Searcharxiv⌕ Search

arXiv subjects

Yan Shen

Publications and source records attributed to Yan Shen.

At least 19 recordsLinked to original sources

Mean-field BSDEs with jumps under quadratic-exponential growth

This paper studies the well-posedness of mean-field backward stochastic differential equations (BSDEs, for short) with Poisson jumps, where the generator has quadratic growth with respect to $Z$ and exponential growth with respect to $U$, where $(Y,Z,U)$ denotes the solution of this BSDE. First, we prove the existence and the uniqueness of local solutions to mean-field backward stochastic differential equations with jumps (BSDEJs, for short) by using a fixed-point argument. Then, based on these local results, we discuss the solvability of global solutions in the following two cases: in the first one, the generator has linear growth with respect to $Y$ and the corresponding marginal distribution $μ_1$; and in the second one, the generator has subquadratic growth with respect to the marginal distribution $μ_2$ and linear growth with respect to the marginal distribution $μ_3$, corresponding to $Z$ and $U$, respectively. Finally, by employing a Girsanov transformation we establish a comparison theorem for mean-field BSDEJs under quadratic-exponential growth conditions.

math.PR↗

Thermal-Mass Coupled Modeling and Optimal Scheduling of Aluminum Smelting Loads for Safe Demand Response Participation

Aluminum smelting loads (ASLs) offer substantial flexibility potential, yet their actual participation in demand response remains conservative owing to the risk of operational failures. Power adjustments disturb the electrolyte temperature and superheat, which may lead to electrolyte freeze-out or yield loss. Existing ASL demand response methods often rely on oversimplified dynamic models of the electrolytic cell's thermal behavior, such as linear models and the Equivalent Thermal Parameter (ETP) model, which may either violate temperature constraints or underestimate the available flexibility. To address this limitation, this paper proposes a Thermal-Mass Coupled (TMC) dynamic model. The model captures the essential physical mechanisms of electrolytic cells, including alumina feed dynamics, ledge phase-change dynamics, and state-dependent current efficiency. The resulting nonlinear relations are reformulated into a tractable mixed-integer linear programming (MILP) model using Taylor approximations and McCormick-envelope reformulations. In the illustrative PBDR and IBDR case studies, the nonlinear reference-model assessment shows that the TMC model achieves net economic improvements 122.4% and 325.1% higher, respectively, than the ETP model. The proposed framework can therefore support deeper demand response participation by aluminum smelters while explicitly assessing adherence to operational safety constraints.

eess.SY↗

Toward Real-Time VLAs: Stage-Aware Two-Step Flow Denoising and System-Level Evaluation

Vision-language-action (VLA) models face a timing gap between low-rate inference and high-rate robot execution. We characterize this gap through end-to-end latency measurements of model inference and the robot execution chain. Repeated Flow Matching denoising contributes substantially to inference cost, while robot-side delays mainly arise from perception acquisition, communication scheduling, and physical response. Analysis of the velocity field shows relatively stable magnitude and direction in early integration, followed by stronger directional correction near the terminal steps. Based on this stage heterogeneity, we propose two-stage non-uniform denoising, reducing the number of steps from 10 to 2 and model-inference time from 61.557 ms to 21.956 ms. We also develop a distributed real-time VLA framework with independent inference, action-publication, and robot-control rates, modular observation acquisition, and action-provenance logging. Using π0.5 as the baseline, we evaluate six real-time execution methods on a long-horizon physical garment-folding task. Legato performs best overall among training-based methods, while Temporal Smoothing leads among training-free methods; both perform strongly in task success, completion time, action continuity, and acceleration smoothness. Combining two-step denoising with representative execution methods substantially reduces inference cost with a small reduction in task performance. These results motivate joint optimization of model-inference efficiency and robot-system timing.

cs.RO↗

Imagine2Act: Leveraging Object-Action Motion Consistency from Imagined Goals for Robotic Manipulation

