arXiv subjects

Han Yang

Publications and source records attributed to Han Yang.

At least 19 recordsLinked to original sources

arXiv2026

Smooth bounding box for object detection

Deep learning-based object detection models are highly dependent on the quality of annotated training data. However, large-scale datasets often contain inevitable label noise, with bounding box localization errors being a prevalent and impactful form in object detection. While label noise handling techniques are well-studied for image classification, their adaptation to the more complex problem of bounding box errors remains underexplored. To address this, we propose a novel Smooth Bounding Box (SBB) strategy to mitigate the adverse effects of bounding box annotation inaccuracies. Our key insight is that annotation errors are often linked to annotator factors rather than specific image content, allowing for a statistical correction approach. Based on object size distribution within datasets, we implement the SBB strategy through two methods: 1) Global Scaling Correction (GSC), which applies a uniform scaling factor to estimate and correct a global average error; and 2) Interval Scaling Correction (ISC), which categorizes objects by size into intervals and estimates a dedicated correction factor for each, enabling more precise, fine-grained calibration. For efficient optimization of multiple parameters in ISC, we design a tailored model fine-tuning strategy. Furthermore, we introduce a Normalized Residual Fluctuation (NRF) metric to quantitatively assess the smoothing effect and training stability. Extensive experiments on multiple benchmarks demonstrate that our method consistently enhances detection accuracy across various model architectures. Both GSC and ISC achieve significant performance improvements over strong baselines, including the latest YOLOv11n, without adding inference overhead. The codes are available at https://github.com/Acui001/SBB.git.

cs.CV↗

arXiv2026

Are Frontier VLM Agents Ready to Be Robot Generalists? An Empirical Study with the Embodied Agent Arena

A robot generalist must interpret a scene, act on it, and satisfy every condition of a task. How far do frontier vision-language models (VLMs) meet these demands? We introduce Embodied Agent Arena, evaluating ten VLM agents across Geometry, Spatial Reasoning, Affordance, Task Planning, and Manipulation. Its 1,000 cases combine 32 established sources with GeoProbe, our 168-case benchmark for camera, motion, depth, and scale estimation. A minimal harness leaves task decisions to the model through source-native interfaces. Closed-weight models lead all five domains, whereas open-weight VLMs show useful spatial reasoning but substantially lower planning and manipulation success. Beneath these averages, similar geometric errors conceal different scale and shape distortions, and valid region estimates need not identify usable action points. During execution, agents can achieve early subgoals yet lose object control, bind an action to the wrong receiving region, or stop before the required physical state holds. Additional computation does not uniformly resolve these failures: code repair can restore execution without completing the task, while self-review can reverse correct judgments. Failure costs also differ: the strongest planners concentrate failed-token expenditure in prolonged body-control tasks, whereas other models fail broadly across procedures. Matched traces show how successful recovery uses feedback to restore a missing prerequisite and advance the remaining task.

cs.RO↗

arXiv2026

Anvil: Scaling Embodied Spatial Intelligence through Knowledge Recirculation

Embodied spatial intelligence requires more than visual recognition: models must localize entities, reason about their relations, and express this knowledge in action-relevant forms. Yet joint training can conflate the knowledge needed at different stages because supervision is fragmented across incompatible geometric and semantic outputs. We introduce Anvil, a unified framework for data generation, training, and benchmarking for embodied spatial intelligence. (1) Anvil-Gen is a heterogeneous data flywheel that combines form-specific generation, cross-stage consistency verification, and failure-driven recollection across 11 Ground--Relation--Act forms. (2) Anvil-Ben provides scene-aligned supervision for learning diverse embodied spatial capabilities and scene-linked assessments that distinguish stage competence from error propagation. (3) Anvil-MOPD is a 9B student that consolidates heterogeneous spatial knowledge through distillation from specialist teachers. Semantic-first-fault routing targets teacher supervision to the student's earliest decisive failure, while stage normalization controls the loss scale across native outputs of different lengths. We construct 5.8M source-grounded records spanning 160K images, reserving 580K spatial records for held-out evaluation and using the remaining 5.22M records for training. On average across seven public benchmarks, Anvil-MOPD outperforms Qwen3.5-9B and RynnBrain-8B by 9.29 and 11.03 percentage points, respectively, while reaching 80.67% on VABench-Point. Controlled studies support targeted coverage, selective transfer, and feedback-guided repair as complementary framework components.

