arXiv subjects

Rui Chen

Publications and source records attributed to Rui Chen.

At least 145 records · Page 8Linked to original sources

arXiv2025

Embodied Tree of Thoughts: Deliberate Manipulation Planning with Embodied World Model

World models have emerged as a pivotal component in robot manipulation planning, enabling agents to predict future environmental states and reason about the consequences of actions before execution. While video-generation models are increasingly adopted, they often lack rigorous physical grounding, leading to hallucinations and a failure to maintain consistency in long-horizon physical constraints. To address these limitations, we propose Embodied Tree of Thoughts (EToT), a novel Real2Sim2Real planning framework that leverages a physics-based interactive digital twin as an embodied world model. EToT formulates manipulation planning as a tree search expanded through two synergistic mechanisms: (1) Priori Branching, which generates diverse candidate execution paths based on semantic and spatial analysis; and (2) Reflective Branching, which utilizes VLMs to diagnose execution failures within the simulator and iteratively refine the planning tree with corrective actions. By grounding high-level reasoning in a physics simulator, our framework ensures that generated plans adhere to rigid-body dynamics and collision constraints. We validate EToT on a suite of short- and long-horizon manipulation tasks, where it consistently outperforms baselines by effectively predicting physical dynamics and adapting to potential failures. Website at https://embodied-tree-of-thoughts.github.io .

cs.RO↗

arXiv2025

HARP: Hallucination Detection via Reasoning Subspace Projection

Hallucinations in Large Language Models (LLMs) pose a major barrier to their reliable use in critical decision-making. Although existing hallucination detection methods have improved accuracy, they still struggle with disentangling semantic and reasoning information and maintaining robustness. To address these challenges, we propose HARP (Hallucination detection via reasoning subspace projection), a novel hallucination detection framework. HARP establishes that the hidden state space of LLMs can be decomposed into a direct sum of a semantic subspace and a reasoning subspace, where the former encodes linguistic expression and the latter captures internal reasoning processes. Moreover, we demonstrate that the Unembedding layer can disentangle these subspaces, and by applying Singular Value Decomposition (SVD) to its parameters, the basis vectors spanning the semantic and reasoning subspaces are obtained. Finally, HARP projects hidden states onto the basis vectors of the reasoning subspace, and the resulting projections are then used as input features for hallucination detection in LLMs. By using these projections, HARP reduces the dimension of the feature to approximately 5% of the original, filters out most noise, and achieves enhanced robustness. Experiments across multiple datasets show that HARP achieves state-of-the-art hallucination detection performance; in particular, it achieves an AUROC of 92.8% on TriviaQA, outperforming the previous best method by 7.5%.

cs.CL↗

arXiv2025

A High-Order Discretization Scheme for Surface Integral Equations for Analyzing the Electroencephalography Forward Problem

A Nystrom-based high-order (HO) discretization scheme for surface integral equations (SIEs) for analyzing the electroencephalography (EEG) forward problem is proposed in this work. We use HO surface elements and interpolation functions for the discretization of the interfaces of the head volume and the unknowns on the elements, respectively. The advantage of this work over existing isoparametric HO discretization schemes resides in the fact that the interpolation points are different from the mesh nodes, allowing for the flexible manipulation of the order of the basis functions without regenerating the mesh of the interfaces. Moreover, the interpolation points are chosen from the quadrature rules with the same number of points on the elements simplifying the numerical computation of the surface integrals for the far-interaction case. In this contribution, we extend the implementation of the HO discretization scheme to the double-layer and the adjoint double-layer formulations, as well as to the isolated-skull-approach for the double-layer formulation and to the indirect adjoint double-layer formulation, employed to improve the solution accuracy in case of high conductivity contrast models, which requires the development of different techniques for the singularity treatment. Numerical experiments are presented to demonstrate the accuracy, flexibility, and efficiency of the proposed scheme for the four SIEs for analyzing the EEG forward problem.

math.NA↗

arXiv2025

Plug-and-Play Homeostatic Spark: Zero-Cost Acceleration for SNN Training Across Paradigms

Spiking neural networks offer event driven computation, sparse activation, and hardware efficiency, yet training often converges slowly and lacks stability. We present Adaptive Homeostatic Spiking Activity Regulation (AHSAR), an extremely simple plug in and training paradigm agnostic method that stabilizes optimization and accelerates convergence without changing the model architecture, loss, or gradients. AHSAR introduces no trainable parameters. It maintains a per layer homeostatic state during the forward pass, maps centered firing rate deviations to threshold scales through a bounded nonlinearity, uses lightweight cross layer diffusion to avoid sharp imbalance, and applies a slow across epoch global gain that combines validation progress with activity energy to tune the operating point. The computational cost is negligible. Across diverse training methods, SNN architectures of different depths, widths, and temporal steps, and both RGB and DVS datasets, AHSAR consistently improves strong baselines and enhances out of distribution robustness. These results indicate that keeping layer activity within a moderate band is a simple and effective principle for scalable and efficient SNN training.