Relational object rearrangement (ROR) tasks (e.g., insert flower to vase) require a robot to manipulate objects with precise semantic and geometric reasoning. Existing approaches either rely on pre-collected demonstrations that struggle to capture complex geometric constraints or generate goal-state observations to capture semantic and geometric knowledge, but fail to explicitly couple object transformation with action prediction, resulting in errors due to generative noise. To address these limitations, we propose Imagine2Act, a 3D imitation-learning framework that incorporates semantic and geometric constraints of objects into policy learning to tackle high-precision manipulation tasks. We first generate imagined goal images conditioned on language instructions and reconstruct corresponding 3D point clouds to provide robust semantic and geometric priors. These imagined goal point clouds serve as additional inputs to the policy model, while an object-action consistency strategy with soft pose supervision explicitly aligns predicted end-effector motion with generated object transformation. This design enables Imagine2Act to reason about semantic and geometric relationships between objects and predict accurate actions across diverse tasks. Experiments in both simulation and the real world demonstrate that Imagine2Act outperforms previous state-of-the-art policies. More visualizations can be found at https://sites.google.com/view/imagine2act.

cs.RO↗

BiRoAD: Learning Shared and Role-Adaptive Representations for Bimanual Manipulation

Bimanual manipulation requires policies that coordinate two arms while adapting their functional roles to scene geometry, object configuration, and task context. Learning such scene-conditioned role adaptation remains challenging, as demonstrations may contain uneven role distributions that limit generalization to underrepresented arm--role configurations. In addition, many bimanual policies predict actions in fixed left- and right-arm action spaces. While this provides a natural parameterization for robot control, it does not explicitly specify how behaviors should transform when functional roles are exchanged across arms. Across different scene initializations, the two arms may follow a similar coordination pattern, but the role-specific behavior assigned to each arm should change with the scene. Therefore, we propose BiRoAD, a Bimanual Role-Adaptive Decomposition framework for learning shared and role-adaptive representations in bimanual policies. Given bimanual trajectory or action-token features, BiRoAD decomposes these features into swap--symmetric and swap--antisymmetric components: the former captures coordination structure invariant to arm exchange, and the latter captures role-specific distinctions that vary consistently with functional role assignment. The two components are then recomposed as residual updates to the original paired arm representations, allowing BiRoAD to serve as a modular feature transformation without changing the policy inputs, imitation-learning objective, or requiring manually defined role labels. Across multiple bimanual manipulation tasks with balanced and imbalanced role distributions, BiRoAD improves robustness across role configurations over corresponding base policies, with notable gains on underrepresented role configurations.

cs.RO↗

Scaling Bimanual Household Manipulation from 1,500 hours of Demonstrations to On-Policy Corrections

Learning generalist policies for robust bimanual manipulation is bottlenecked by the scarcity of high quality large scale human demonstration data. In this work, we release 1,500 hours of diverse bimanual manipulation demonstrations covering everyday household tasks, and use this comprehensive corpus to train XR-2, a powerful vision-language-action (VLA) model. Enabled by a purpose built high throughput data pipeline and a carefully designed multi stage training paradigm, XR-2 attains strong manipulation performance in our systematic experiments while retaining favorable training efficiency and high data utilization. We further study two critical scaling axes: varying the amount of expert demonstration data, and post training on DAgger correction data from real time human interventions. In both settings, task success rate improves steadily over the data ranges we probe, exhibiting a clear consistent scaling trend at our current data scale. These results validate both the learning capacity of XR-2 and the promising scaling properties of the released dataset, which we open source to support reproducible research on bimanual robot manipulation learning.

cs.RO↗

Integrating Fast-response Capability into Virtual Power Plant Operation for Ancillary Services

Virtual power plants (VPPs) can aggregate distributed energy resources (DERs) to provide ancillary services for power systems, creating new profit opportunities. Ancillary services such as secondary frequency regulation require providers to have sufficient response capability to follow rapidly changing control commands. If overlooking the response requirement, the VPP will not be able to accurately measure its regulation capability, reducing its earnings in performance-based markets or risking disqualification. This paper integrates the requirement for fast-response capability into the operational framework of VPPs providing ancillary services. We leverage historical control commands to formulate chance constraints in the bidding model, mandating that the VPP's fast-response capability meets the requirement of ancillary services with a specified probability. Case studies verify that considering fast-response capabilities can enhance VPP operation.

eess.SY↗

ReactBench: A Cause-Driven Benchmark for Multimodal Hallucination via Systematic Evaluation

