arXiv subjects

Junhong Liu

Publications and source records attributed to Junhong Liu.

At least 19 recordsLinked to original sources

arXiv2026

PhyGile: Physics-Prefix Guided Motion Generation for Agile General Humanoid Motion Tracking

Humanoid robots are expected to execute agile and expressive whole-body motions in real-world settings. Existing text-to-motion generation models are predominantly trained on captured human motion datasets, whose priors assume human biomechanics, actuation, mass distribution, and contact strategies. When such motions are directly retargeted to humanoid robots, the resulting trajectories may satisfy geometric constraints (e.g., joint limits and pose continuity) and appear kinematically reasonable. However, they frequently violate the physical feasibility required for real-world execution. To address these issues, we present PhyGile, a unified framework that closes the loop between robot-native motion generation and General Motion Tracking (GMT). PhyGile performs physics-prefix-guided robot-native motion generation at inference time, directly generating robot-native motions in a 262-dimensional skeletal space with physics-guided prefixes, thereby eliminating inference-time retargeting artifacts and reducing generation-execution discrepancies. Before physics-prefix adaptation, we train the GMT controller with a curriculum-based mixture-of-experts scheme, followed by post-training on unlabeled motion data to improve robustness over large-scale robot motions. During physics-prefix adaptation, the GMT controller is further fine-tuned with generated objectives under physics-derived prefixes, enabling agile and stable execution of complex motions on real robots. Extensive offline and real-robot experiments demonstrate that PhyGile expands the frontier of text-driven humanoid control, enabling stable tracking of agile, highly difficult whole-body motions that go well beyond walking and low-dynamic motions typically achieved by prior methods.

cs.RO↗

arXiv2026

Athena-Brain Technical Report: An Efficient Robot Brain for General Intelligence and Embodied Interaction

Large language models (LLMs) have demonstrated remarkable capabilities in language understanding, reasoning, and world knowledge. As embodied agents become increasingly capable, there is a growing demand for compact models that can serve as an on-device brain, preserving the broad general intelligence of LLMs while enabling effective high-level interaction with embodied environments. Existing approaches, however, often prioritize either general-purpose intelligence or specialized embodied capabilities, making it challenging to satisfy both requirements within a single model. We present \textbf{Athena-Brain-8B}, an 8B LLM designed to serve as an on-device brain for embodied intelligence for embodied intelligence. Through a multi-stage post-training pipeline consisting of General Supervised Fine-Tuning, General Reinforcement Learning, Embodied Expert training, and Model Merge, Athena-Brain-8B maintains strong general capabilities while acquiring strong high-level embodied interaction capabilities and generating concise responses for efficient embodied interaction. Experimental results demonstrate the effectiveness of Athena across both general and embodied evaluations. Compared with the corresponding Qwen3-8B thinking model, Athena-Brain-8B achieves comparable performance on general language and reasoning benchmarks while generating substantially shorter responses. On in-domain embodied benchmarks, Athena-Brain-8B consistently outperforms models of similar scale and surpasses several substantially larger frontier models evaluated zero-shot, demonstrating that compact language models can effectively integrate strong general intelligence with embodied capabilities.

cs.AI↗

arXiv2026

Quantum-Resilient Distributed Optimization for Multi-Region Unit Commitment

Multi-region unit commitment with reserve sharing requires coordinated optimization across jurisdictionally distinct system operators, exposing sensitive cost curves, topology, and dispatch decisions to inference attacks. The accelerating progress of quantum computing further compounds this threat. As quantum hardware matures, current classically-encrypted data flow becomes vulnerable to retrospective decryption. To enable post-quantum-secure distributed optimization, we propose a customized Benders decomposition-based approach with the global summation structure to share aggregated cuts and variables. By exploiting this structure, we further develop a multi-layer quantum-resilient secure aggregation protocol comprising additive masking for information-theoretic content privacy, affine variable transformation hiding individual sensitive data flows, and reveal-bound lattice-based zero-knowledge proofs providing resilience against active adversaries. Simulation results show that the proposed approach achieves the mean suboptimality of 0.09%-0.22% with lightweight computational overhead, recovers up to 51% of system cost via inter-regional reserve sharing, and imposes no measurable cost-quality trade-off, whereas the noisy ADMM degrades monotonically under tightening privacy budgets and becomes structurally infeasible on combinatorially dense systems.

