arXiv subjects

Yiming Chen

Publications and source records attributed to Yiming Chen.

At least 73 records · Page 4Linked to original sources

arXiv2025

Scalable data-driven modeling of microstructure evolution by learning local dependency and spatiotemporal translation invariance rules in phase field simulation

Phase-field (PF) simulation provides a powerful framework for predicting microstructural evolution but suffers from prohibitive computational costs that severely limit accessible spatiotemporal scales in practical applications. While data-driven methods have emerged as promising approaches for accelerating PF simulations, existing methods require extensive training data from numerous evolution trajectories, and their inherent black-box nature raises concerns about long-term prediction reliability. This work demonstrates, through examples of grain growth and spinodal decomposition, that a minimalist Convolutional Neural Network (CNN) trained with a remarkably small dataset even from a single small-scale simulation can achieve seamless scalability to larger systems and reliable long-term predictions far beyond the temporal range of the training data. The key insight of this work lies in revealing that the success of CNN-based models stems from the alignment between their inductive biases and the physical priors of phase-field simulations specifically, locality and spatiotemporal translation invariance. Through effective receptive field analysis, we verify that the model captures these essential properties during training. Therefore, from a reductionist perspective, the surrogate model essentially establishes a spatiotemporally invariant regression mapping between a grid point's local environment and its subsequent state. Further analysis of the model's feature space demonstrates that microstructural evolution effectively represents a continuous redistribution of a finite set of local environments. When the model has already encountered nearly all possible local environments in the early-stage training data, it can reliably generalize to much longer evolution timescales, regardless of the dramatic changes in global microstructural morphology.

cond-mat.mtrl-sci↗

arXiv2025

Fortuity with a single matrix

We construct and study a supersymmetric quantum mechanical model with a single $U(N)$ adjoint fermionic matrix. The model is exactly solvable yet contains a large number of fortuitous states. We investigate these states exactly at finite $N$ and, in the large $N$ limit, via a unitary matrix model. In particular, we develop a way to "follow $N$" in the unitary matrix integral and study how the answer of the integral depends sensitively on the value of $N$.

hep-th↗

arXiv2025

Integrating Ergonomics and Manipulability for Upper Limb Postural Optimization in Bimanual Human-Robot Collaboration

This paper introduces an upper limb postural optimization method for enhancing physical ergonomics and force manipulability during bimanual human-robot co-carrying tasks. Existing research typically emphasizes human safety or manipulative efficiency, whereas our proposed method uniquely integrates both aspects to strengthen collaboration across diverse conditions (e.g., different grasping postures of humans, and different shapes of objects). Specifically, the joint angles of a simplified human skeleton model are optimized by minimizing the cost function to prioritize safety and manipulative capability. To guide humans towards the optimized posture, the reference end-effector poses of the robot are generated through a transformation module. A bimanual model predictive impedance controller (MPIC) is proposed for our human-like robot, CURI, to recalibrate the end effector poses through planned trajectories. The proposed method has been validated through various subjects and objects during human-human collaboration (HHC) and human-robot collaboration (HRC). The experimental results demonstrate significant improvement in muscle conditions by comparing the activation of target muscles before and after optimization.

cs.RO↗

arXiv2025

Chimera: Compositional Image Generation using Part-based Concepting

Personalized image generative models are highly proficient at synthesizing images from text or a single image, yet they lack explicit control for composing objects from specific parts of multiple source images without user specified masks or annotations. To address this, we introduce Chimera, a personalized image generation model that generates novel objects by combining specified parts from different source images according to textual instructions. To train our model, we first construct a dataset from a taxonomy built on 464 unique (part, subject) pairs, which we term semantic atoms. From this, we generate 37k prompts and synthesize the corresponding images with a high-fidelity text-to-image model. We train a custom diffusion prior model with part-conditional guidance, which steers the image-conditioning features to enforce both semantic identity and spatial layout. We also introduce an objective metric PartEval to assess the fidelity and compositional accuracy of generation pipelines. Human evaluations and our proposed metric show that Chimera outperforms other baselines by 14% in part alignment and compositional accuracy and 21% in visual quality.

cs.CV↗

arXiv2025

Advancing Complex Wide-Area Scene Understanding with Hierarchical Coresets Selection