While multimodal large language models (MLLMs) have achieved rapid progress in vision-language understanding, they remain prone to multimodal hallucinations, producing responses that are inconsistent with the visual input. Existing benchmarks predominantly focus on detecting hallucination outcomes rather than evaluating the underlying causes of these failures. Moreover, many benchmarks rely on simplistic scenarios and limited evaluation formats that no longer challenge state-of-the-art models. To address these limitations, we introduce ReactBench, a cause-driven hallucination benchmark featuring multiple tasks and an exam-style evaluation format. By generating adversarial images and hallucination-inducing queries, ReactBench introduces four targeted tasks: Relational Erasure, Counterfactual Attribute, Alteration Tracing, and Dense Counting. These tasks systematically expose co-occurrence bias, language priors, cross-image comparative perception deficiencies, and fine-grained perceptual bottlenecks. Beyond standard accuracy-based evaluation, we leverage Chain-of-Thought reasoning to identify fine-grained sub-causes of hallucination within each task. Extensive evaluations reveal that current MLLMs remain notably vulnerable to cause-specific hallucination triggers, demonstrating the value of ReactBench as a systematic and interpretable testbed for diagnosing and improving multimodal model robustness. The project page is available at https://reactbench.github.io/.

cs.CV↗

AT-VLA: Adaptive Tactile Injection for Enhanced Feedback Reaction in Vision-Language-Action Models

Vision-Language-Action (VLA) models have significantly advanced the capabilities of robotic agents in executing diverse tasks; however, they still face challenges in contact-rich manipulation scenarios that require precise physical interactions. To address this limitation, recent studies have attempted to incorporate tactile signals during downstream tasks, enabling pretrained VLAs to interpret tactile feedback. Nevertheless, introducing new modalities during finetuning, which are rarely present in the pretrain stage, may disrupt the pretrained capabilities of VLAs. In addition, the inherently slow inference speed of VLAs hampers real-time responsiveness and limits the effective utilization of tactile feedback for action adjustment. To overcome these challenges, we propose Adaptive Tactile Vision-Language-Action (AT-VLA), which introduces a novel Adaptive Tactile Injection mechanism. This mechanism dynamically determines the appropriate timing and locations for tactile injection, incorporating only when it significantly contributes to action generation, thereby minimizing interference with pretrained representations. Furthermore, to enable rapid and accurate tactile responses, we propose a Tactile Reaction Dual-Stream mechanism, which decouples sensory processing into a slow visual-language stream for low-frequency perceptual reasoning and a fast tactile control stream for high-frequency physical interaction understanding, achieving real-time close-loop responses within 0.04 s. Real-world experiments thoroughly validate the effectiveness of AT-VLA in contact-rich manipulation tasks. The project page is available at: https://sites.google.com/view/at-vla.

cs.RO↗

LeHome: A Simulation Environment for Deformable Object Manipulation in Household Scenarios

Household environments present one of the most common, impactful yet challenging application domains for robotics. Within household scenarios, manipulating deformable objects is particularly difficult, both in simulation and real-world execution, due to varied categories and shapes, complex dynamics, and diverse material properties, as well as the lack of reliable deformable-object support in existing simulations. We introduce LeHome, a comprehensive simulation environment designed for deformable object manipulation in household scenarios. LeHome covers a wide spectrum of deformable objects, such as garments and food items, offering high-fidelity dynamics and realistic interactions that existing simulators struggle to simulate accurately. Moreover, LeHome supports multiple robotic embodiments and emphasizes low-cost robots as a core focus, enabling end-to-end evaluation of household tasks on resource-constrained hardware. By bridging the gap between realistic deformable object simulation and practical robotic platforms, LeHome provides a scalable testbed for advancing household robotics. Webpage: https://lehome-web.github.io/ .

cs.RO↗

Industrial overcapacity can enable seasonal flexibility in electricity use

In many countries, declining demand in energy-intensive industries (EIIs) such as cement, steel, and aluminum is leading to industrial overcapacity. Although industrial overcapacity is traditionally envisioned as problematic and resource-wasteful, it could unlock EIIs' flexibility in electricity use. Here, using China's aluminum smelting industry as a case study, we evaluate the system-level cost-benefit of retaining EII overcapacity for flexible electricity use in decarbonized energy systems. We find that overcapacity can enable aluminum smelters to adopt a seasonal operation paradigm, ceasing production during winter load peaks that are exacerbated by heating electrification and renewable seasonality. This seasonal operation paradigm could reduce the investment and operational costs of China's decarbonized electricity system by 23-32 billion CNY/year (11-15% of the aluminum smelting industry's product value), sufficient to offset the increased smelter maintenance and product storage costs associated with overcapacity. It may also create labor complementarities between the aluminum and thermal power sectors.