eess.SY↗

arXiv2026

Lyapunov Guidance: A Unified Framework for Stabilizing Generative Flows

Flow matching has emerged as an effective framework for learning complex data distributions, but adapting pretrained flow models to new tasks often requires computationally expensive retraining. Post-training guidance provides a more efficient alternative, but existing methods are largely heuristic and offer no explicit stability guarantees. We address this limitation by proposing LyaGuide, a unified Lyapunov-guided framework that formulates flow guidance as a Lyapunov control problem. Our main theoretical result establishes an equivalence between guided flow matching and Lyapunov control, thereby unifying common guidance strategies, such as classifier guidance, reward guidance, and energy-based guidance, within a single control-theoretic framework. To enforce the Lyapunov condition, we introduce a pseudo-projection operator with a closed-form expression that endows learned or heuristic guidance terms with explicit stability guarantees. LyaGuide supports two practical settings: a model-driven setting, where the target guidance distribution is specified through a known Lyapunov function, and a data-driven setting, where the guidance is adapted from task-specific downstream data. LyaGuide is compatible with existing guidance methods, introduces minimal additional computational overhead, and is straightforward to integrate in practice. Extensive experiments on synthetic benchmarks, image inverse problems, reinforcement learning planning, and energy-based modeling demonstrate consistent improvements in sample quality, guidance fidelity, and robustness, while maintaining computational efficiency.

cs.LG↗

arXiv2026

Adaptive Federated Learning to Optimize Integrated Flows in Cyber-Physical Data Centers

Data centers play an increasingly critical role in societal digitalization, yet their rapidly growing energy demand poses significant challenges for sustainable operation. To enhance the energy efficiency of geographically distributed data centers, this paper formulates a multi-period optimization model that captures the interdependence of electricity, heat, and data flows. The optimization of such integrated multi-domain flows inherently involves mixed-integer formulations and the access to proprietary or sensitive datasets, which correspondingly exacerbate computational complexity and raise data-privacy concerns. To address these challenges, an adaptive federated learning-to-optimization approach is proposed, accounting for the heterogeneity of datasets across distributed data centers. To safeguard privacy, cryptography techniques are leveraged in both the learning and optimization processes. A model acceptance criterion with convergence guarantee is developed to improve learning performance and filter out potentially contaminated data, while a verifiable double aggregation mechanism is further proposed to simultaneously ensure privacy and integrity of shared data during optimization. Theoretical analysis and numerical simulations demonstrate that the proposed approach preserves the privacy and integrity of shared data, achieves near-optimal performance, and exhibits high computational efficiency, making it suitable for large-scale data center optimization under privacy constraints.

eess.SY↗

arXiv2026

Engagement Process: Rethinking the Temporal Interface of Action and Observation

Task completion in digital and physical environments increasingly involves complex temporal interaction, where actions and observations unfold over different time scales rather than align with fixed observation--action steps. To model such interactions, we propose \emph{Engagement Process} (EP), an interaction formalism that inherits the decision-theoretic structure of POMDPs while making time explicit in the action--observation interface. EP represents actions and observations as decoupled event streams along time, rather than updates paired at fixed decision steps. This interface captures single-agent timing issues such as deliberation latency, delayed feedback, and persistent actions, while supporting richer agent-side organization, multi-rate coordination, and compositional interaction among subsystems. Across toy, LLM-agent, and learning experiments, EP exposes temporal behaviors hidden by step-based interfaces and enables policies to adapt under explicit time costs.

cs.AI↗

arXiv2026

OmniVerifier-M1: Multimodal Meta-Verifier with Explicit Structured Recalibration

Visual outcomes are increasingly central to multimodal large language models, making reliable and fine-grained verification essential for scaling generalist foundation models. In this work, we investigate multimodal meta-verification, which leverages verifier-generated rationales rather than decision-only signals, and explore how to effectively incorporate meta-verification feedback into multimodal verifier training. We identify two key findings. First, symbolic verifier outputs (e.g., bounding boxes) outperform textual explanations as meta-verification rationales, enabling efficient rule-based reinforcement learning rewards while avoiding reliance on model-based rewards from auxiliary judge models. Second, decoupling reinforcement learning objectives for binary judgment and meta-verification substantially outperforms joint reward optimization, due to intrinsic differences in output structure and learning dynamics. Based on these insights, we train OmniVerifier-M1, a generalist visual verifier leveraging symbolic meta-verification and decoupled reinforcement learning. OmniVerifier-M1 provides robust verification and fine-grained error localization, and further enables M1-TTS, a verifier-driven agentic generation system achieving dynamic region-level self-correction. This approach paves the way for more reliable, interpretable, and fine-grained multimodal verification, supporting safer and more controllable foundation model deployment.

