Search arXiv⌕ Search

arXiv subjects

Jin Yang

Publications and source records attributed to Jin Yang.

At least 37 records · Page 2Linked to original sources
arXiv2026

Differential Amplifier-Inspired AmpAttention for Multi-View Robotic Manipulation

Multi-view robotic manipulation methods with the attention mechanism have recently achieved significant progress in both training efficiency and task performance. However, the inherent redundancy, occlusion, and viewpoint dependency in robotic view images often lead to severe attention drift. To address this challenge, we propose AmpAttention, a novel attention mechanism inspired by differential amplifiers in analog circuits. It aims to suppress attention noise and capture high signal-to-noise ratio signals for more reliable perception. Based on this, we introduce the RVAF model, which integrates task-guided intra-view and inter-view AmpAttention. Compared to previous state-of-the-art methods, RVAF achieves the optimal average success rate across 18 RLBench tasks (249 variations) while reducing training time by 33.3\%. RVAF also demonstrates strong potential in real-world high-precision tasks, exemplified by its ability to pick up a dart and accurately insert it into the red bullseye. Furthermore, we extend RVAF to RVAF++ by incorporating the SAM2 image encoder. RVAF++ achieves substantial gains on high-precision tasks, achieving a 91\% success rate on the `insert peg' task. More qualitative results are provided at the anonymous project website https://anonymous.4open.science/w/RVAF-Anonymization.

cs.RO↗
arXiv2026

Source Side Mitigation of AI Datacenter Power Fluctuations with a Hybrid Energy Storage System and Residual Differentiable Predictive Control

The rapid growth of hyperscale AI datacenters introduces structured, workload-driven active-power fluctuations at the point of interconnection. These fluctuations appear to the grid as time-varying disturbance injections that cannot be captured by conventional peak- or average-load representations. To reduce the residual power disturbance before it propagates into the bulk power system, this paper proposes a hybrid energy storage system with differentiable predictive control (HESS-DPC) framework for datacenter-side power smoothing. A workload-driven disturbance model is first established, representing the point-of-interconnection load deviation as the superposition of training and fine-tuning workloads to capture the structured forcing inputs that can excite generator frequency dynamics. A frequency-based rule-based controller then allocates this deviation between a battery energy storage system (BESS) and a supercapacitor (SC), assigning the energy-dominant component to the BESS and the fast-varying component to the SC. To overcome the anticipation and constraint limitations of fixed-frequency decomposition, a residual differentiable predictive control policy is trained offline to compute finite-horizon command corrections around the rule-based baseline while enforcing a one-step safeguard. Simulations on the NPCC 140-bus system show that HESS-DPC reduces grid-side residual deviations during workload transitions, improves SC state-of-charge sustainability over extended operation, and reduces generator peak-to-peak frequency deviations by more than 80 percent across all monitored generators, with the worst-affected generator response falling from 15.1 mHz to 1.3 mHz. These results confirm that local active-power smoothing at the datacenter point of interconnection can substantially mitigate frequency disturbances caused by AI workloads.

eess.SY↗
arXiv2026

Beyond Scaling Law: A Data-Efficient Distillation Framework for Reasoning

Large language models (LLMs) demonstrate remarkable reasoning capabilities in tasks such as algorithmic coding and mathematical problem-solving. Recent methods have improved reasoning through expanded corpus and multistage training combining reinforcement learning and supervised fine-tuning. Although some methods suggest that small but targeted dataset can incentivize reasoning via only distillation, a reasoning scaling laws is still taking shape, increasing computational costs. To address this, we propose a data-efficient distillation framework (DED) that optimizes the Pareto frontier of reasoning distillation. Inspired by the on-policy learning and diverse roll-out strategies of reinforcement learning, the key idea of our approach is threefold: (1) We identify that benchmark scores alone do not determine an effective teacher model. Through comprehensive comparisons of leading reasoning LLMs, we develop a method to select an optimal teacher model. (2) While scaling distillation can enhance reasoning, it often degrades out-of-domain performance. A carefully curated, smaller corpus achieves a balanced trade-off between in-domain and out-of-domain capabilities. (3) Diverse reasoning trajectories encourage the student model to develop robust reasoning skills. We validate our method through evaluations on mathematical reasoning (AIME 2024/2025, MATH-500) and code generation (LiveCodeBench), achieving state-of-the-art results with only 0.8k carefully curated examples, bypassing the need for extensive scaling. Our systematic analysis demonstrates that DED outperforms existing methods by considering factors beyond superficial hardness, token length, or teacher model capability. This work offers a practical and efficient pathway to advanced reasoning while preserving general capabilities.