Scene understanding is one of the core tasks in computer vision, aiming to extract semantic information from images to identify objects, scene categories, and their interrelationships. Although advancements in Vision-Language Models (VLMs) have driven progress in this field, existing VLMs still face challenges in adaptation to unseen complex wide-area scenes. To address the challenges, this paper proposes a Hierarchical Coresets Selection (HCS) mechanism to advance the adaptation of VLMs in complex wide-area scene understanding. It progressively refines the selected regions based on the proposed theoretically guaranteed importance function, which considers utility, representativeness, robustness, and synergy. Without requiring additional fine-tuning, HCS enables VLMs to achieve rapid understandings of unseen scenes at any scale using minimal interpretable regions while mitigating insufficient feature density. HCS is a plug-and-play method that is compatible with any VLM. Experiments demonstrate that HCS achieves superior performance and universality in various tasks.

cs.CV↗

arXiv2025

Reasoning in Space via Grounding in the World

In this paper, we claim that 3D visual grounding is the cornerstone of spatial reasoning and introduce the Grounded-Spatial Reasoner (GS-Reasoner) to explore the effective spatial representations that bridge the gap between them. Existing 3D LLMs suffer from the absence of a unified 3D representation capable of jointly capturing semantic and geometric information. This deficiency is manifested either in poor performance on grounding or in an excessive reliance on external modules, ultimately hindering the seamless integration of grounding and spatial reasoning. To address this, we propose a simple yet effective dual-path pooling mechanism that tightly aligns geometric features with both semantic and positional cues, constructing a unified image patch-based 3D representation that encapsulates all essential information without increasing the number of input tokens. Leveraging this holistic representation, GS-Reasoner is the first 3D LLM that achieves autoregressive grounding entirely without external modules while delivering performance comparable to state-of-the-art models, establishing a unified and self-contained framework for 3D spatial reasoning. To further bridge grounding and spatial reasoning, we introduce the Grounded Chain-of-Thought (GCoT) dataset. This dataset is meticulously curated to include both 3D bounding box annotations for objects referenced in reasoning questions and step-by-step reasoning paths that integrate grounding as a core component of the problem-solving process. Extensive experiments demonstrate that GS-Reasoner achieves impressive results on 3D visual grounding, which in turn significantly enhances its spatial reasoning capabilities, leading to state-of-the-art performance.

cs.CV↗

arXiv2025

Valuative Invariants of Catalan Matroids

We decompose the indicator function of each $(a, b)$-Catalan matroid polytope as a weighted sum of indicator function of matroid polytopes that correspond to direct sums of uniform matroids. Catalan matroids lie in the interior of the convex hull of direct sums of uniform matroids in the polytope of all matroids introduced by Ferroni and Fink. Moreover, we describe combinatorially the coefficients of the convex combination of direct sums of uniform matroid corresponding to an $(a,b)$-Catalan matroid. In particular, this allows us to derive explicit formulas for arbitrary valuative invariants of $(a, b)$-Catalan matroids. Among other applications, we prove that $(a,b)$-Catalan matroids are Ehrhart positive, and we find formulas for the Kazhdan--Lusztig invariants of these matroids.

math.CO↗

arXiv2025

Clink! Chop! Thud! -- Learning Object Sounds from Real-World Interactions

Can a model distinguish between the sound of a spoon hitting a hardwood floor versus a carpeted one? Everyday object interactions produce sounds unique to the objects involved. We introduce the sounding object detection task to evaluate a model's ability to link these sounds to the objects directly involved. Inspired by human perception, our multimodal object-aware framework learns from in-the-wild egocentric videos. To encourage an object-centric approach, we first develop an automatic pipeline to compute segmentation masks of the objects involved to guide the model's focus during training towards the most informative regions of the interaction. A slot attention visual encoder is used to further enforce an object prior. We demonstrate state of the art performance on our new task along with existing multimodal action understanding tasks.

cs.CV↗

arXiv2025

Search for Active and Inactive Ion Insertion Sites in Organic Crystalline Materials