cs.NE↗

arXiv2025

Solution of the Electric Field Integral Equation Using a Hybrid Quantum-Classical Scheme: Investigation of Accuracy and Efficiency

Conventional classical solvers are commonly used for solving matrix equation systems resulting from the discretization of SIEs in computational electromagnetics (CEM). However, the memory requirement would become a bottleneck for classical computing as the electromagentic problems become much larger. As an alternative, quantum computing has a natural "parallelization" advantage with much lower storage complexity due to the superposition and entanglement in quantum mechanics. Even though several quantum algorithms have been applied for the SIEs-based methods in the literature, the size of the matrix equation systems solvable using them is still limited. In this work, we use a hybrid quantum-classical scheme to solve the EFIE for analyzing electromagentic scattering from three-dimensional (3D) perfect electrically conducting objects with arbitrary shapes in CEM for the first time. Instead of directly solving the original EFIE matrix equation system using the quantum algorithms, the hybrid scheme first designs the preconditioned linear system and then uses a double-layer iterative strategy for its solution, where the external iteration layer builds subspace matrix equation systems with smaller dimension and the internal iteration layer solves the smaller systems using the quantum algorithms. Two representative quantum algorithms, HHL and VQLS, are considered in this work, which are executed on the quantum simulator and quantum computer platforms. We present the theoretical time complexity analysis of the hybrid quantum-classical scheme and perform numerical experiments to investigate the accuracy and efficiency of the hybrid scheme. The results show that the computational complexity of the hybrid VQLS-classical scheme is lower than the conventional fast solvers in classical computing, which indicates the hybrid scheme is more promising for analyzing large-scale electromagnetic problems.

quant-ph↗

arXiv2025

ViTaMIn-B: A Reliable and Efficient Visuo-Tactile Bimanual Manipulation Interface

Handheld devices have opened up unprecedented opportunities to collect large-scale, high-quality demonstrations efficiently. However, existing systems often lack robust tactile sensing or reliable pose tracking to handle complex interaction scenarios, especially for bimanual and contact-rich tasks. In this work, we propose ViTaMIn-B, a more capable and efficient handheld data collection system for such tasks. We first design DuoTact, a novel compliant visuo-tactile sensor built with a flexible frame to withstand large contact forces during manipulation while capturing high-resolution contact geometry. To enhance the cross-sensor generalizability, we propose reconstructing the sensor's global deformation as a 3D point cloud and using it as the policy input. We further develop a robust, unified 6-DoF bimanual pose acquisition process using Meta Quest controllers, which eliminates the trajectory drift issue in common SLAM-based methods. Comprehensive user studies confirm the efficiency and high usability of ViTaMIn-B among novice and expert operators. Furthermore, experiments on four bimanual manipulation tasks demonstrate its superior task performance relative to existing systems. Project page: https://chuanyune.github.io/ViTaMIn-B_page/

cs.RO↗

arXiv2025

Two-phase flow in porous metal foam flow fields of PEM fuel cells

Porous metal foam (PMF) flow field is a potential option for proton exchange membrane fuel cells (PEMFCs) due to its excellent capabilities in gas distribution and water drainage. However, the gas-liquid two-phase flow in the PMF flow field on the pore scale is still unclear. In this study, we investigate the gas-liquid two-phase flow in the PMF flow field. Film, plug, and ligament flows are found in the hydrophilic PMF flow field, while slug and droplet flows are found in the hydrophobic PMF flow field. The results suggest that optimizing the pore size, increasing the metal foam surface hydrophobicity, and optimizing the operating condition are helpful for the water management of the PMF flow field. The frequency analysis of the pressure drop also shows that the dominant frequency can be used as an indicator to analyze the transition between different flow patterns.

physics.flu-dyn↗

arXiv2025

Mass transfer and water management in proton exchange membrane fuel cells with a composite foam-rib flow field

Mass transfer capability of reactants and hydrothermal management is important for the performance and durability of proton exchange membrane fuel cells. In the conventional rib flow field, the oxygen transport is affected by the accumulation of under-rib liquid water which causes excessive concentration loss and limits cell performance. To improve the cell performance, a composite foam-rib flow field structure is proposed by combining the metal foam flow field and the conventional rib flow field. The proposed design is simulated by using a three-dimensional homogeneous non-isothermal numerical model. The results show that the composite foam-rib flow field, by improving the oxygen transfer and water removal capabilities under the ribs, can improve the oxygen concentration and current density without increasing the pumping power, thus improving the cell performance under different conditions. The key parameters of the composite foam-rib flow field are optimized. With the optimal metal foam filling ratio of 0.75 and porosity of 0.85, the peak power density and the limiting current density for the composite foam-rib flow field are higher than the conventional rib flow field by 5.20% and 22.68%.