cs.CL↗

arXiv2026

PoseX: AI Defeats Physics Approaches on Protein-Ligand Cross Docking

Existing protein-ligand docking studies typically focus on the self-docking scenario, which is less practical in real applications. Moreover, some studies involve heavy frameworks requiring extensive training, posing challenges for convenient and efficient assessment of docking methods. To fill these gaps, we design PoseX, an open-source benchmark to evaluate both self-docking and cross-docking, enabling a practical and comprehensive assessment of algorithmic advances. Specifically, we curated a novel dataset comprising 718 entries for self-docking and 1,312 entries for cross-docking; second, we incorporated 23 docking methods in three methodological categories, including physics-based methods (e.g., Schrödinger Glide), AI docking methods (e.g., DiffDock) and AI co-folding methods (e.g., AlphaFold3); third, we developed a relaxation method for post-processing to minimize conformational energy and refine binding poses; fourth, we built a leaderboard to rank submitted models in real-time. We derived some key insights and conclusions from extensive experiments: (1) AI approaches have consistently outperformed physics-based methods in overall docking success rate. (2) Most intra- and intermolecular clashes of AI approaches can be greatly alleviated with relaxation, which means combining AI modeling with physics-based post-processing could achieve excellent performance. (3) AI co-folding methods exhibit ligand chirality issues, except for Boltz-1x, which introduced physics-inspired potentials to fix hallucinations, suggesting modeling on stereochemistry improves the structural plausibility markedly. (4) Specifying binding pockets significantly promotes docking performance, indicating that pocket information can be leveraged adequately, particularly for AI co-folding methods, in future modeling efforts. The code, dataset, and leaderboard are released at https://github.com/CataAI/PoseX.

cs.LG↗

arXiv2026

Decarbonizing China's private passenger vehicles: A dynamic material flow assessment of metal demands and embodied emissions

The continuous growth of China's private passenger vehicle fleet has intensified material demand and embodied carbon emissions, underscoring the need for effective decarbonization pathways. This study develops a transferable, dynamic material flow analysis framework to assess vehicle stocks, metal flows (steel, aluminum, and copper), and embodied emissions from 2000 to 2070, and to quantify the contributions of demand-side and technology-side efficiency measures. The results reveal that: (1) The vehicle fleet is projected to peak at 327-507 million vehicles by mid-century, with new energy vehicles dominating both in-use stocks and end-of-life flows by the 2040s. (2) Cumulative metal demand is projected to reach 1914-2990 million tonnes over the upcoming five decades, with 879-1320 million tonnes supplied from secondary sources under baseline conditions. Technology-oriented measures substantially enhance recycling performance, enabling secondary steel to fully meet manufacturing demand and allowing aluminum and copper cycles to approach near closure by 2070. (3) Correspondingly, cumulative embodied carbon emissions from vehicle metals by 2070 range from 4958 to 9218 megatonnes of carbon dioxide, with technological upgrading reducing emissions by 1051-1619 megatonnes. In collaborative scenarios, demand management accounts for 64.3% of total emission reductions, while technology-oriented measures become increasingly important over the medium to long term. Overall, the findings demonstrate that unmanaged demand growth can substantially offset technological mitigation gains, highlighting the necessity of integrated demand- and technology-oriented strategies. This study provides a systemic and transferable framework to guide circular economy development and deep decarbonization transitions in vehicle fleets in China and other emerging economies.

physics.soc-ph↗

arXiv2025

Planning future charging infrastructure for private EVs: A city-scale assessment of demand and capacity