cs.LG↗
arXiv2026

Ling and Ring 2.6 Technical Report: Efficient and Instant Agentic Intelligence at Trillion-Parameter Scale

Efficient and scalable agentic intelligence requires models that can deliver both low-latency responses and strong reasoning capabilities while remaining practical to train, serve, and deploy. In this report, we present Ling-2.6 and Ring-2.6, a family of models designed to address this challenge at scale. Ling-2.6 is optimized for instant response generation and high capability per output token, whereas Ring-2.6 is tailored for deeper reasoning and more advanced agentic workflows. Instead of training from scratch, we upgrade the Ling-2.0 base model through architectural migration pre-training and large-scale post-training. This upgrade is guided by a unified co-design of model architecture, optimization objectives, serving systems, and agent training environments, enabling improvements in both model capability and deployment efficiency. At the architectural level, we introduce a hybrid linear attention design that integrates Lightning Attention with MLA, improving the efficiency of long-context training and decoding. To further enhance token efficiency, we optimize capability per output token through Evolutionary Chain-of-Thought, Linguistic Unit Policy Optimization, bidirectional preference alignment, and shortest-correct-response distillation. For agentic capabilities, we propose KPop, a reinforcement learning framework designed to support stable training of Ring-2.6-1T on large-scale environment-grounded data. KPop improves training efficiency through asynchronous scheduling across coding, search, tool use, and workflow execution, enabling scalable learning from complex agent-environment interactions. Together, Ling-2.6 and Ring-2.6 provide a practical pathway toward efficient, scalable, and open agentic systems. We open-source all checkpoints in the 2.6 family to support further research and development in practical agentic intelligence.

cs.CL↗
arXiv2026

Active Source-free Domain Adaptation in Open-set Medical Image Segmentation via Decomposed Uncertainty and Prototype Discrepancy

Deep learning (DL) methods are challenged to demonstrate robust performance across different segmentation datasets due to domain shifts, but active domain adaptation techniques enhance their generalization performance by querying a few samples from target domains for adaptation training. However in clinical practice, target domains often include private classes of new anatomical structures or pathologies that are not presented in the source data, and existing methods implement closed-set segmentation where source and target domains have the same segmentation classes. Additionally, source data are often inaccessible during adaptation due to strict data privacy regulations. To address these limitations, we propose an Active Source-free Open-set Domain Adaptation (ASFOSDA) method which is the first work to implement active learning for adapting DL models in open-set medical image segmentation without the access to source data. This method employs an active open-set query strategy to select the most informative target samples for training models based on Class-aware Decomposed Uncertainty (CDU) and Class-agnostic Prototype Discrepancy (CPD). CDU measures sample aleatoric uncertainty and model epistemic uncertainty by employing test time augmentation in stochastic processes. CPD measures cross-domain and self-domain discrepancy for selecting diverse samples. Subsequently, to boost the adaptation performance by enhancing training samples, a Target-refined Self-training strategy is proposed to generate high-quality pseudo labels for unselected samples, thus combining them with labeled samples for a semi-supervised training. We evaluated our method on cross-domain open-set volumetric medical image segmentation tasks, and it outperformed state-of-the-art adaptation methods.

eess.IV↗
arXiv2026

Coexistence Regime and Thermal Crystallization in the cavity-mediated extended Bose-Hubbard Model

By means of path integral- Monte Carlo, we study the finite-temperature behavior of the extended Bose-Hubbard model with cavity-mediated long-range interactions at unit filling. At zero temperature, the system supports superfluid, Mott-insulating, supersolid, and charge-density-wave phases, with a strongly first-order transition between superfluid and charge density wave states characterized by a broad coexistence region. Focusing on this coexistence regime, we explore how the dominant order evolves with temperature. When the system is initialized in a superfluid state, the superfluid density is progressively suppressed upon heating, and a normal fluid is stabilized. Upon further increasing the temperature, a thermally assisted emergence of crystalline order occurs which eventually melts into the normal fluid. In contrast, simulations initialized in a charge-density-wave configuration display a smooth thermal melting of density order, with no reemergence of superfluid coherence. Overall, our results show that metastability persists at low temperatures, but ultimately disappears at higher temperatures, where thermally induced crystallization takes place.