physics.flu-dyn↗

arXiv2025

Chain-of-Query: Unleashing the Power of LLMs in SQL-Aided Table Understanding via Multi-Agent Collaboration

Table understanding requires structured, multi-step reasoning. Large Language Models (LLMs) struggle with it due to the structural complexity of tabular data. Recently, multi-agent frameworks for SQL generation have shown promise in tackling the challenges of understanding tabular data, but existing approaches often suffer from limitations such as the inability to comprehend table structure for reliable SQL generation, error propagation that results in invalid queries, and over-reliance on execution correctness. To address these issues, we propose Chain-of-Query (CoQ), a novel multi-agent framework for SQL-aided table understanding. CoQ adopts natural-language-style representations of table schemas to abstract away structural noise and enhance understanding. It employs a clause-by-clause SQL generation strategy to improve query quality and introduces a hybrid reasoning division that separates SQL-based mechanical reasoning from LLM-based logical inference, thereby reducing reliance on execution outcomes. Extensive experiments across four models and five widely used benchmarks demonstrate that CoQ achieves substantial accuracy improvements and significantly lowers invalid SQL rates compared to prior generic LLM-based, SQL-aided, and hybrid baselines, confirming its superior effectiveness in table understanding. The code is available at https://github.com/SongyuanSui/ChainofQuery.

cs.CL↗

arXiv2025

Exploring pion emission properties of (strange) hidden-charm molecular pentaquarks in a chiral quark model

The internal structure of the exotic $P_c$ and $P_{cs}$ pentaquarks remains an open question. To address this, we demonstrate that pion emission serves as a sensitive probe by calculating its properties within a molecular scenario using the chiral quark model and coupled-channel effects. Our results reveal a strong dependence of the decay widths on the internal structure and spatial wave functions. We therefore expect this study to stimulate experimental measurements of these decays, which are crucial for determining the nature of these states and guiding the search for further molecular partners.

hep-ph↗

arXiv2025

FusionFM: All-in-One Multi-Modal Image Fusion with Flow Matching

Current multi-modal image fusion methods typically rely on task-specific models, leading to high training costs and limited scalability. While generative methods provide a unified modeling perspective, they often suffer from slow inference due to the complex sampling trajectories from noise to image. To address this, we formulate image fusion as a direct probabilistic transport from source modalities to the fused image distribution, leveraging the flow matching paradigm to improve sampling efficiency and structural consistency. To mitigate the lack of high-quality fused images for supervision, we collect fusion results from multiple state-of-the-art models as priors, and employ a task-aware selection function to select the most reliable pseudo-labels for each task. We further introduce a Fusion Refiner module that employs a divide-and-conquer strategy to systematically identify, decompose, and enhance degraded components in selected pseudo-labels. For multi-task scenarios, we integrate elastic weight consolidation and experience replay mechanisms to preserve cross-task performance and enhance continual learning ability from both parameter stability and memory retention perspectives. Our approach achieves competitive performance across diverse fusion tasks, while significantly improving sampling efficiency and maintaining a lightweight model design. The code will be available at: https://github.com/Ist-Zhy/FusionFM.

cs.CV↗

arXiv2025

Imbalance in Balance: Online Concept Balancing in Generation Models

In visual generation tasks, the responses and combinations of complex concepts often lack stability and are error-prone, which remains an under-explored area. In this paper, we attempt to explore the causal factors for poor concept responses through elaborately designed experiments. We also design a concept-wise equalization loss function (IMBA loss) to address this issue. Our proposed method is online, eliminating the need for offline dataset processing, and requires minimal code changes. In our newly proposed complex concept benchmark Inert-CompBench and two other public test sets, our method significantly enhances the concept response capability of baseline models and yields highly competitive results with only a few codes released at https://github.com/KwaiVGI/IMBA-Loss.

cs.CV↗

arXiv2025

MOSAIC: Generating Consistent, Privacy-Preserving Scenes from Multiple Depth Views in Multi-Room Environments