physics.soc-ph↗

Towards Reliable Forgetting: A Survey on Machine Unlearning Verification

With growing demands for privacy protection, security, and legal compliance (e.g., GDPR), machine unlearning has emerged as a critical technique for ensuring the controllability and regulatory alignment of machine learning models. However, a fundamental challenge in this field lies in effectively verifying whether unlearning operations have been successfully and thoroughly executed. Despite a growing body of work on unlearning techniques, verification methodologies remain comparatively underexplored and often fragmented. Existing approaches lack a unified taxonomy and a systematic framework for evaluation. To bridge this gap, this paper presents the first structured survey of machine unlearning verification methods. We propose a taxonomy that organizes current techniques into two principal categories -- behavioral verification and parametric verification -- based on the type of evidence used to assess unlearning fidelity. We examine representative methods within each category, analyze their underlying assumptions, strengths, and limitations, and identify potential vulnerabilities in practical deployment. In closing, we articulate a set of open problems in current verification research, aiming to provide a foundation for developing more robust, efficient, and theoretically grounded unlearning verification mechanisms.

cs.LG↗

BiPreManip: Learning Affordance-Based Bimanual Preparatory Manipulation through Anticipatory Collaboration

Many everyday objects are difficult to directly grasp (e.g., a flat iPad) or manipulate functionally (e.g., opening the cap of a pen lying on a desk). Such tasks require sequential, asymmetric coordination between two arms, where one arm performs preparatory manipulation that enables the other's goal-directed action - for instance, pushing the iPad to the table's edge before picking it up, or lifting the pen body to allow the other hand to remove its cap. In this work, we introduce Collaborative Preparatory Manipulation, a class of bimanual manipulation tasks that demand understanding object semantics and geometry, anticipating spatial relationships, and planning long-horizon coordinated actions between the two arms. To tackle this challenge, we propose a visual affordance-based framework that first envisions the final goal-directed action and then guides one arm to perform a sequence of preparatory manipulations that facilitate the other arm's subsequent operation. This affordance-centric representation enables anticipatory inter-arm reasoning and coordination, generalizing effectively across various objects spanning diverse categories. Extensive experiments in both simulation and the real world demonstrate that our approach substantially improves task success rates and generalization compared to competitive baselines.

cs.RO↗

Methods for characterization of atomic-scale field emission point-electron-source

Field emission (FE) electron sources are made close to atomic-scale to reach the highest spatial resolution as well as stable emission for electron microscopy, electron beam inspection and lithography. At present, no single agreed method exists of using FE current-voltage data to extract the apparent emission area, which is needed for predicting some beam properties. The 1956 theory of Murphy and Good (MG) is better physics than the 1920s theory of Fowler and Nordheim (FN) and colleagues, but many researchers use simplified FN theory to analyse experimental data. The present paper reports an experimental method of finding apparent emission area, based on using field ion and field electron microscopes (FIM-FEM). The discrepancy of emission area between the FIM-FEM method and MG-based analysis is a factor of 7.4, while that with simplified FN-based analysis is about 25, confirming MG theory is better for FE data analysis. The result allows deduction of key indicators, including source energy spread, reduced brightness and emission efficiency. A downloadable program is made available to help analysis. Our work provides a new experimental method of characterizing FE electron sources, especially the atomic-scale cold cathode, for which existing plot-based data-analysis methods are not suitable.

quant-ph↗

A3D: Adaptive Affordance Assembly with Dual-Arm Manipulation

Furniture assembly is a crucial yet challenging task for robots, requiring precise dual-arm coordination where one arm manipulates parts while the other provides collaborative support and stabilization. To accomplish this task more effectively, robots need to actively adapt support strategies throughout the long-horizon assembly process, while also generalizing across diverse part geometries. We propose A3D, a framework which learns adaptive affordances to identify optimal support and stabilization locations on furniture parts. The method employs dense point-level geometric representations to model part interaction patterns, enabling generalization across varied geometries. To handle evolving assembly states, we introduce an adaptive module that uses interaction feedback to dynamically adjust support strategies during assembly based on previous interactions. We establish a simulation environment featuring 50 diverse parts across 8 furniture types, designed for dual-arm collaboration evaluation. Experiments demonstrate that our framework generalizes effectively to diverse part geometries and furniture categories in both simulation and real-world settings.

