG-Echo's outputs function as physiologically grounded digital biomarkers that accurately track objective metrics such as LVEF and myocardial wall thickness. These findings prove that wearable single-lead ECGs can effectively detect fine-grained structural heart disease, offering a practical solution for population-scale screening.

eess.SP↗
arXiv2026

LLM-Enhanced Dialogue Management for Full-Duplex Spoken Dialogue Systems

Achieving full-duplex communication in spoken dialogue systems (SDS) requires real-time coordination between listening, speaking, and thinking. This paper proposes a semantic voice activity detection (VAD) module as a dialogue manager (DM) to efficiently manage turn-taking in full-duplex SDS. Implemented as a lightweight (0.5B) LLM fine-tuned on full-duplex conversation data, the semantic VAD predicts four control tokens to regulate turn-switching and turn-keeping, distinguishing between intentional and unintentional barge-ins while detecting query completion for handling user pauses and hesitations. By processing input speech in short intervals, the semantic VAD enables real-time decision-making, while the core dialogue engine (CDE) is only activated for response generation, reducing computational overhead. This design allows independent DM optimization without retraining the CDE, balancing interaction accuracy and inference efficiency for scalable, next-generation full-duplex SDS.

cs.CL↗
arXiv2026

Time series learning in a many-body Rydberg system with emergent collective amplification

Interacting Rydberg atoms constitute a versatile platform for the realization of non-equilibrium states of matter. Close to phase transitions, they respond collectively to external perturbations, which can be harnessed for technological applications in the domain of quantum metrology and sensing. Owing to the controllable complexity and straightforward interpretability of Rydberg atoms, we can observe and tune the emergent collective amplification. Here, we investigate the application of an interacting Rydberg vapour for the purpose of time series prediction. The vapour is driven by a laser field whose Rabi frequency is modulated in order to input the time series. We find that close to a non-equilibrium phase transition, where collective effects are amplified, the capability of the system to learn the input becomes enhanced. This is reflected in an increase of the accuracy with which future values of the time series can be predicted. Using the Lorenz time series and temperature data as examples, our work demonstrates how emergent phenomena enhance the capability of noisy many-body systems for data processing and forecasting.

quant-ph↗
arXiv2026

AutoLab: Can Frontier Models Solve Long-Horizon Auto Research and Engineering Tasks?

Scientific and engineering progress is fundamentally a long-horizon iterative process: proposing changes, running experiments, measuring outcomes, and continuously refining artifacts. Yet existing benchmarks for frontier models primarily evaluate either single-turn responses or short-horizon agent trajectories, failing to capture the challenges of sustained iterative improvement over extended time horizons. To address this gap, we introduce AutoLab, a new benchmark for ultra long-horizon closed-loop optimization. AutoLab consists of 36 realistic, expert-curated tasks spanning four diverse domains: system optimization, puzzle & challenge, model development, and CUDA kernel optimization. Each task begins with a correct but deliberately suboptimal baseline and challenges agents to improve it within a strict wall-clock budget. Evaluating 17 state-of-the-art models reveals the dominant predictor of success is not the quality of an agent's initial attempt, but its persistence in repeatedly benchmarking, editing, and incorporating empirical feedback. While claude-opus-4.6 exhibits strong long-horizon optimization capabilities, most frontier models, including several proprietary ones, either terminate prematurely or exhaust their budgets with minimal progress. These results underscore the importance of time awareness and persistent iteration in autonomous agents. We open-source the full benchmark, evaluation harness, and task artifacts, to accelerate research toward truly capable long-horizon agents.

cs.AI↗
arXiv2026

CREward: A Type-Specific Creativity Reward Model

Creativity is a complex phenomenon. When it comes to representing and assessing creativity, treating it as a single undifferentiated quantity would appear naive and underwhelming. In this work, we learn the \emph{first type-specific creativity reward model}, coined CREward, which spans three creativity ``axes," geometry, material, and texture, to allow us to view creativity through the lens of the image formation pipeline. To build our reward model, we first conduct a human benchmark evaluation to capture human perception of creativity for each type across various creative images. We then analyze the correlation between human judgments and predictions by large vision-language models (LVLMs), confirming that LVLMs exhibit strong alignment with human perception. Building on this observation, we collect LVLM-generated labels to train our CREward model that is applicable to both evaluation and generation of creative images. We explore three applications of CREward: creativity assessment, explainable creativity, and creative sample acquisition for both human design inspiration and guiding creative generation through low-rank adaptation.