cs.CV↗

arXiv2026

In-Context Learning for Robots: Methods and Applications

General-purpose robots must infer what a new task requires and translate that understanding into appropriate physical action. In-context learning (ICL) for robots supports this process by using demonstrations and interaction to direct existing competence with neural parameters held fixed during deployment. We organize this literature review around the interfaces connecting contextual evidence to execution, distinguishing four families: context-conditioned policies, geometric demonstration transfer, world-model-based control, and skill- and agent-based execution. Comparing these interfaces clarifies their transfer assumptions and the roles of training, correspondence, and memory in making context useful. Across manipulation and navigation, we examine how these mechanisms preserve taught requirements as objects, environments, and execution conditions change. This analysis links method design to evaluation practices that distinguish responsiveness to teaching, physical transfer, and benefits from retained experience. The resulting agenda connects compositional task acquisition and faithful transfer with physical recursive self-improvement, in which experience improves the ability to learn subsequent tasks.

cs.RO↗

arXiv2026

DexTaG: Tactile-as-Guidance in Reinforcement Learning for Dexterous Manipulation

Glove-based motion capture is emerging as a scalable approach to collecting dexterous-hand demonstration data. However, due to the kinematic gap between the human and robot hand, the recorded human motions cannot be executed directly on the robot, especially for contact-rich tool-use tasks involving in-hand reorientation. Prior work bridges this gap in simulation through reinforcement learning (RL) or trajectory optimization, but the human contact pattern is hard to preserve under such formulations, often producing unnatural manipulation and unstable functional grasps. These methods also train a separate policy or solve a separate optimization for each reference trajectory, which is inefficient. To solve these problems, we propose DexTaG, a tactile-guided RL framework for dexterous manipulation. During training, tactile signals captured by the glove guide policy search toward the measured human contact pattern, reducing reliance on precise reference geometry for contact supervision. To improve efficiency, we train a single generalizable retargeter jointly on all training trajectories of the same object. The retargeter is further distilled into a tactile-free student controller conditioned on the target object trajectory for real-world deployment. On marker-pen and hammer manipulation tasks, DexTaG learns natural, contact-rich behaviors that baselines with distance-based contact heuristics fail to learn, generalizes to held-out trajectories of the same object and task, and outperforms single-trajectory baselines on OakInk2.

cs.RO↗

arXiv2026

SyncWorld: Visual Calibration Enables World Models as Zero-Shot Simulators

World models are increasingly used as policy-in-the-loop imagination environments, where reliable rollouts require fine-grained controllability with respect to low-level robot actions. A key obstacle to scaling such models in robotics is that actions are not a universal language in pixel space: changes in visual environment, camera view, robot placement, or embodiment alter how the same numerical action manifests visually, leading to conflicting supervision under mixed training and brittle generalization at deployment. We introduce SyncWorld, an action-conditioned world model that serves as a zero-shot simulator across unseen environments without any additional training. SyncWorld leverages a visual calibration episode---paired frames and actions that showcase all the controllable degrees of freedom---to specify the setup-specific Action--Visual Mapping in context. Training with visual calibration contexts teaches the model to interpret actions through visual evidence and to leverage interaction history when explicit calibration is unavailable. Experiments show that SyncWorld can accurately simulate action outcomes in previously unseen settings, and that its capability of simulating rollouts enables test-time policy improvement without training.

cs.CV↗

arXiv2026

Learning to Allocate Incentives for Incentivized Advertising via Offline Model-Based Reinforcement Learning

Complete your ad view and grab a 5-cent bonus! In incentivized advertising, a platform promises users a bonus before observing downstream ad revenue, encouraging them to click and complete ads. It must balance the incentive promised in advance against the revenue realized afterward: insufficient incentives forfeit monetization opportunities, whereas excessive incentives reduce net profit. Because current incentives may also shape user expectations and future engagement, incentive allocation is a sequential decision problem with delayed revenue, cost sensitivity, and carryover effects. Existing work has not studied decision-making algorithms for this setting. Auto-bidding assumes available ad opportunities, while targeted promotion optimizes incentives outside the ad monetization pipeline. We formulate the problem as an MDP and develop an offline model-based RL framework for cost-controllable sequential incentive allocation. It learns a world model of user feedback and ad revenue, then performs conservative policy optimization. An independent counterfactual scorer evaluates each learned policy on held-out logs, enabling pre-launch selection without costly online exposure. Experiments on large-scale industrial data and online A/B tests show that the scorer provides a stable offline signal. The deployment path from causal inference to offline RL and then Offline-MBRL further validates the framework: MB-IQL improves per-user net profit by 7.96\% over TD3+BC, whereas reverting to plain IQL reduces it by 6.56\% (both $p<0.0001$).