cs.RO↗

General mean-field BSDEs with integrable terminal values

This paper investigates $L^{1}$ solutions for mean-field backward stochastic differential equations (MFBSDEs) under different weak assumptions in both one-dimensional and multi-dimensional settings, whose generator $f(ω,t,y,z,μ)$ depends not only on the solution process $(Y,Z)$ but also on the law of $(Y,Z)$. In the one-dimensional case where $f$ depends on the law of $Y$, we show with the help of a test function method and a localization procedure that such type of equations with an integrable terminal condition admits an $L^{1}$ solution, when the generator $f(ω,t,y,z,μ)$ has a one-sided linear growth in $(y,μ)$, and an iterated-logarithmically sub-linear growth in $z$. Furthermore, by leveraging the additional extended monotonicity in $y$ and an iterated-logarithmically uniform continuity in $z$ of the generator $f(ω,t,y,z,μ)$ together with a strengthened nondecreasing condition in $μ$, we derive a comparison theorem for $L^{1}$ solutions, which immediately leads to the uniqueness of the $L^{1}$ solutions. Next, we establish the existence and the uniqueness of $L^{1}$ solutions for multi-dimensional mean-field BSDEs with integrable parameters in which the generator $f(ω,t,y,z,μ)$ depends on $μ=\mathbb{P}_{Y}$ and satisfies a one-sided Osgood condition as well as a general growth condition in $y$, a Lipschitz continuity as well as a sublinear growth condition in $z$, and a Lipschitz condition in $μ$. Finally, the solvability of $L^{1}$ solutions for general MFBSDEs is studied, where the generator $f(ω,t,y,z,μ)$ depends on both the solution process $(Y,Z)$ and its joint law $\mathbb{P}_{(Y,Z)}$.

math.PR↗

Learning Environment-Aware Affordance for 3D Articulated Object Manipulation under Occlusions

Perceiving and manipulating 3D articulated objects in diverse environments is essential for home-assistant robots. Recent studies have shown that point-level affordance provides actionable priors for downstream manipulation tasks. However, existing works primarily focus on single-object scenarios with homogeneous agents, overlooking the realistic constraints imposed by the environment and the agent's morphology, e.g., occlusions and physical limitations. In this paper, we propose an environment-aware affordance framework that incorporates both object-level actionable priors and environment constraints. Unlike object-centric affordance approaches, learning environment-aware affordance faces the challenge of combinatorial explosion due to the complexity of various occlusions, characterized by their quantities, geometries, positions and poses. To address this and enhance data efficiency, we introduce a novel contrastive affordance learning framework capable of training on scenes containing a single occluder and generalizing to scenes with complex occluder combinations. Experiments demonstrate the effectiveness of our proposed approach in learning affordance considering environment constraints. Project page at https://chengkaiacademycity.github.io/EnvAwareAfford/

cs.RO↗

A Hybrid Discontinuous Galerkin Neural Network Method for Solving Hyperbolic Conservation Laws with Temporal Progressive Learning

For hyperbolic conservation laws, traditional methods and physics-informed neural networks (PINNs) often encounter difficulties in capturing sharp discontinuities and maintaining temporal consistency. To address these challenges, we introduce a hybrid computational framework by coupling discontinuous Galerkin (DG) discretizations with a temporally progressive neural network architecture. Our method incorporates a structure-preserving weak-form loss -- combining DG residuals and Rankine-Hugoniot jump conditions -- with a causality-respecting progressive training strategy. The proposed framework trains neural networks sequentially across temporally decomposed subintervals, leveraging pseudo-label supervision to ensure temporal coherence and solution continuity. This approach mitigates error accumulation and enhances the model's capacity to resolve shock waves and steep gradients without explicit limiters. Besides, a theoretical analysis establishes error bounds for the proposed framework, demonstrating convergence toward the physical solution under mesh refinement and regularized training. Numerical experiments on Burgers and Euler equations show that our method consistently outperforms standard PINNs, PINNs-WE, and first-order DG schemes in both accuracy and robustness, particularly in capturing shocks and steep gradients. These results highlight the promise of combining classical discretization techniques with machine learning to develop robust and accurate solvers for nonlinear hyperbolic systems.

math.NA↗