arXiv subjects

Yu Deng

Publications and source records attributed to Yu Deng.

At least 55 records · Page 3Linked to original sources

arXiv2025

Scalable Vision-Language-Action Model Pretraining for Robotic Manipulation with Real-Life Human Activity Videos

This paper presents a novel approach for pretraining robotic manipulation Vision-Language-Action (VLA) models using a large corpus of unscripted real-life video recordings of human hand activities. Treating human hand as dexterous robot end-effector, we show that "in-the-wild" egocentric human videos without any annotations can be transformed into data formats fully aligned with existing robotic V-L-A training data in terms of task granularity and labels. This is achieved by the development of a fully-automated holistic human activity analysis approach for arbitrary human hand videos. This approach can generate atomic-level hand activity segments and their language descriptions, each accompanied with framewise 3D hand motion and camera motion. We process a large volume of egocentric videos and create a hand-VLA training dataset containing 1M episodes and 26M frames. This training data covers a wide range of objects and concepts, dexterous manipulation tasks, and environment variations in real life, vastly exceeding the coverage of existing robot data. We design a dexterous hand VLA model architecture and pretrain the model on this dataset. The model exhibits strong zero-shot capabilities on completely unseen real-world observations. Additionally, fine-tuning it on a small amount of real robot action data significantly improves task success rates and generalization to novel objects in real robotic experiments. We also demonstrate the appealing scaling behavior of the model's task performance with respect to pretraining data scale. We believe this work lays a solid foundation for scalable VLA pretraining, advancing robots toward truly generalizable embodied intelligence.

cs.RO↗

arXiv2025

Understanding the atomically precise evolution of the miscibility of newly prepared face-centered cubic W-Cu nanoalloys and its asymmetry

According to classical Miedema theory, reducing crystals to the order of nanometer sizes might greatly modulate the mixing enthalpy of elements, thus enabling the invention of a lot of new bulk-immiscible alloys. Although numerous alloys with higher mixing enthalpies remain unexplored, this strategy is approaching its limit, as reflected by the critical diameter of recent alloys of 1.8 nm, which corresponds to ~150 atoms and hardly provides a crystalline order. Future development requires not only even smaller atomic-scale control but also a new surface energy-saving mechanism. Here, we report the formation of W-Cu nanoalloys with a very large miscibility gap in the bulk via the use of an atomically size-selected cluster beam source as an example. The face-centered cubic (FCC) structure was demonstrated through electron diffraction, which indicated a lattice constant of 3.88Å for W0.85Cu0.15 nanoalloys (~2280 atoms). In this comprehensive study that covers a large parameter space of W/Cu compositions and numbers of atoms, an asymmetric miscibility nanophase diagram in which W-rich compositions favor mixing and the critical size is approximately 6000 atoms, which far exceeds the approximately tens of atoms predicted via classical theory, was obtained for the first time. Density functional theory (DFT) calculations revealed a mutual strain-induced mechanism that simultaneously lowers the surface energies while reducing the size to the atomic scale. This approach paves the way for the development of new high-performance nonequilibrium phase alloys.

cond-mat.mtrl-sci↗

arXiv2025

Long time derivation of the Boltzmann equation from hard sphere dynamics

We provide a rigorous derivation of Boltzmann's kinetic equation from the hard sphere system for rarefied gas, which is valid for arbitrarily long times, as long as the solution to the Boltzmann equation exists. This extends Lanford's landmark theorem (1975), which justifies this derivation for a sufficiently short time. In a companion paper (arXiv:2503.01800), we connect this derivation to existing literature on hydrodynamic limits. This completes the resolution of Hilbert's Sixth Problem pertaining to the derivation of fluid equations from Newton's laws, in the case of a rarefied, hard sphere gas. The general strategy follows the paradigm introduced by the first two authors for the long-time derivation of the wave kinetic equation in wave turbulence theory. This is based on propagating a long-time cumulant ansatz, which keeps memory of the full collision history of the relevant particles, by an important partial time expansion. The heart of the matter is proving the smallness of these cumulants in $L^1$, which can be reduced to combinatorial properties for the associated diagrams which we call molecules. These properties are then proved by devising an elaborate cutting algorithm, which is a major novelty of this work.

math.AP↗

arXiv2025

MoGe-2: Accurate Monocular Geometry with Metric Scale and Sharp Details

We propose MoGe-2, an advanced open-domain geometry estimation model that recovers a metric scale 3D point map of a scene from a single image. Our method builds upon the recent monocular geometry estimation approach, MoGe, which predicts affine-invariant point maps with unknown scales. We explore effective strategies to extend MoGe for metric geometry prediction without compromising the relative geometry accuracy provided by the affine-invariant point representation. Additionally, we discover that noise and errors in real data diminish fine-grained detail in the predicted geometry. We address this by developing a unified data refinement approach that filters and completes real data from different sources using sharp synthetic labels, significantly enhancing the granularity of the reconstructed geometry while maintaining the overall accuracy. We train our model on a large corpus of mixed datasets and conducted comprehensive evaluations, demonstrating its superior performance in achieving accurate relative geometry, precise metric scale, and fine-grained detail recovery -- capabilities that no previous methods have simultaneously achieved.

