arXiv subjects

Li Zhao

Publications and source records attributed to Li Zhao.

At least 37 records · Page 2Linked to original sources

arXiv2026

MVP-LAM: Learning Action-Centric Latent Action via Cross-Viewpoint Reconstruction

Latent actions learned from diverse human videos serve as pseudo-labels for vision-language-action (VLA) pretraining, but provide effective supervision only if they remain informative about the underlying ground-truth actions. For effective supervision, latent actions should contain information about the underlying actions even though they are inaccessible. We propose Multi-ViewPoint Latent Action Moel (MVP-LAM), which learns latent actions that are highly informative about ground-truth actions from multi-view videos. MVP-LAM trains latent actions with a cross-viewpoint reconstruction objective, so that a latent action from one view must explain the future in another view, reducing reliance on viewpoint-specific cues. On Bridge V2, MVP-LAM produces more action-centric latent actions, achieving higher mutual information with ground-truth actions and improved action prediction, including under out-of-distribution evaluation. Finally, pretraining VLAs with MVP-LAM latent actions improves downstream manipulation performance on various benchmarks. The code and trained checkpoints are available at https://jmsnu.github.io.

cs.RO↗

arXiv2026

Enabling High-Accuracy Data Assimilation with Limited Ensembles via Machine Learning-Based Covariance Correction

Data assimilation (DA) integrates numerical model forecasts with observations to achieve the optimal state estimation. Ensemble-based methods, such as the ensemble Kalman filter (EnKF), are widely used for state estimation for high-dimensional and nonlinear dynamic systems. However, their performance strongly depends on the ensemble size, therefore causing a tradeoff problem between analysis accuracy and computational cost. To address this problem, this study presents a machine learning-based EnKF framework that maintains high accuracy with a relatively small ensemble size. Specifically, a multilayer perceptron (MLP) function is built to predict the difference between the forecast error covariances estimated from a limited ensemble and a sufficiently large ensemble, with the latter being assumed to be an accurate approximation of the underlying truth. This predicted covariance difference term is then incorporated into the EnKF algorithm via an element-wise scaling strategy, resulting in an amended forecast covariance matrix that better approximates the true uncertainty level and sequentially produces more accurate analysis results. To demonstrate the feasibility and robustness of the proposed algorithm, we perform a set of numerical experiments with the Lorenz-63 and Lorenz-96 systems under various configurations, and the results consistently indicate that the proposed algorithm can significantly outperform the standard EnKF with the same limited ensemble size, by achieving notably higher analysis accuracy while remaining computationally efficient. This approach provides a practical and feasible pathway to accurate and computationally efficient data assimilation for high-dimensional and nonlinear dynamic systems.

physics.ao-ph↗

arXiv2026

Reinforcing VLAs in Task-Agnostic World Models

Post-training Vision-Language-Action (VLA) models via reinforcement learning (RL) in learned world models has emerged as an effective strategy to adapt to new tasks without costly real-world interactions. However, while using imagined trajectories reduces the sample complexity of policy training, existing methods still heavily rely on task-specific data to fine-tune both the world and reward models, fundamentally limiting their scalability to unseen tasks. To overcome this, we argue that world and reward models should capture transferable physical priors that enable zero-shot inference. We propose RAW-Dream (Reinforcing VLAs in task-Agnostic World Dreams), a new paradigm that completely disentangles world model learning from downstream task dependencies. RAW-Dream utilizes a world model pre-trained on diverse task-free behaviors for predicting future rollouts, and an off-the-shelf Vision-Language Model (VLM) for reward generation. Because both components are task-agnostic, VLAs can be readily finetuned for any new task entirely within this zero-shot imagination. Furthermore, to mitigate world model hallucinations, we introduce a dual-noise verification mechanism to filter out unreliable rollouts. Extensive experiments across simulation and real-world settings demonstrate consistent performance gains, proving that generalized physical priors can effectively substitute for costly task-dependent data, offering a highly scalable roadmap for VLA adaptation.

cs.AI↗

arXiv2026

From Human Videos to Robot Manipulation: A Survey on Scalable Vision-Language-Action Learning with Human-Centric Data