cond-mat.quant-gas↗
arXiv2026

Full-Field Calibration of Coupled Thermomechanical Material Models at Finite Strain

Calibrating thermomechanical material models from experiments is challenging because deformation, temperature, and force responses are strongly coupled, while measurements are usually restricted to specimen surfaces. We present a full-field calibration framework for coupled finite-strain thermomechanical material models using boundary displacement, reaction-force data, and temperature. The forward model is formulated as a near-incompressible thermo-hyperelastic problem with thermomechanical coupling derived from a Helmholtz free energy, and the inverse problem is posed as a PDE-constrained optimization problem with weighted observation terms for the available data streams. Reduced gradients are computed with adjoint sensitivities that are obtained by automatic differentiation, enabling gradient-based calibration of nonlinear transient thermomechanical systems. The formulation is first verified on synthetic examples involving uniform thermal preconditioning and localized transient rod contact, where the ground-truth parameters are recovered from full-field measurements and force observations. The same workflow is then applied to experimental thermomechanical data by first calibrating a hyperelastic mechanical baseline from cyclic equibiaxial loading and subsequently identifying thermal expansion and directional shrinkage parameters from surface-temperature and boundary-force histories. The results demonstrate that coupled thermomechanical parameters can be inferred from experimentally accessible surface data without requiring volumetric observations.

cs.CE↗
arXiv2026

Dynamics of Cognitive Heterogeneity: Investigating Behavioral Biases in Multi-Stage Supply Chains with LLM-Based Simulation

Modeling coordination among generative agents in complex multi-round decision-making presents a core challenge for AI and operations management. Although behavioral experiments have revealed cognitive biases behind supply chain inefficiencies, traditional methods face scalability and control limitations. We introduce a scalable experimental paradigm using Large Language Models (LLMs) to simulate multi-stage supply chain dynamics. Grounded in a Hierarchical Reasoning Framework, this study specifically analyzes the impact of cognitive heterogeneity on agent interactions. Unlike prior homogeneous settings, we employ DeepSeek and GPT agents to systematically vary reasoning sophistication across supply chain tiers. Through rigorously replicated and statistically validated simulations, we investigate how this cognitive diversity influences collective outcomes. Results indicate that agents exhibit myopic and self-interested behaviors that exacerbate systemic inefficiencies. However, we demonstrate that information sharing effectively mitigates these adverse effects. Our findings extend traditional behavioral methods and offer new insights into the dynamics of AI-enabled organizations. This work underscores both the potential and limitations of LLM-based agents as proxies for human decision-making in complex operational environments.

cs.MA↗
arXiv2026

From Accounting to Coordination: A Virtual Water-Aware Electricity-Computation-Water Nexus Framework for Data Center Dispatch

The expansion of data centers (DCs) drives a sustained increase in electricity demand and associated water withdrawals at generation sites. These withdrawals occur at generation sites and are virtually allocated to demand based on network power flows. Consequently, the actual water footprint of a specific load varies dynamically with generation dispatch and network conditions. Existing approaches typically rely on static statistical accounting to quantify these water footprints. However, such static methods fail to capture how dispatch optimization and workload relocation dynamically affect water withdrawals. As a result, static statistical accounting approaches remain decoupled from the optimization process, rendering them incapable of guiding workload relocation or power dispatch to mitigate water stress. To address this limitation, this paper develops an operational electricity-computation-water (ECW) nexus framework that internalizes virtual water impacts directly into power system dispatch. The framework represents dispatch optimization as a differentiable optimization layer embedded within a deep learning architecture, enabling efficient end-to-end learning of coordination policies while preserving operational feasibility. Combined with fixed-point coordination, the framework enforces consistency between virtual water attribution and physical generation-side withdrawals. Case studies on the IEEE 30-bus and 118-bus test systems demonstrate reliable convergence, exact power-water consistency, and reductions of approximately 3-5% in generation-related freshwater withdrawals under water-constrained conditions.