The position of mobile active and inactive ions, specifically ion insertion sites, within organic crystals, significantly affects the properties of organic materials used for energy storage and ionic transport. Identifying the positions of these atom (and ion) sites in an organic crystal is difficult, especially when the element has a low X-ray scattering power, such as lithium (Li) and hydrogen, which are difficult to detect with powder X-ray diffraction (XRD) methods. First-principles calculations, exemplified by density functional theory (DFT), are very effective for confirming the relative stability of ion positions in materials. However, the lack of effective strategies to identify ion sites in these organic crystalline frameworks renders this task extremely challenging. This work presents two algorithms: (i) Efficient Location of Ion Insertion Sites from Extrema in electrostatic local potential and charge density (ELIISE), and (ii) ElectRostatic InsertioN (ERIN), which leverage charge density and electrostatic potential fields accessed from first-principles calculations, combined with the Simultaneous Ion Insertion and Evaluation (SIIE) workflow -- that inserts all ions simultaneously -- to determine ion positions in organic crystals. We demonstrate that these methods accurately reproduce known ion positions in 16 organic materials and also identify previously overlooked low-energy sites in tetralithium 2,6-naphthalenedicarboxylate (Li$_4$NDC), an organic electrode material, highlighting the importance of inserting all ions simultaneously as done in the SIIE workflow.

cond-mat.mtrl-sci↗

arXiv2025

Recent Advances in Large Langauge Model Benchmarks against Data Contamination: From Static to Dynamic Evaluation

Data contamination has received increasing attention in the era of large language models (LLMs) due to their reliance on vast Internet-derived training corpora. To mitigate the risk of potential data contamination, LLM benchmarking has undergone a transformation from static to dynamic benchmarking. In this work, we conduct an in-depth analysis of existing static to dynamic benchmarking methods aimed at reducing data contamination risks. We first examine methods that enhance static benchmarks and identify their inherent limitations. We then highlight a critical gap-the lack of standardized criteria for evaluating dynamic benchmarks. Based on this observation, we propose a series of optimal design principles for dynamic benchmarking and analyze the limitations of existing dynamic benchmarks. This survey provides a concise yet comprehensive overview of recent advancements in data contamination research, offering valuable insights and a clear guide for future research efforts. We maintain a GitHub repository to continuously collect both static and dynamic benchmarking methods for LLMs. The repository can be found at this link.

cs.LG↗

arXiv2025

OmniTry: Virtual Try-On Anything without Masks

Virtual Try-ON (VTON) is a practical and widely-applied task, for which most of existing works focus on clothes. This paper presents OmniTry, a unified framework that extends VTON beyond garment to encompass any wearable objects, e.g., jewelries and accessories, with mask-free setting for more practical application. When extending to various types of objects, data curation is challenging for obtaining paired images, i.e., the object image and the corresponding try-on result. To tackle this problem, we propose a two-staged pipeline: For the first stage, we leverage large-scale unpaired images, i.e., portraits with any wearable items, to train the model for mask-free localization. Specifically, we repurpose the inpainting model to automatically draw objects in suitable positions given an empty mask. For the second stage, the model is further fine-tuned with paired images to transfer the consistency of object appearance. We observed that the model after the first stage shows quick convergence even with few paired samples. OmniTry is evaluated on a comprehensive benchmark consisting of 12 common classes of wearable objects, with both in-shop and in-the-wild images. Experimental results suggest that OmniTry shows better performance on both object localization and ID-preservation compared with existing methods. The code, model weights, and evaluation benchmark of OmniTry will be made publicly available at https://omnitry.github.io/.

cs.CV↗

arXiv2025

Pedestrian Dead Reckoning using Invariant Extended Kalman Filter

This paper presents a cost-effective inertial pedestrian dead reckoning method for the bipedal robot in the GPS-denied environment. Each time when the inertial measurement unit (IMU) is on the stance foot, a stationary pseudo-measurement can be executed to provide innovation to the IMU measurement based prediction. The matrix Lie group based theoretical development of the adopted invariant extended Kalman filter (InEKF) is set forth for tutorial purpose. Three experiments are conducted to compare between InEKF and standard EKF, including motion capture benchmark experiment, large-scale multi-floor walking experiment, and bipedal robot experiment, as an effort to show our method's feasibility in real-world robot system. In addition, a sensitivity analysis is included to show that InEKF is much easier to tune than EKF.