Recent progress in generalizable embodied control has been driven by large-scale pretraining of Vision-Language-Action (VLA) models. However, most existing approaches rely on large collections of robot demonstrations, which are costly to obtain and tightly coupled to specific embodiments. Human videos, by contrast, are abundant and capture rich interactions, providing diverse semantic and physical cues for real-world manipulation. Yet, embodiment differences and the frequent absence of task-aligned annotations make their direct use in VLA models challenging. This survey provides a unified view of how human videos are transformed into effective knowledge for VLA models. We categorize existing approaches into four classes based on the action-related information they derive: (i) latent action representations that encode inter-frame changes; (ii) predictive world models that forecast future frames; (iii) explicit 2D supervision that extracts image-plane cues; and (iv) explicit 3D reconstruction that recovers geometry or motion. Beyond this taxonomy, we highlight three key open challenges in this area: structuring unstructured videos into training-ready episodes, grounding video-derived supervision into robot-executable actions under embodiment and viewpoint heterogeneity, and designing evaluation protocols that better predict real-world deployment performance and transfer efficiency, thereby informing future research directions. A curated list of papers and resources is available at https://github.com/AaronFengZY/HumanCentricToVLA-Survey.

cs.RO↗

arXiv2026

Causal Time Series Generation via Diffusion Models

Time series generation (TSG) synthesizes realistic sequences and has achieved remarkable success. Among TSG, conditional models generate sequences given observed covariates, however, such models learn observational correlations without considering unobserved confounding. In this work, we propose a causal perspective on conditional TSG and introduce causal time series generation as a new TSG task family, formalized within Pearl's causal ladder, extending beyond observational generation to include interventional and counterfactual settings. To instantiate these tasks, we develop CaTSG, a unified diffusion-based framework with backdoor-adjusted guidance that causally steers sampling toward desired interventions and individual counterfactuals while preserving observational fidelity. Specifically, our method derives causal score functions via backdoor adjustment and the abduction-action-prediction procedure, thus enabling principled support for all three levels of TSG. Extensive experiments on both synthetic and real-world datasets show that CaTSG achieves superior fidelity and also supporting interventional and counterfactual generation that existing baselines cannot handle. Overall, we propose the causal TSG family and instantiate it with CaTSG, providing an initial proof-of-concept and opening a promising direction toward more reliable simulation under interventions and counterfactual generation.

cs.LG↗

arXiv2026

GEAR: Granularity-Adaptive Advantage Reweighting for LLM Agents via Self-Distillation

Reinforcement learning has become a widely used post-training approach for LLM agents, where training commonly relies on outcome-level rewards that provide only coarse supervision. While finer-grained credit assignment is promising for effective policy updates, obtaining reliable local credit and assigning it to the right parts of the long-horizon trajectory remains an open challenge. In this paper, we propose Granularity-adaptivE Advantage Reweighting (GEAR), an adaptive-granularity credit assignment framework that reshapes the trajectory-level GRPO advantage using token- and segment-level signals derived from self-distillation. GEAR compares an on-policy student with a ground-truth-conditioned teacher to obtain a reference-guided divergence signal for identifying adaptive segment boundaries and modulating local advantage weights. This divergence often spikes at the onset of a semantic deviation, while later tokens in the same autoregressive continuation may return to low divergence. GEAR therefore treats such spikes as anchors for adaptive credit regions: where the student remains aligned with the teacher, token-level resolution is preserved; where it departs, GEAR groups the corresponding continuation into an adaptive segment and uses the divergence at the departure point to modulate the segment' s advantage. Experiments across eight mathematical reasoning and agentic tool-use benchmarks with Qwen3 4B and 8B models show that GEAR consistently outperforms standard GRPO, self-distillation-only baselines, and token- or turn-level credit-assignment methods. The gains are especially strong on benchmarks with lower GRPO baseline accuracy, reaching up to around 20\% over GRPO, suggesting that the proposed adaptive reweighting scheme is especially useful in more challenging long-horizon settings.