cs.AI↗

arXiv2026

A Structural Dynamics Graph World Model: Unified Modeling, Constrained Rollout, and Interpretable Calibration

The state evolution of a complex system arises jointly from object laws, relational propagation, domain conservation, and unmodeled error. Forcing all sources into one black box makes mechanism attribution and constraint preservation unauditable; forcing every mechanism into one equation family discards mature domain solvers. We propose SD-GWM, a Structural Dynamics Graph World Model as an executable structural contract: nodes declare self-dynamics S, edges declare neighbor graph-coupled dynamics N---both fixed-form mechanism assets (rules, ODEs, solvers) calibrating only authorized parameters. An optional bounded residual R concentrates learnability, while a global projection maps states to feasibility, enforcing constraints without guaranteeing accuracy gains. On eight pre-registered research questions, SD-GWM delivers (i) heterogeneous integration: rules and solvers plug in natively; (ii) semantic fidelity: disabling R preserves source semantics bit-for-bit, with four theory properties under explicit proof/empirical boundaries; (iii) auditable governance: stepwise traces enable counterfactual fault localization (top-1 = 1.0) without post-hoc approximations. On a semi-synthetic flood testbed and USGS streamflow, SD-GWM reduces constraint violations to floating-point tolerance in analytical tests and to zero in semi-synthetic and real-data cases. Persistence matches SD-GWM in calm periods, but during a 254-day extreme-flood shift persistence and all neural baselines collapse (90-min RMSE 892-3007 cfs) while SD-GWM holds at 108 cfs (8-28x gain). The bounded residual cuts RMSE ~50% only under backbone bias. We position SD-GWM not as a universally superior forecaster, but as a verifiable substrate for auditable, constraint-safe spatiotemporal mining.

cs.AI↗

arXiv2026

An $H^{-1}$ least-squares UnCut FEM on domains defined by a level set function

We propose a novel UnCut finite element method (FEM) for the Poisson and Stokes equations on domains with curved boundaries represented by a level set function. Like the $ϕ$-FEM, the method avoids numerical integration over cut subregions of boundary elements, but introduces a novel least-squares formulation that minimizes an $H^{-1}$ residual of the governing equations. This formulation ensures stability without requiring large stabilization parameters, thereby eliminating the need for user-tuned penalty parameters and improving the robustness of the computation. Optimal-order convergence of the UnCut FEM solutions is rigorously established in the $H^1$ norm for both the Poisson and Stokes equations, and numerical experiments are presented to support the theoretical analysis.

math.NA↗

arXiv2026

Active Passivation Tunes Hotspot Locations in GaN Transistors with In Situ Thermal Mechanical Visualization

Efficient thermal dissipation has become critical in emerging electronic devices. However, most existing studies have primarily focused on engineering heat dissipation pathways, largely overlooking the intrinsic behavior of the heat source itself. We demonstrate an active passivation technology that proactively tunes hotspot locations in GaN transistors. By adjusting the active passivation layer length, the hotspot is shifted from the gate edge to the drain-side AP edge, establishing a clear one-to-one spatial correlation. In-situ thermal-mechanical visualization via micro-Raman thermography, combined with multi-physics electro-thermal-mechanical simulations, directly captures the spatial redistribution of both temperature and thermal stress profiles. Electrical analysis confirms that this hotspot migration is driven by the spatial shift of the peak electric field and localized Joule heating. This proactive heat-source tuning strategy provides critical design guidelines for power electronics.