cs.CV↗

arXiv2025

Brain Imaging Foundation Models, Are We There Yet? A Systematic Review of Foundation Models for Brain Imaging and Biomedical Research

Foundation models (FMs), large neural networks pretrained on extensive and diverse datasets, have revolutionized artificial intelligence and shown significant promise in medical imaging by enabling robust performance with limited labeled data. Although numerous surveys have reviewed the application of FM in healthcare care, brain imaging remains underrepresented, despite its critical role in the diagnosis and treatment of neurological diseases using modalities such as MRI, CT, and PET. Existing reviews either marginalize brain imaging or lack depth on the unique challenges and requirements of FM in this domain, such as multimodal data integration, support for diverse clinical tasks, and handling of heterogeneous, fragmented datasets. To address this gap, we present the first comprehensive and curated review of FMs for brain imaging. We systematically analyze 161 brain imaging datasets and 86 FM architectures, providing information on key design choices, training paradigms, and optimizations driving recent advances. Our review highlights the leading models for various brain imaging tasks, summarizes their innovations, and critically examines current limitations and blind spots in the literature. We conclude by outlining future research directions to advance FM applications in brain imaging, with the aim of fostering progress in both clinical and research settings.

eess.IV↗

arXiv2025

Estimands for Randomized Discontinuation Designs in Oncology

Randomized discontinuation design (RDD) is an enrichment strategy commonly used to address limitations of traditional placebo-controlled trials, particularly the ethical concern of prolonged placebo exposure. RDD consists of two phases: an initial open-label phase in which all eligible patients receive the investigational medicinal product (IMP), followed by a double-blind phase in which responders are randomized to continue with the IMP or switch to placebo. This design tests whether the IMP provides benefit beyond the placebo effect. The estimand framework introduced in ICH E9(R1) strengthens the dialogue among clinical research stakeholders by clarifying trial objectives and aligning them with appropriate statistical analyses. However, its application in oncology trials using RDD remains unclear. This manuscript uses the phase III JAVELIN Gastric 100 trial and the phase II trial of sorafenib (BAY 43-9006) as case studies to propose an estimand framework tailored for oncology trials employing RDD in phase III and phase II settings, respectively. We highlight some similarities and differences between RDDs and traditional randomized controlled trials in the context of ICH E9(R1). This approach aims to support more efficient regulatory decision-making.

stat.ME↗

arXiv2025

Structured 3D Latents for Scalable and Versatile 3D Generation

We introduce a novel 3D generation method for versatile and high-quality 3D asset creation. The cornerstone is a unified Structured LATent (SLAT) representation which allows decoding to different output formats, such as Radiance Fields, 3D Gaussians, and meshes. This is achieved by integrating a sparsely-populated 3D grid with dense multiview visual features extracted from a powerful vision foundation model, comprehensively capturing both structural (geometry) and textural (appearance) information while maintaining flexibility during decoding. We employ rectified flow transformers tailored for SLAT as our 3D generation models and train models with up to 2 billion parameters on a large 3D asset dataset of 500K diverse objects. Our model generates high-quality results with text or image conditions, significantly surpassing existing methods, including recent ones at similar scales. We showcase flexible output format selection and local 3D editing capabilities which were not offered by previous models. Code, model, and data will be released.

cs.CV↗

arXiv2025

Cardiac Digital Twins at Scale from MRI: Open Tools and Representative Models from ~55000 UK Biobank Participants

A cardiac digital twin is a virtual replica of a patient's heart for screening, diagnosis, prognosis, risk assessment, and treatment planning of cardiovascular diseases. This requires an anatomically accurate patient-specific 3D structural representation of the heart, suitable for electro-mechanical simulations or study of disease mechanisms. However, generation of cardiac digital twins at scale is demanding and there are no public repositories of models across demographic groups. We describe an automatic open-source pipeline for creating patient-specific left and right ventricular meshes from cardiovascular magnetic resonance images, its application to a large cohort of ~55000 participants from UK Biobank, and the construction of the most comprehensive cohort of adult heart models to date, comprising 1423 representative meshes across sex (male, female), body mass index (range: 16 - 42 kg/m$^2$) and age (range: 49 - 80 years). Our code is available at https://github.com/cdttk/biv-volumetric-meshing/tree/plos2025 , and pre-trained networks, representative volumetric meshes with fibers and UVCs will be made available soon.