cs.LG↗

arXiv2026

What to Ignore, What to React: Visually Robust RL Fine-Tuning of VLA Models

Reinforcement learning (RL) fine-tuning has shown promise for Vision-Language-Action (VLA) models in robotic manipulation, but deployment-time visual shifts pose practical challenges. A key difficulty is that standard task rewards supervise task success, but offer limited guidance on whether a visual change is task-irrelevant or changes the behavior required for manipulation. We propose PAIR-VLA (Paired Action Invariance & Sensitivity for Visually Robust VLA), an RL fine-tuning framework to address this difficulty by adding two auxiliary objectives over paired visual variants during PPO optimization: an invariance term that reduces the discrepancy between action distributions for a task-preserving pair (e.g., different distractors), and a sensitivity objective that encourages separable action distributions for a task-altering pair (e.g., target object in a different pose). Together, these objectives turn visual variants from mere observation diversity into behavior-level guidance on policy responses during RL fine-tuning. We evaluate on ManiSkill3 across two representative VLA architectures, OpenVLA and $π_{0.5}$, under diverse out-of-distribution visual shifts including unseen distractors, texture changes, target object pose variation, viewpoint shifts, and lighting changes. Our method consistently improves over standard PPO, achieving average improvements of 16.62% on $π_{0.5}$ and 9.10% on OpenVLA. Notably, ablations further show generalization across visual shifts: invariance guidance learned from distractor and texture variants transfers to target-pose and lighting shifts, while adding sensitivity guidance on target-pose variants further improves robustness to nuisance shifts, highlighting the broader transferability of behavior-level RL guidance.

cs.RO↗

arXiv2026

WarmPrior: Straightening Flow-Matching Policies with Temporal Priors

Generative policies based on diffusion and flow matching have become a dominant paradigm for visuomotor robotic control. We show that replacing the standard Gaussian source distribution with WarmPrior, a simple temporally grounded prior constructed from readily available recent action history, consistently improves success rates on robotic manipulation tasks. We trace this gain to markedly straighter probability paths, echoing the effect of optimal-transport couplings in Rectified Flow. Beyond standard behavior cloning, WarmPrior also reshapes the exploration distribution in prior-space reinforcement learning, improving both sample efficiency and final performance. Collectively, these results identify the source distribution as an important and underexplored design axis in generative robot control.

cs.LG↗

arXiv2026

VLA-GSE: Boosting Parameter-Efficient Fine-Tuning in VLA with Generalized and Specialized Experts

Vision-language-action (VLA) models inherit rich visual-semantic priors from pre-trained vision-language backbones, but adapting them to robotic control remains challenging. Full fine-tuning (FFT) is prone to overfitting on downstream robotic data and catastrophic forgetting of pretrained vision-language capabilities. Parameter-efficient fine-tuning (PEFT) better preserves pre-trained knowledge, yet existing PEFT methods still struggle to adapt effectively to robot control tasks. To address this gap, we propose VLA-GSE, a parameter-efficient VLA fine-tuning framework that improves control adaptation while retaining PEFT's knowledge preservation advantage. Specifically, VLA-GSE (Generalized and Specialized Experts) is initialized by spectrally decomposing the frozen backbone, assigning leading singular components to generalized experts (shared experts) and disjoint residual components to specialized experts (routed experts). This decomposition improves adaptation capacity under a fixed trainable-parameter budget. Under a comparable parameter budget, VLA-GSE updates only 2.51% of the full model parameters and consistently outperforms strong FFT and PEFT baselines. It achieves 81.2% average zero-shot success on LIBERO-Plus, preserves pre-trained VLM capability comparably to LoRA on multimodal understanding benchmarks, and improves real-world manipulation success under multiple distribution shifts. Code is available at: https://github.com/YuhuaJiang2002/VLA-GSE

cs.RO↗

arXiv2026

Thermodynamic Geometry of Relaxation

While the geometry of equilibrium states and driven non-equilibrium processes is clearly understood, a geometric description for relaxation towards equilibrium is still lacking. Here, we propose a thermo-geometric measure based on the Rayleigh quotient, reformulating relaxation as a fundamental competition between entropic stiffness and frictional dissipation. Taking a van der Waals gas with two dissipation channels as an example, we explicitly demonstrate its relaxation landscape. Particularly, we find that upon approaching the critical temperature $T_c$, the slow-mode relaxation rate vanishes linearly as $λ_s \propto (T-T_c)/T_c$, indicating critical slowing down. This study completes the thermodynamic geometry framework, providing a general tool for characterizing the relaxation dynamics of complex systems.

cond-mat.stat-mech↗

arXiv2026

An Adaptive Subdomain Coupling Approach in Domain Decomposition for Multiphase Porous Media Flow