cs.RO↗

arXiv2025

CodeJudgeBench: Benchmarking LLM-as-a-Judge for Coding Tasks

Large Language Models (LLMs) have significantly advanced the state-of-the-art in various coding tasks. Beyond directly answering user queries, LLMs can also serve as judges, assessing and comparing the quality of responses generated by other models. Such an evaluation capability is crucial both for benchmarking different LLMs and for improving response quality through response ranking. However, despite the growing adoption of the LLM-as-a-Judge paradigm, its effectiveness in coding scenarios remains underexplored due to the absence of dedicated benchmarks. To address this gap, we introduce CodeJudgeBench, a benchmark explicitly designed to evaluate the performance of LLM-as-a-Judge models across three critical coding tasks: code generation, code repair, and unit test generation. Through comprehensive benchmarking of 26 LLM-as-a-Judge models, we find that recent thinking models significantly outperform non-thinking models on our carefully designed code judging tasks. Notably, even relatively small thinking models, such as Qwen3-8B, can outperform specially trained LLM-as-a-Judge models up to 70B in size. Nevertheless, all models still exhibit significant randomness in their judgment of coding tasks. For pairwise judging tasks, simply changing the order in which responses are presented can substantially impact accuracy. In addition, when judging code and unit tests written by different LLMs, LLM-as-a-Judge models also show variance in performance. This sensitivity raises concerns about the reliability and consistency of LLM-as-a-Judge in coding scenarios. Lastly, we study optimal prompting strategies for LLM-as-a-Judge. We find that using pair-wise comparison outperforms scalar point-wise judging. Furthermore, retaining comments and reasoning in the full, unprocessed LLM response leads to improved judge performance.

cs.CL↗

arXiv2025

InterMamba: Efficient Human-Human Interaction Generation with Adaptive Spatio-Temporal Mamba

Human-human interaction generation has garnered significant attention in motion synthesis due to its vital role in understanding humans as social beings. However, existing methods typically rely on transformer-based architectures, which often face challenges related to scalability and efficiency. To address these issues, we propose a novel, efficient human-human interaction generation method based on the Mamba framework, designed to meet the demands of effectively capturing long-sequence dependencies while providing real-time feedback. Specifically, we introduce an adaptive spatio-temporal Mamba framework that utilizes two parallel SSM branches with an adaptive mechanism to integrate the spatial and temporal features of motion sequences. To further enhance the model's ability to capture dependencies within individual motion sequences and the interactions between different individual sequences, we develop two key modules: the self-adaptive spatio-temporal Mamba module and the cross-adaptive spatio-temporal Mamba module, enabling efficient feature learning. Extensive experiments demonstrate that our method achieves state-of-the-art results on two interaction datasets with remarkable quality and efficiency. Compared to the baseline method InterGen, our approach not only improves accuracy but also requires a minimal parameter size of just 66M ,only 36% of InterGen's, while achieving an average inference speed of 0.57 seconds, which is 46% of InterGen's execution time.

cs.CV↗

arXiv2025

Rethinking Image Forgery Detection via Soft Contrastive Learning and Unsupervised Clustering

Image forgery detection aims to detect and locate forged regions in an image. Most existing forgery detection algorithms formulate classification problems to classify pixels into forged or pristine. However, the definition of forged and pristine pixels is only relative within one single image, e.g., a forged region in image A is actually a pristine one in its source image B (splicing forgery). Such a relative definition has been severely overlooked by existing methods, which unnecessarily mix forged (pristine) regions across different images into the same category. To resolve this dilemma, we propose the FOrensic ContrAstive cLustering (FOCAL) method, a novel, simple yet very effective paradigm based on soft contrastive learning and unsupervised clustering for the image forgery detection. Specifically, FOCAL 1) designs a soft contrastive learning (SCL) to supervise the high-level forensic feature extraction in an image-by-image manner, explicitly reflecting the above relative definition; 2) employs an on-the-fly unsupervised clustering algorithm (instead of a trained one) to cluster the learned features into forged/pristine categories, further suppressing the cross-image influence from training data; and 3) allows to further boost the detection performance via simple feature-level concatenation without the need of retraining. Extensive experimental results over six public testing datasets demonstrate that our proposed FOCAL significantly outperforms the state-of-the-art competitors by big margins: +24.8% on Coverage, +18.9% on Columbia, +17.3% on FF++, +15.3% on MISD, +15.0% on CASIA and +10.5% on NIST in terms of IoU (see also Fig. 1). The paradigm of FOCAL could bring fresh insights and serve as a novel benchmark for the image forgery detection task. The code is available at https://github.com/HighwayWu/FOCAL.