cs.AI↗
arXiv2026

Three-Stage Learning Unlocks Strong Performance in Simple Models for Long-Term Time Series Forecasting

Recent studies on long-term time series forecasting have shown that simple linear models and MLP-based predictors can achieve strong performance without increasingly complex architectures. However, many competitive baselines still rely on structural priors such as frequency-domain modeling, explicit decomposition, multi-scale mixing, or sophisticated cross-variable interaction modules, while paying less attention to how simple temporal mappings should be trained and organized. In this paper, we propose STAIR, short for Stagewise Temporal Adaptation via Individualization and Residual Learning, a training paradigm for long-term time series forecasting that aims to unlock the capacity of simple temporal mapping models without introducing complex architectural modules. STAIR decomposes forecasting ability into three progressive stages: it first learns common temporal dynamics across variables through a shared temporal mapping, then adapts the shared model to each variable via channel-wise fine-tuning to capture variable-specific patterns, and finally complements the backbone with cross-variable information through residual learning. We further introduce Shared-to-Individual Fine-tuning and alpha-RevIN to mitigate the limitations of strict channel independence and the overly strong normalization prior induced by standard RevIN. This design gradually increases modeling flexibility while keeping the core temporal predictor as a shallow MLP in the main experiments, with linear variants analyzed separately. Experiments on nine long-term forecasting benchmarks show that STAIR matches or outperforms recent strong baselines while preserving a simple temporal backbone, providing a concise and effective modeling perspective for long-term time series forecasting.

cs.LG↗
arXiv2026

FEFormer: Frequency-enhanced Vision Transformer for Generic Knowledge Extraction and Adaptive Feature Fusion in Volumetric Medical Image Segmentation

Accurate segmentation of organs and lesions in medical images is essential for clinical applications including diagnosis, prognosis, and treatment planning. While Vision Transformers (ViTs) have shown impressive segmentation performance, they face key challenges in module and architecture design. Specifically, self-attention struggles to capture fine-grained local features critical for understanding detailed anatomical structures, standard MLP modules lack explicit mechanisms to preserve spatial information, conventional encoder-decoder architectures rely on naive feature fusion strategies that cannot handle large semantic discrepancies, and existing designs lack explicit mechanisms to propagate low-level information from encoder to decoder. To address these limitations, we propose a Frequency-enhanced Vision Transformer (FEFormer) for robust and efficient volumetric medical image segmentation that explicitly models frequency information to jointly capture global context and fine structural details. FEFormer comprises four novel components: a Frequency-enhanced Dynamic Self-Attention (FDSA) module that jointly captures fine-grained local details and global long-range dependencies through locality-preserving convolution with frequency-domain attention; a Frequency-decomposed Gating MLP (FGMLP) that adaptively models low- and high-frequency components for enhanced semantic and structural representation; a Wavelet-guided Adaptive Feature Fusion (WAFF) module that enables semantically consistent encoder-decoder feature integration in the frequency domain; and a Frequency-enabled Cross-scale Stem Bridge (FCSB) that enhances low-level feature propagation across scales. Evaluated on four diverse volumetric medical image segmentation tasks, FEFormer achieved superior segmentation performance with high computational efficiency compared to state-of-the-art methods.

eess.IV↗
arXiv2026

Floquet-tuned superfluid-checkerboard competition in dipolar bosons

We study hard-core dipolar bosons on a square lattice subject to a unidirectional periodic drive that Floquet-engineers anisotropic hopping. Driving along one lattice direction provides a controlled way to suppress transverse tunneling, yielding a kinetically quasi-one-dimensional regime with strongly anisotropic transport within the leading-order high-frequency Floquet effective description. In this limit, the system does not reduce to decoupled chains, due to the long-range in-plane dipolar interaction remains isotropic and couples different chains. Focusing on dipoles polarized perpendicular to the plane, for which the interaction is purely repulsive and isotropic, we use sign-problem-free worm-algorithm quantum Monte Carlo simulations to map the half-filling phase diagram versus kinetic anisotropy and dipolar coupling. We find that increasing kinetic anisotropy systematically lowers the interaction strength required to stabilize checkerboard order, demonstrating that Floquet-induced suppression of transverse motion enhances density ordering. Near the superfluid--checkerboard boundary, finite-size results reveal a narrow transition region where the stiffness drops rapidly while checkerboard correlations rise sharply; Its pronounced sharpening with system size is consistent with a weakly first-order transition rounded by finite-size effects. Away from half filling, on the doped sides of the checkerboard plateau, we identify a narrow checkerboard-supersolid regime with simultaneously finite checkerboard correlations and superfluid stiffness, where the superfluid stiffness is anisotropic but the density pattern is isotropic.