The numerical simulation of large-scale multiphase flow in porous media is of considerable importance across various application fields, particularly in the petroleum industry. The fully implicit method is preferred in reservoir simulations owing to its superior numerical stability and more relaxed time step constraints. However, this method requires solving a large nonlinear system, which becomes highly nonlinear in complex heterogeneous media with small grid scales, emphasizing the need for efficient and convergent numerical methods to accelerate nonlinear solvers on parallel computing systems. In this paper, we present an adaptively coupled subdomain framework based on domain decomposition methods. This framework effectively handles strong local nonlinearities in global problems by solving subproblems within the coupled regions. Furthermore, we propose several adaptive coupling strategies and present a novel method for calculating initial guesses, aimed at improving the convergence and scalability of nonlinear solvers. A series of numerical experiments validate the effectiveness and robustness of the proposed framework. Additionally, large-scale reservoir simulations demonstrate that the proposed method achieves competitive parallel performance.

math.NA↗

arXiv2026

Co-Evolving Latent Action World Models

Adapting pretrained video generation models into controllable world models via latent actions is a promising step towards creating generalist world models. The dominant paradigm adopts a two-stage approach that trains latent action model (LAM) and the world model separately, resulting in redundant training and limiting their potential for co-adaptation. A conceptually simple and appealing idea is to directly replace the forward dynamic model in LAM with a powerful world model and training them jointly, but it is non-trivial and prone to representational collapse. In this work, we propose CoLA-World, which for the first time successfully realizes this synergistic paradigm, resolving the core challenge in joint learning through a critical warm-up phase that effectively aligns the representations of the from-scratch LAM with the pretrained world model. This unlocks a co-evolution cycle: the world model acts as a knowledgeable tutor, providing gradients to shape a high-quality LAM, while the LAM offers a more precise and adaptable control interface to the world model. Empirically, CoLA-World matches or outperforms prior two-stage methods in both video simulation quality and downstream visual planning, establishing a robust and efficient new paradigm for the field.

cs.LG↗

arXiv2026

Learning Additively Compositional Latent Actions for Embodied AI

Latent action learning infers pseudo-action labels from visual transitions, providing an approach to leverage internet-scale video for embodied AI. However, most methods learn latent actions without structural priors that encode the additive, compositional structure of physical motion. As a result, latents often entangle irrelevant scene details or information about future observations with true state changes and miscalibrate motion magnitude. We introduce Additively Compositional Latent Action Model (AC-LAM), which enforces scene-wise additive composition structure over short horizons on the latent action space. These AC constraints encourage simple algebraic structure in the latent action space~(identity, inverse, cycle consistency) and suppress information that does not compose additively. Empirically, AC-LAM learns more structured, motion-specific, and displacement-calibrated latent actions and provides stronger supervision for downstream policy learning, outperforming state-of-the-art LAMs across simulated and real-world tabletop tasks.

cs.CV↗

arXiv2026

BridgeDiff: Bridging Human Observations and Flat-Garment Synthesis for Virtual Try-Off

Virtual try-off (VTOFF) aims to recover canonical flat-garment representations from images of dressed persons for standardized display and downstream virtual try-on. Prior methods often treat VTOFF as direct image translation driven by local masks or text-only prompts, overlooking the gap between on-body appearances and flat layouts. This gap frequently leads to inconsistent completion in unobserved regions and unstable garment structure. We propose BridgeDiff, a diffusion-based framework that explicitly bridges human-centric observations and flat-garment synthesis through two complementary components. First, the Garment Condition Bridge Module (GCBM) builds a garment-cue representation that captures global appearance and semantic identity, enabling robust inference of continuous details under partial visibility. Second, the Flat Structure Constraint Module (FSCM) injects explicit flat-garment structural priors via Flat-Constraint Attention (FC-Attention) at selected denoising stages, improving structural stability beyond text-only conditioning. Extensive experiments on standard VTOFF benchmarks show that BridgeDiff achieves state-of-the-art performance, producing higher-quality flat-garment reconstructions while preserving fine-grained appearance and structural integrity.