physics.app-ph↗

arXiv2026

AutoNeural: Co-Designing Vision-Language Models for NPU Inference

While Neural Processing Units (NPUs) offer high theoretical efficiency for edge AI, state-of-the-art Vision--Language Models (VLMs) tailored for GPUs often falter on these substrates. We attribute this hardware-model mismatch to two primary factors: the quantization brittleness of Vision Transformers (ViTs) and the I/O-bound nature of autoregressive attention mechanisms, which fail to utilize the high arithmetic throughput of NPUs. To bridge this gap, we propose AutoNeural, an NPU-native VLM architecture co-designed for integer-only inference. We replace the standard ViT encoder with a MobileNetV5-style backbone utilizing depthwise separable convolutions, which ensures bounded activation distributions for stable INT4/8/16 quantization. Complementing this, our language backbone integrates State-Space Model (SSM) principles with Transformer layers, employing efficient gated convolutions to achieve linear-time complexity. This hybrid design eliminates the heavy memory I/O overhead of Key-Value caching during generation. Our approach delivers substantial efficiency gains, reducing quantization error of vision encoder by up to 7x and end-to-end latency by 14x compared to conventional baselines. The AutoNeural also delivers 3x decoding speed and 4x longer context window than the baseline. We validate these improvements via a real-world automotive case study on the Qualcomm SA8295P SoC, demonstrating real-time performance for cockpit applications. Our results highlight that rethinking model topology specifically for NPU constraints is a prerequisite for robust multi-modal edge intelligence.

cs.CL↗

arXiv2026

TopoRetarget: Interaction-Preserving Retargeting for Dexterous Manipulation

Human hand-object demonstrations provide dense reference motions for training dexterous manipulation reinforcement learning (RL) policies through reference tracking. However, to use such demonstrations for RL policy learning, retargeting must preserve hand pose and task-relevant hand-object contact structure. Otherwise, contact and feasibility artifacts can degrade downstream RL policy performance. We introduce TopoRetarget, an interaction-preserving retargeting framework that uses a single set of parameters across diverse retargeting conditions while maintaining task-relevant hand-object interaction and adapting human demonstrations to dexterous robot hands. The method constructs a sparse interaction graph over hand and object keypoints and optimizes distance-weighted Laplacian deformation with directional consistency, kinematic constraints, and penetration handling. Evaluations show that the generated references improve both interaction fidelity and policy learning: TopoRetarget achieves the best contact precision and alignment over all baselines on the ContactPose Dataset, improves Pen-Spin training success by 40.6 percentage points over the existing baseline methods, and enables zero-shot transfer to Wuji Hand hardware on cube reorientation and pen spinning.

cs.RO↗

arXiv2026

Classification of weak Bruhat interval modules of $0$-Hecke algebras

Weak Bruhat interval modules of the $0$-Hecke algebra in type $A$ offer a unified framework for studying modules associated to quasisymmetric functions. This class of modules has recently been generalized from type $A$ to all Coxeter types. In this paper, we give an equivalent description, in a type-independent manner, when two left weak Bruhat intervals in a Coxeter group are descent-preserving isomorphic. As an application, we classify all weak Bruhat interval modules of $0$-Hecke algebras up to isomorphism, and thereby answering an open question of Jung-Kim-Lee-Oh and confirming a conjecture of Kim-Lee-Oh. Furthermore, for finite Coxeter groups, we show that the set of minimum (respectively, maximum) elements of all left weak Bruhat intervals within each descent-preserving isomorphism class forms an interval under the right weak Bruhat order.

math.RT↗

arXiv2026

When Knowledge Is Not Free: Cost-Aware Evidence Selection in Retrieval-Augmented Generation

Retrieval-Augmented Generation (RAG) typically assumes that external knowledge is free, but many high-quality sources are paywalled, licensed, restricted, or otherwise costly to access. We introduce cost-aware RAG, a setting where retrieved evidence is assigned access-cost tiers and systems must answer under an explicit evidence-access budget. We instantiate this setting by augmenting MS MARCO v2.1 with access-friction tiers and evaluate budgeted evidence selection across general-domain and domain-specific QA benchmarks. Our results show that static selection is brittle: no fixed selector uniformly dominates, and larger budgets do not reliably improve answer quality, even when costly evidence is domain-matched. We then study agentic cost-aware RAG, where an LLM decides when to retrieve, which tier to access, and when to stop. Agents show strong promise as adaptive evidence-acquisition controllers, but their behavior remains highly model- and task-dependent. These findings suggest that cost-aware evidence acquisition is a central challenge for the next generation of RAG systems. All code and data are available at https://github.com/Mignonmy/Cost-Aware.

cs.CL↗

arXiv2026

MatterSim-MT: A multi-task foundation model for in silico materials characterization