cs.CV↗

arXiv2025

HARDMath2: A Benchmark for Applied Mathematics Built by Students as Part of a Graduate Class

Large language models (LLMs) have shown remarkable progress in mathematical problem-solving, but evaluation has largely focused on problems that have exact analytical solutions or involve formal proofs, often overlooking approximation-based problems ubiquitous in applied science and engineering. To fill this gap, we build on prior work and present HARDMath2, a dataset of 211 original problems covering the core topics in an introductory graduate applied math class, including boundary-layer analysis, WKB methods, asymptotic solutions of nonlinear partial differential equations, and the asymptotics of oscillatory integrals. This dataset was designed and verified by the students and instructors of a core graduate applied mathematics course at Harvard. We build the dataset through a novel collaborative environment that challenges students to write and refine difficult problems consistent with the class syllabus, peer-validate solutions, test different models, and automatically check LLM-generated solutions against their own answers and numerical ground truths. Evaluation results show that leading frontier models still struggle with many of the problems in the dataset, highlighting a gap in the mathematical reasoning skills of current LLMs. Importantly, students identified strategies to create increasingly difficult problems by interacting with the models and exploiting common failure modes. This back-and-forth with the models not only resulted in a richer and more challenging benchmark but also led to qualitative improvements in the students' understanding of the course material, which is increasingly important as we enter an age where state-of-the-art language models can solve many challenging problems across a wide domain of fields.

cs.LG↗

arXiv2025

Simulation of the Background from $^{13}$C$(α, n)^{16}$O Reaction in the JUNO Scintillator

Large-scale organic liquid scintillator detectors are highly efficient in the detection of MeV-scale electron antineutrinos. These signal events can be detected through inverse beta decay on protons, which produce a positron accompanied by a neutron. A noteworthy background for antineutrinos coming from nuclear power reactors and from the depths of the Earth (geoneutrinos) is generated by ($α, n$) reactions. In organic liquid scintillator detectors, $α$ particles emitted from intrinsic contaminants such as $^{238}$U, $^{232}$Th, and $^{210}$Pb/$^{210}$Po, can be captured on $^{13}$C nuclei, followed by the emission of a MeV-scale neutron. Three distinct interaction mechanisms can produce prompt energy depositions preceding the delayed neutron capture, leading to a pair of events correlated in space and time within the detector. Thus, ($α, n$) reactions represent an indistinguishable background in liquid scintillator-based antineutrino detectors, where their expected rate and energy spectrum are typically evaluated via Monte Carlo simulations. This work presents results from the open-source SaG4n software, used to calculate the expected energy depositions from the neutron and any associated de-excitation products. Also simulated is a detailed detector response to these interactions, using a dedicated Geant4-based simulation software from the JUNO experiment. An expected measurable $^{13}$C$(α, n)^{16}$O event rate and reconstructed prompt energy spectrum with associated uncertainties, are presented in the context of JUNO, however, the methods and results are applicable and relevant to other organic liquid scintillator neutrino detectors.

physics.ins-det↗

arXiv2025

Zero-one Grothendieck Polynomials

Fink, Mészáros and St.Dizier showed that the Schubert polynomial $\mathfrak{S}_w(x)$ is zero-one if and only if $w$ avoids twelve permutation patterns. In this paper, we prove that the Grothendieck polynomial $\mathfrak{G}_w(x)$ is zero-one, i.e., with coefficients either 0 or $\pm$1, if and only if $w$ avoids six patterns. As applications, we show that the normalized double Schubert polynomial $N(\mathfrak{S}_w(x;y))$ is Lorentzian when $\mathfrak{G}_w(x)$ is zero-one, partially confirming a conjecture of Huh, Matherne, Mészáros and St.Dizier. Moreover, we verify several conjectures on the support and coefficients of Grothendieck polynomials posed by Mészáros, Setiabrata and St.Dizier for the case of zero-one Grothendieck polynomials.

math.CO↗