cs.CV↗

arXiv2026

Automatic Network Planning with Digital Radio Twin

Network planning seeks to determine base station parameters that maximize coverage and capacity in cellular networks. However, achieving optimal planning remains challenging due to the diversity of deployment scenarios and the significant simulation-to-reality discrepancy. In this paper, we propose \emph{AutoPlan}, a new automatic network planning framework by leveraging digital radio twin (DRT) techniques. We derive the DRT by finetuning the parameters of building materials to reduce the sim-to-real discrepancy based on crowdsource real-world user data. Leveraging the DRT, we design a Bayesian optimization based algorithm to optimize the deployment parameters of base stations efficiently. Using the field measurement from Husker-Net, we extensively evaluate \emph{AutoPlan} under various deployment scenarios, in terms of both coverage and capacity. The evaluation results show that \emph{AutoPlan} flexibly adapts to different scenarios and achieves performance comparable to exhaustive search, while requiring less than 2\% of its computation time.

cs.NI↗

arXiv2026

Trade-R1: Bridging Verifiable Rewards to Stochastic Environments via Process-Level Reasoning Verification

Reinforcement Learning (RL) has enabled Large Language Models (LLMs) to achieve remarkable reasoning in domains like mathematics and coding, where verifiable rewards provide clear signals. However, extending this paradigm to financial decision is challenged by the market's stochastic nature: rewards are verifiable but inherently noisy, causing standard RL to degenerate into reward hacking. To address this, we propose Trade-R1, a model training framework that bridges verifiable rewards to stochastic environments via process-level reasoning verification. Our key innovation is a verification method that transforms the problem of evaluating reasoning over lengthy financial documents into a structured Retrieval-Augmented Generation (RAG) task. We construct a triangular consistency metric, assessing pairwise alignment between retrieved evidence, reasoning chains, and decisions to serve as a validity filter for noisy market returns. We explore two reward integration strategies: Fixed-effect Semantic Reward (FSR) for stable alignment signals, and Dynamic-effect Semantic Reward (DSR) for coupled magnitude optimization. Experiments on different country asset selection demonstrate that our paradigm reduces reward hacking, with DSR achieving superior cross-market generalization while maintaining the highest reasoning consistency.

cs.AI↗

arXiv2025

Chains of rotating boson stars with quartic or sextic self-interaction

This paper investigates chains of rotating boson stars (BSs) within Einstein gravity coupled to a complex scalar field. The model incorporates quartic or sextic self-interactions in the scalar Lagrangian, which support the existence of stationary, solitonic, gravitationally bound solutions. We numerically construct these multi-component systems and investigate how the self-interactions alter their global properties -- specifically the Arnowitt-Deser-Misner (ADM) mass $M$, the angular momentum $J$ and the morphology of their ergospheres. A central result is the distinct dependence of the $(ω, M)$ and $(ω, J)$ relations on the parity of the chains. Specifically, systems with an even number of constituents display spiraling curves, while those with an odd number exhibit loop structures. Moreover, we observe that two initially distinct ergospheres merge into a single one as the frequency $ω$ increases. Our analysis also indicates that the quartic interaction imposes more restrictive existence bounds, particularly for odd-numbered chains, thereby restricting stable configurations to the weak-coupling regime. In contrast, the sextic interaction has a weaker effect and enables stable solutions at substantially stronger couplings.

gr-qc↗

arXiv2025

HW-GNN: Homophily-Aware Gaussian-Window Constrained Graph Spectral Network for Social Network Bot Detection

Social bots are increasingly polluting online platforms by spreading misinformation and engaging in coordinated manipulation, posing severe threats to cybersecurity. Graph Neural Networks (GNNs) have become mainstream for social bot detection due to their ability to integrate structural and attribute features, with spectral-based approaches demonstrating particular efficacy due to discriminative patterns in the spectral domain. However, current spectral GNN methods face two limitations: (1) their broad-spectrum fitting mechanisms degrade the focus on bot-specific spectral features, and (2) certain domain knowledge valuable for bot detection, e.g., low homophily correlates with high-frequency features, has not been fully incorporated into existing methods. To address these challenges, we propose HW-GNN, a novel homophily-aware graph spectral network with Gaussian window constraints. Our framework introduces two key innovations: (i) a Gaussian-window constrained spectral network that employs learnable Gaussian windows to highlight bot-related spectral features, and (ii) a homophily-aware adaptation mechanism that injects domain knowledge between homophily ratios and frequency features into the Gaussian window optimization process. Through extensive experimentation on multiple benchmark datasets, we demonstrate that HW-GNN achieves state-of-the-art bot detection performance, outperforming existing methods with an average improvement of 4.3% in F1-score, while exhibiting strong plug-in compatibility with existing spectral GNNs.

cs.SI↗