eess.IV↗

arXiv2025

Deteriorated Interlayer Coupling in Twisted Bilayer Cobaltites

A wealth of remarkable behaviors is observed at the interfaces between magnetic oxides due to the coexistence of Coulomb repulsion and interatomic exchange interactions. While previous research has focused on bonded oxide heterointerfaces, studies on magnetism in van der Waals interfaces remain rare. In this study, we stacked two freestanding cobaltites with precisely controlled twist angles. Scanning transmission electron microscopy revealed clear and ordered moiré patterns, which exhibit an inverse relationship with the twist angle. We found that the Curie temperature in the twisted region is reduced by approximately 13 K compared to the single-layer region using nitrogen-vacancy (NV) magnetometry. This phenomenon may be related to the weakening of the orbital hybridization between oxygen ions and transition metal ions in the unbonded interfaces. Our findings suggest a potential avenue for modulating magnetic interactions in correlated systems through twist, providing opportunities for the discovery of unknown quantum states.

cond-mat.mtrl-sci↗

arXiv2025

On the wave turbulence theory of 2D gravity waves, I: deterministic energy estimates

Our goal in this paper is to initiate the rigorous investigation of wave turbulence and derivation of wave kinetic equations (WKE) for water waves models. This problem has received intense attention in recent years in the context of semilinear models, such as semilinear Schrödinger equations or multi-dimensional KdV-type equations. However, our situation here is different since the water waves equations are quasilinear and the solutions cannot be constructed by iteration of the Duhamel formula due to unavoidable derivative loss. This is the first of two papers in which we design a new strategy to address this issue, in the context of 2D gravity waves.

math.AP↗

arXiv2025

On the wave turbulence theory of 2D gravity waves, II: propagation of randomness

This is the second part of our work initiating the rigorous study of wave turbulence for water waves equations. We combine energy estimates, normal forms, and probabilistic and combinatorial arguments to complete the construction of long-time solutions with random initial data for the 2d (1d interface) gravity water waves system on large tori. This is the first long-time regularity result for solutions of water waves systems with large energy (but small local energy), which is the correct setup for applications to wave turbulence. Such a result is only possible in the presence of randomness.

math.AP↗

arXiv2025

MoGe: Unlocking Accurate Monocular Geometry Estimation for Open-Domain Images with Optimal Training Supervision

We present MoGe, a powerful model for recovering 3D geometry from monocular open-domain images. Given a single image, our model directly predicts a 3D point map of the captured scene with an affine-invariant representation, which is agnostic to true global scale and shift. This new representation precludes ambiguous supervision in training and facilitate effective geometry learning. Furthermore, we propose a set of novel global and local geometry supervisions that empower the model to learn high-quality geometry. These include a robust, optimal, and efficient point cloud alignment solver for accurate global shape learning, and a multi-scale local geometry loss promoting precise local geometry supervision. We train our model on a large, mixed dataset and demonstrate its strong generalizability and high accuracy. In our comprehensive evaluation on diverse unseen datasets, our model significantly outperforms state-of-the-art methods across all tasks, including monocular estimation of 3D point map, depth map, and camera field of view. Code and models can be found on our project page.

cs.CV↗

arXiv2025

Hilbert's sixth problem: derivation of fluid equations via Boltzmann's kinetic theory

In this paper, we rigorously derive the fundamental PDEs of fluid mechanics, such as the compressible Euler and incompressible Navier-Stokes-Fourier equations, starting from the hard sphere particle systems undergoing elastic collisions. This resolves Hilbert's sixth problem, as it pertains to the program of deriving the fluid equations from Newton's laws by way of Boltzmann's kinetic theory. The proof relies on the derivation of Boltzmann's equation on 2D and 3D tori, which is an extension of our previous work (arXiv:2408.07818).

math.AP↗

arXiv2025

ITBench: Evaluating AI Agents across Diverse Real-World IT Automation Tasks

Realizing the vision of using AI agents to automate critical IT tasks depends on the ability to measure and understand effectiveness of proposed solutions. We introduce ITBench, a framework that offers a systematic methodology for benchmarking AI agents to address real-world IT automation tasks. Our initial release targets three key areas: Site Reliability Engineering (SRE), Compliance and Security Operations (CISO), and Financial Operations (FinOps). The design enables AI researchers to understand the challenges and opportunities of AI agents for IT automation with push-button workflows and interpretable metrics. ITBench includes an initial set of 94 real-world scenarios, which can be easily extended by community contributions. Our results show that agents powered by state-of-the-art models resolve only 13.8% of SRE scenarios, 25.2% of CISO scenarios, and 0% of FinOps scenarios. We expect ITBench to be a key enabler of AI-driven IT automation that is correct, safe, and fast.