We introduce a diffusion-based approach for generating privacy-preserving digital twins of multi-room indoor environments from depth images only. Central to our approach is a novel Multi-view Overlapped Scene Alignment with Implicit Consistency (MOSAIC) model that explicitly considers cross-view dependencies within the same scene in the probabilistic sense. MOSAIC operates through a multi-channel inference-time optimization that avoids error accumulation common in sequential or single-room constraints in panorama-based approaches. MOSAIC scales to complex scenes with zero extra training and provably reduces the variance during denoising process when more overlapping views are added, leading to improved generation quality. Experiments show that MOSAIC outperforms state-of-the-art baselines on image fidelity metrics in reconstructing complex multi-room environments. Resources and code are at https://mosaic-cmubig.github.io

cs.CV↗

arXiv2025

2D Addressable Mid-infrared Metasurface Spatial Light Modulator

Active metasurfaces enable dynamic control of light for applications in beam steering, pixelated holography, and adaptive optics, but demonstrations of two-dimensional (2D) electrically addressable arrays have so far been limited. Here we introduce a scalable 2D architecture based on phase-change materials (PCMs) integrated metasurfaces and apply it to realize the first transmissive mid-infrared (mid-IR) spatial light modulator (SLM). The device is fabricated through standard silicon photonic foundry processing combined with backend-of-line (BEOL) integration and employs multilayer backend metal interconnects to implement a crossbar addressing scheme. Each pixel is integrated with a silicon diode selector to suppress sneak-path currents, a feature essential for scaling to large arrays. The result establishes a foundry-compatible route to high-density, large-area active metasurfaces with independently tunable pixels.

physics.optics↗

arXiv2025

On the Convexification of a Class of Mixed-Integer Conic Sets

We investigate mixed-integer second-order conic (SOC) sets with a nonlinear right-hand side in the SOC constraint, a structure frequently arising in mixed-integer quadratically constrained programming (MIQCP). Under mild assumptions, we show that the convex hull can be exactly described by replacing the right-hand side with its concave envelope. This characterization enables strong relaxations for MIQCPs via reformulations and cutting planes. Computational experiments on distributionally robust chance-constrained knapsack variants demonstrate the efficacy of our reformulation techniques.

math.OC↗

arXiv2025

Solving 0-1 Integer Programs with Unknown Knapsack Constraints Using Membership Oracles

We consider solving a combinatorial optimization problem with unknown knapsack constraints using a membership oracle for each unknown constraint such that, given a solution, the oracle determines whether the constraint is satisfied or not with absolute certainty. The goal of the decision maker is to find the best possible solution subject to a budget on the number of oracle calls. Inspired by active learning for binary classification based on Support Vector Machines (SVMs), we devise a framework to solve the problem by learning and exploiting surrogate linear constraints. The framework includes training linear separators on the labeled points and selecting new points to be labeled, which is achieved by applying a sampling strategy and solving a 0-1 integer linear program. Following the active learning literature, a natural choice would be SVM as a linear classifier and the information-based sampling strategy known as simple margin, for each unknown constraint. We improve on both sides: we propose an alternative sampling strategy based on mixed-integer quadratic programming and a linear separation method inspired by an algorithm for convex optimization in the oracle model. We conduct experiments on classical problems and variants inspired by realistic applications to show how different linear separation methods and sampling strategies influence the quality of the results in terms of several metrics including objective value, dual bound and running time.

cs.LG↗

arXiv2025

Seed3D 1.0: From Images to High-Fidelity Simulation-Ready 3D Assets

Developing embodied AI agents requires scalable training environments that balance content diversity with physics accuracy. World simulators provide such environments but face distinct limitations: video-based methods generate diverse content but lack real-time physics feedback for interactive learning, while physics-based engines provide accurate dynamics but face scalability limitations from costly manual asset creation. We present Seed3D 1.0, a foundation model that generates simulation-ready 3D assets from single images, addressing the scalability challenge while maintaining physics rigor. Unlike existing 3D generation models, our system produces assets with accurate geometry, well-aligned textures, and realistic physically-based materials. These assets can be directly integrated into physics engines with minimal configuration, enabling deployment in robotic manipulation and simulation training. Beyond individual objects, the system scales to complete scene generation through assembling objects into coherent environments. By enabling scalable simulation-ready content creation, Seed3D 1.0 provides a foundation for advancing physics-based world simulators. Seed3D 1.0 is now available on https://console.volcengine.com/ark/region:ark+cn-beijing/experience/vision?modelId=doubao-seed3d-1-0-250928&tab=Gen3D

eess.IV↗

arXiv2025

The Complexity of Recognizing Facets for the Knapsack Polytope

The complexity class DP is the class of all languages that are the intersection of a language in NP and a language in coNP. It was conjectured that recognizing a facet for the knapsack polytope is DP-complete. We provide a positive answer to this conjecture. Moreover, despite the \DP-hardness of the recognition problem, we give a polynomial time algorithm for deciding if an inequality with a fixed number of distinct coefficients defines a facet of a knapsack polytope.

math.OC↗