Accurate property characterization is a major bottleneck in materials design. While first-principles methods and task-specific machine-learning models have driven important progress, they remain fundamentally limited in scalability and generalizability across the vast space of structures and properties relevant to real-world materials design. We present MatterSim-MT, a multi-task foundation model for in silico materials simulation and property characterization. The model is pretrained on over 35 million first-principles-labeled structures covering 89 elements, temperatures up to 5000 K and pressures up to 1000 GPa, and is fine-tuned on various properties including Bader charges, magnetic moments, Born effective charges, and dielectric matrices. Out of the box, MatterSim-MT not only serves as a foundation model for predicting material structure, dynamics and thermodynamics, its multi-task architecture also enables a wide range of complex simulations that cannot be captured by potential energy surfaces alone. For example, we demonstrate pressure-dependent LO-TO phonon splitting in SiC with close agreement with experiment, electric hysteresis in ferroelectric BaTiO3, and the cationic-to-anionic redox transition during delithiation of a Li-rich cathode material. Finally, we show that MatterSim-MT scales well with more data and parameters, can be efficiently fine-tuned to higher levels of theory, and can be efficiently extended to new systems via active learning. Overall, we believe this approach provides a scalable route to accurate in silico materials characterization.

cond-mat.mtrl-sci↗

arXiv2026

Simultaneous Contact Selection and Planning for Contact-Rich Manipulation with Cascaded Optimization

We propose an optimization-based framework for robust contact-rich manipulation. Recent contact-implicit methods enable online hybrid planning across contact modes, allowing closed-loop manipulation for a given target state and contact location sequence of the robot and object. However, most existing approaches lack the ability to autonomously reason and generate diverse contact location sequences and manipulation trajectories, i.e., active contact location selection, which limits their applicability to relatively simple tasks. Active contact location selection is challenging due to complementarity in contact dynamics and the sparse gradients, making the design of a unified framework for contact selection and planning difficult. To address these challenges, we introduce Simultaneous Contact Selection and Planning (SCSP), a cascaded optimization framework comprising Contact Selection Optimization (CSO) and Contact Planning Optimization (CPO). CSO leverages a surrogate contact model and discrete-continuous optimization to efficiently resolve the nonsmoothness and coupling in contact selection, enabling online global searching of optimal contact locations. CPO performs prior-guided contact planning by evaluating the reference contact locations produced by CSO and generating corresponding manipulation trajectories in real time for redundant manipulators. Extensive simulations and real-world experiments demonstrate that SCSP produces diverse manipulation behaviors and robust control under inaccurate dynamics and perceptual noise. We further validate the generalization of the framework on challenging manipulation tasks. Project website: \href{https://sites.google.com/view/scsp-robot}{https://sites.google.com/view/scsp-robot}.

cs.RO↗

arXiv2026

Co-creation of AI technology, empowering curators of cultural heritage information and guarding research commons

The substance of this paper is the description of the use of Retrieval-Augmented Generation (RAG) for specific digital collections of cultural assets. The collections are provided by institutions operating in the cultural sector. The topical areas are the humanities and social sciences. More concretely, most of the work presented here was enabled by a European-funded research project MuseIT which is clearly situated in the realm of fostering new technologies for Cultural Heritage. We adhere to this interaction by presenting a sequence of our experimentations. This sequence is narrated as a specific journey of engineering all executed around a specific data-sharing and archiving platform Dataverse. Implementing a local chatbot for collections - a method also known as RAG in Information Retrieval - is the current culmination of this journey. The engineering journey we describe in the core of the paper starts from "archives for everyone" and ends with "local chatbots for specific collections".

cs.DL↗

arXiv2026

Enhancing 3D Semantic Scene Completion with a Refinement Module

We propose ESSC-RM, a plug-and-play Enhancing framework for Semantic Scene Completion with a Refinement Module, which can be seamlessly integrated into existing SSC models. ESSC-RM operates in two phases: a baseline SSC network first produces a coarse voxel prediction, which is subsequently refined by a 3D U-Net-based Prediction Noise-Aware Module (PNAM) and Voxel-level Local Geometry Module (VLGM) under multiscale supervision. Experiments on SemanticKITTI show that ESSC-RM consistently improves semantic prediction performance. When integrated into CGFormer and MonoScene, the mean IoU increases from 16.87% to 17.27% and from 11.08% to 11.51%, respectively. These results demonstrate that ESSC-RM serves as a general refinement framework applicable to a wide range of SSC models.

cs.CV↗