cond-mat.quant-gas↗
arXiv2026

Adapting Medical Vision Foundation Models for Volumetric Medical Image Segmentation via Active Learning and Selective Semi-supervised Fine-tuning

Medical vision foundation models remain limited in downstream tasks, particularly volumetric medical image segmentation. While fine-tuning on labeled target-domain data improves performance, existing approaches typically rely on randomly selected samples, which may fail to identify the most informative data and thus hinder adaptation. To address the limitations, we propose an Active Selective Semi-supervised Fine-tuning framework for efficient adaptation of Med-VFMs to generalize across volumetric medical image segmentation. ASSFT integrates a novel active learning strategy with selective semi-supervised learning to maximize adaptation performance under a limited annotation budget, without requiring access to source data. Specifically, we introduce an Active Test-Time Sample Query strategy that identifies informative samples from the target domain using two complementary query metrics: Diversified Knowledge Divergence and Anatomical Segmentation Difficulty. DKD quantifies both the knowledge gap between pre-training and target domains and the semantic diversity within the target dataset, enabling the selection of samples that contain previously unlearned knowledge while maintaining intra-domain diversity. ASD estimates the segmentation difficulty of target anatomical structures by measuring predictive uncertainty within foreground regions of interest, allowing the model to prioritize samples with complex anatomical patterns rather than those dominated by background uncertainty. Second, we propose a Selective Semi-supervised Fine-tuning strategy to further improve adaptation performance by leveraging unlabeled target samples. Instead of utilizing all pseudo-labeled data, the proposed method selectively incorporates reliable unlabeled samples based on predictive confidence and semantic distance to labeled samples, enabling stable semi-supervised training while avoiding noisy pseudo-labels.

eess.IV↗
arXiv2026

Copula-enhanced Vision Transformer for high myopia diagnosis through OU UWF fundus images

The advancement of AI-assisted myopia screening necessitates the joint diagnosis of both-eye (OU) high myopia (HM) status and the prediction of axial length (AL). This clinical requirement introduces a complex mixed-type (binary-continuous) multitask learning task with bi-domain (OU) image covariates, giving rise to two key challenges: i) capture the inter-ocular asymmetry of OU images within a cutting-edge foundation model; ii) model and estimate the conditional dependence structure among mixed-type multivariate responses given image covariates. We address the challenges by: i) imposing residual adapters on the Vision Transformer foundation model to capture the OU similarity and heterogeneity simultaneously; ii) developing a four-dimensional copula loss that is implementable in PyTorch based on a latent variable expression for the Gaussian copula likelihood, and proposing a computationally efficient fast Monte Carlo Expectation Maximization (fMCEM) algorithm to estimate copula parameters. We further formulate a specific overfitting problem called stronger covariance phenomenon in multitask learning. We reveal the disturbance of the phenomenon to estimation of copula parameters and theoretically demonstrate the numerical stability of the proposed fMCEM algorithm against the disturbance. The application to our annotated OU ultra-widefield fundus image dataset and simulation on synthetic data demonstrate that our method stably enhances the predictive capabilities on both classification and regression tasks.

cs.CV↗
arXiv2026

Covariance test for discretely observed functional data: when and how it works?