cs.AI↗

arXiv2024

High-temperature Phonon Coherence and Tunneling Effect in Semiconductor Superlattices

Phonons, the quanta of lattice vibrations, are primary heat carriers for semiconductors and dielectrics. The demand of effective phonon manipulation urgently emerges, because the thermal management is crucial for the ongoing development of micro/nano semiconductor devices towards higher integration and power densities1, 2. Phonons also show wave-particle duality, while they are commonly treated as particle flows in current semiconductor structures3, 4. However, it sees constraints when the structure size reduces to nano and atomic scales, where the wave behavior of phonons begins to dominate, and studies of these phonon behaviors and their manipulations become long-standing challenges in experiments5. Here we show the experimental realization of coherent phonon transport, a wave-based thermal conduction fashion, in semiconductor structures. We report the successful observation of robust phonon coherence and tunneling effect in InAs/AlAs superlattices over an extensive temperature range up to 500 K, a breakthrough towards practical-application temperature for semiconductors compared with cryogenic conditions6. Our results demonstrate that the phonon coherence is robust even at a record-high interface density due to the dominating long-wavelength phonons, and the first-principles calculations clearly reveal their wave-particle duality. This revelation heralds a promising pathway towards efficient thermal phonon engineering at extreme scales, holding implications for a broad spectrum of semiconductor device applications, including microelectronics, optoelectronics, and thermoelectrics.

cond-mat.mtrl-sci↗

arXiv2024

CogACT: A Foundational Vision-Language-Action Model for Synergizing Cognition and Action in Robotic Manipulation

The advancement of large Vision-Language-Action (VLA) models has significantly improved robotic manipulation in terms of language-guided task execution and generalization to unseen scenarios. While existing VLAs adapted from pretrained large Vision-Language-Models (VLM) have demonstrated promising generalizability, their task performance is still unsatisfactory as indicated by the low tasks success rates in different environments. In this paper, we present a new advanced VLA architecture derived from VLM. Unlike previous works that directly repurpose VLM for action prediction by simple action quantization, we propose a omponentized VLA architecture that has a specialized action module conditioned on VLM output. We systematically study the design of the action module and demonstrates the strong performance enhancement with diffusion action transformers for action sequence modeling, as well as their favorable scaling behaviors. We also conduct comprehensive experiments and ablation studies to evaluate the efficacy of our models with varied designs. The evaluation on 5 robot embodiments in simulation and real work shows that our model not only significantly surpasses existing VLAs in task performance and but also exhibits remarkable adaptation to new robots and generalization to unseen objects and backgrounds. It exceeds the average success rates of OpenVLA which has similar model size (7B) with ours by over 35% in simulated evaluation and 55% in real robot experiments. It also outperforms the large RT-2-X model (55B) by 18% absolute success rates in simulation. Code and models can be found on our project page (https://cogact.github.io/).

cs.RO↗

arXiv2024

SuperPose: Improved 6D Pose Estimation with Robust Tracking and Mask-Free Initialization

We developed a robust solution for real-time 6D object detection in industrial applications by integrating FoundationPose, SAM2, and LightGlue, eliminating the need for retraining. Our approach addresses two key challenges: the requirement for an initial object mask in the first frame in FoundationPose and issues with tracking loss and automatic rotation for symmetric objects. The algorithm requires only a CAD model of the target object, with the user clicking on its location in the live feed during the initial setup. Once set, the algorithm automatically saves a reference image of the object and, in subsequent runs, employs LightGlue for feature matching between the object and the real-time scene, providing an initial prompt for detection. Tested on the YCB dataset and industrial components such as bleach cleanser and gears, the algorithm demonstrated reliable 6D detection and tracking. By integrating SAM2 and FoundationPose, we effectively mitigated common limitations such as the problem of tracking loss, ensuring continuous and accurate tracking under challenging conditions like occlusion or rapid movement.

cs.CV↗

arXiv2024

Retrieval Augmented Generation-Based Incident Resolution Recommendation System for IT Support

Clients wishing to implement generative AI in the domain of IT Support and AIOps face two critical issues: domain coverage and model size constraints due to model choice limitations. Clients might choose to not use larger proprietary models such as GPT-4 due to cost and privacy concerns and so are limited to smaller models with potentially less domain coverage that do not generalize to the client's domain. Retrieval augmented generation is a common solution that addresses both of these issues: a retrieval system first retrieves the necessary domain knowledge which a smaller generative model leverages as context for generation. We present a system developed for a client in the IT Support domain for support case solution recommendation that combines retrieval augmented generation (RAG) for answer generation with an encoder-only model for classification and a generative large language model for query generation. We cover architecture details, data collection and annotation, development journey and preliminary validations, expected final deployment process and evaluation plans, and finally lessons learned.

cs.IR↗