cs.CV↗
arXiv2026

HALO: Learning Human-Robot Collaboration via Heterogeneous-Agent Lyapunov Policy Optimization

To improve generalization and resilience in human-robot collaboration (HRC), robots must contend with diverse combinations of human behaviors and contexts, motivating multi-agent reinforcement learning (MARL). However, inherent heterogeneity between robots and humans creates a rationality gap (RG), where decentralized policy updates deviate from cooperative joint optimization. The resulting learning problem is a general-sum differentiable game, so independent policy-gradient updates can oscillate or diverge without added structure. We propose heterogeneous-agent Lyapunov policy optimization (HALO), a framework that stabilizes decentralized MARL by enforcing Lyapunov-based contraction in policy-parameter space. Unlike Lyapunov-based safe RL, which targets state/trajectory constraints in constrained Markov decision processes, HALO uses Lyapunov certification to stabilize decentralized policy learning. HALO rectifies decentralized gradients via optimal quadratic projections, ensuring monotonic contraction of RG and enabling effective exploration of open-ended interaction spaces. Extensive simulations and real-world humanoid-robot experiments show that this certified stability improves generalization and robustness in collaborative corner cases. Our project website is available at https://HaoZhang-THU.github.io/HALO/.

cs.RO↗
arXiv2026

Function2Scene: 3D Indoor Scene Layout from Functional Specifications

Most text-driven 3D indoor scene synthesis methods generate rooms from object-centric prompts, asking what furniture should be placed rather than how the space is used. Yet in real interior design, a layout is judged by how well it supports its occupants, e.g., their activities and physical needs. We introduce Function2Scene, a framework for generating 3D indoor layouts from functional specifications, i.e., natural-language design briefs describing who will use a room and what they need to do there. Given such a specification, our system parses occupant personas and activities, derives a customized set of functional design constraints from a taxonomy of 17 criteria spanning spatial, ergonomic, activity, and environmental considerations, and uses these constraints to guide layout generation. Rather than relying on an LLM to directly produce a final scene, Function2Scene performs iterative evaluation and refinement through a tool-augmented check-and-repair loop, combining geometric measurements, LLM-based contextual reasoning, and VLM-based visual assessment. Experiments on 30 professionally written interior-design cases show that Function2Scene produces layouts that better satisfy functional requirements than recent LLM-based scene synthesis baselines, with our results preferred in 94.3% of pairwise comparisons. Our work reframes text-driven indoor scene synthesis from placing plausible objects to designing spaces that support human use.

cs.CV↗
arXiv2026

Advances in Neural 3D Mesh Texturing: A Survey

Texturing 3D meshes plays a vital role in determining the visual realism of digital objects and scenes. Although recent generative 3D approaches based on Neural Radiance Fields and Gaussian Splatting can produce textured assets directly, polygonal meshes remain the core representation across modeling, animation, visual effects, and gaming pipelines. Neural 3D mesh texturing therefore continues to be an essential and active area of research. In this survey, we present a comprehensive review of recent advances in neural 3D mesh texturing, covering methods for texture synthesis, transfer, and completion. We first summarize key foundations in mesh geometry, texture mapping, differentiable rendering, and neural generative models, and then organize the literature into a unified taxonomy spanning early GAN-based methods to modern diffusion-based pipelines. We further analyze common architectures and supervision strategies, review datasets and evaluation protocols, and discuss emerging applications, practical/commercial systems, and open challenges. Together, these insights provide a structured perspective on the current landscape and help guide future developments in learning-based 3D mesh texturing.

cs.CV↗
arXiv2026

Probability-Entropy Calibration: An Elastic Indicator for Adaptive Fine-tuning

Token-level reweighting is a simple yet effective mechanism for controlling supervised fine-tuning, but common indicators are largely one-dimensional: the ground-truth probability reflects downstream alignment, while token entropy reflects intrinsic uncertainty induced by the pre-training prior. Ignoring entropy can misidentify noisy or easily replaceable tokens as learning-critical, while ignoring probability fails to reflect target-specific alignment. RankTuner introduces a probability--entropy calibration signal, the Relative Rank Indicator, which compares the rank of the ground-truth token with its expected rank under the prediction distribution. The inverse indicator is used as a token-wise Relative Scale to reweight the fine-tuning objective, focusing updates on truly under-learned tokens without over-penalizing intrinsically uncertain positions. Experiments on multiple backbones show consistent improvements on mathematical reasoning benchmarks, transfer gains on out-of-distribution reasoning, and pre code generation performance over probability-only or entropy-only reweighting baselines.

cs.LG↗