For covariance test in functional data analysis, existing methods are developed only for fully observed curves, whereas in practice, trajectories are typically observed discretely and with noise. To bridge this gap, we employ a pool-smoothing strategy to construct an FPC-based test statistic, allowing the number of estimated eigenfunctions to grow with the sample size. This yields a consistently nonparametric test, while the challenge arises from the concurrence of diverging truncation and discretized observations. Facilitated by advancing perturbation bounds of estimated eigenfunctions, we establish that the asymptotic null distribution remains valid across permissable truncation levels. Moreover, when the sampling frequency (i.e., the number of measurements per subject) reaches certain magnitude of sample size, the test behaves as if the functions were fully observed. This phase transition phenomenon differs from the well-known result of the pooling mean/covariance estimation, reflecting the elevated difficulty in covariance test due to eigen-decomposition. The numerical studies, including simulations and real data examples, yield favorable performance compared to existing methods.

stat.ME↗
arXiv2026

LLM-Enhanced Multi-Agent Reinforcement Learning with Expert Workflow for Real-Time P2P Energy Trading

Real-time peer-to-peer (P2P) electricity markets dynamically adapt to fluctuations in renewable energy and variations in demand, maximizing economic benefits through instantaneous price responses while enhancing grid flexibility. However, scaling expert guidance for massive personalized prosumers poses critical challenges, including diverse decision-making demands and a lack of customized modeling frameworks. This paper proposes an integrated large language model-multi-agent reinforcement learning (LLM-MARL) framework for real-time P2P energy trading to address challenges such as the limited technical capability of prosumers, the lack of expert experience, and security issues of distribution networks. LLMs are introduced as experts to generate personalized strategies, guiding MARL under the centralized training with decentralized execution (CTDE) paradigm through imitation. To handle the scalability issues inherent in large-scale P2P networks, a differential attention-based critic network is introduced to efficiently extract key interaction features and enhance convergence. Experimental results demonstrate that LLM-generated strategies effectively substitute human experts. The proposed imitative expert MARL algorithms achieve significantly lower economic costs and voltage violation rates on test sets compared to baseline algorithms, while maintaining robust stability. This paper provides an effective solution for the real-time decision-making of the P2P electricity market by bridging expert knowledge with agent learning.

cs.MA↗
arXiv2026

TextBFGS: A Case-Based Reasoning Approach to Code Optimization via Error-Operator Retrieval

Iterative code generation with Large Language Models (LLMs) can be viewed as an optimization process guided by textual feedback. However, existing LLM self-correction methods predominantly operate in a stateless, trial-and-error manner akin to first-order search, failing to leverage past problem-solving experiences. To bridge this gap, we introduce TextBFGS, a Case-Based Reasoning (CBR) framework inspired by the Quasi-Newton optimization method. Instead of retrieving raw, unstructured textual instances, TextBFGS maintains a dynamic Case Base of historical "Error-to-Operator" correction trajectories to approximate the semantic curvature (inverse Hessian matrix) of the task. Specifically, given a textual error feedback (the target problem), TextBFGS retrieves analogous historical correction patterns (Retrieve) and applies these abstract operators to refine the current code (Reuse/Revise). Furthermore, successful adaptations are continuously retained back into the Case Base (Retain), enabling a self-evolving system. Empirical evaluations on Python code optimization tasks (HumanEval, MBPP) demonstrate that TextBFGS significantly outperforms stateless baselines. It achieves superior pass rates with fewer model calls, establishing an efficient, experience-driven paradigm for LLM-based code optimization.

cs.LG↗
arXiv2026

Hyperbolic Multiview Pretraining for Robotic Manipulation

3D-aware visual pretraining has proven effective in improving the performance of downstream robotic manipulation tasks. However, existing methods are constrained to Euclidean embedding spaces, whose flat geometry limits their ability to model structural relations among embeddings. As a result, they struggle to learn structured embeddings that are essential for robust spatial perception in robotic applications. To this end, we propose HyperMVP, a self-supervised framework for \underline{Hyper}bolic \underline{M}ulti\underline{V}iew \underline{P}retraining. Hyperbolic space offers geometric properties well suited for capturing structural relations. Methodologically, we extend the masked autoencoder paradigm and design a GeoLink encoder to learn multiview hyperbolic representations. The pretrained encoder is then finetuned with visuomotor policies on manipulation tasks. In addition, we introduce 3D-MOV, a large-scale dataset comprising multiple types of 3D point clouds to support pretraining. We evaluate HyperMVP on COLOSSEUM, RLBench, and real-world scenarios, where it consistently outperforms strong baselines across diverse tasks and perturbation settings. Our results highlight the potential of 3D-aware pretraining in a non-Euclidean space for learning robust and generalizable robotic manipulation policies.

cs.RO↗