This study proposes the first demand-driven, multi-objective planning model for optimizing city-scale capacity allocation of EV charging infrastructure. The model employs a bottom-up approach to estimate charging demand differentiated by vehicle type-battery electric vehicles (BEVs), extended-range electric vehicles (EREVs), and plug-in hybrid electric vehicles (PHEVs). Chongqing, a rapidly expanding EV industry cluster in China with a strong industrial base, supportive policies, and diverse urban morphologies, is selected as the case study. The results show that (1) monthly EV electricity consumption in Chongqing rose from 18.9 gigawatt-hours (GWh) in June 2022 to 57.5 GWh in December 2024, with associated carbon emissions increasing from 9.9 kilotons of carbon dioxide (ktCO2) to 30 ktCO2; (2) 181,622 additional charging piles were installed between 2022 and 2024, with the fastest growth observed in Yubei, reflecting a demand-responsive strategy that prioritizes areas with higher population density, higher income levels, and adequate land availability for pile deployment, rather than broad geographic coverage; and (3) between 2025 and 2030, EV electricity demand is projected to reach 1940 GWh, with the number of charging piles exceeding 1.4 million, and charging demand from EREVs and PHEVs expected to overtake BEVs later in the period. While Chongqing serves as the pilot area, the proposed planning platform is adaptable for application in cities worldwide, enabling cross-regional comparisons under diverse socio-economic, geographic, and policy conditions. Overall, this work offers policymakers a versatile tool to support sustainable, cost-effective EV infrastructure deployment aligned with low-carbon electrification targets in the transportation sector.

physics.soc-ph↗

arXiv2025

Distilling Cross-Modal Knowledge via Feature Disentanglement

Knowledge distillation (KD) has proven highly effective for compressing large models and enhancing the performance of smaller ones. However, its effectiveness diminishes in cross-modal scenarios, such as vision-to-language distillation, where inconsistencies in representation across modalities lead to difficult knowledge transfer. To address this challenge, we propose frequency-decoupled cross-modal knowledge distillation, a method designed to decouple and balance knowledge transfer across modalities by leveraging frequency-domain features. We observed that low-frequency features exhibit high consistency across different modalities, whereas high-frequency features demonstrate extremely low cross-modal similarity. Accordingly, we apply distinct losses to these features: enforcing strong alignment in the low-frequency domain and introducing relaxed alignment for high-frequency features. We also propose a scale consistency loss to address distributional shifts between modalities, and employ a shared classifier to unify feature spaces. Extensive experiments across multiple benchmark datasets show our method substantially outperforms traditional KD and state-of-the-art cross-modal KD approaches. Code is available at https://github.com/Johumliu/FD-CMKD.

cs.CV↗

arXiv2025

Synergising Hierarchical Data Centers and Power Networks: A Privacy-Preserving Approach

In the era of digitization, data centers have emerged as integral contributors sustaining our interlinked world, bearing responsibility for an increasing proportion of the world's energy consumption. To facilitate the their fast rollout while progressing towards net-zero energy systems, the synergy of hierarchical data centers (cloud-fog-edge) and power networks can play a pivotal role. However, existing centralized co-dispatch manners encroach on the privacy of different agents within the integrated systems, meanwhile suffering from the combinatorial explosion. In this research, we propose a near-optimal distributed privacy-preserving approach to solve the non-convex synergy (day-ahead co-dispatch) problem. The synergy problem is formulated as a mixed integer quadratically constrained quadratic programming considering both communication and energy conservation, where Lyapunov optimization is introduced to balance operating costs and uncertain communication delays. To mitigate impacts of the highly non-convex nature, the normalized multi-parametric disaggregation technique is leveraged to reformulate the problem into a mixed integer non-linear programming. To further overcome non-smoothness of the reformulated problem, the customized $\ell_1-$surrogate Lagrangian relaxation method with convergence guarantees is proposed to solve the problem in a distributed privacy-preserving manner. The effectiveness, optimality, and scalability of the proposed methodologies for the synergy problem are validated via numerical simulations. Simulation results also indicate that computing tasks can be delayed and migrated within the hierarchical data centers, demonstrating the flexible resource allocation capabilities of the hierarchical data center architecture, further facilitating peak load balancing in the power network.

eess.SY↗

arXiv2025

Rec-AD: An Efficient Computation Framework for FDIA Detection Based on Tensor Train Decomposition and Deep Learning Recommendation Model

Deep learning models have been widely adopted for False Data Injection Attack (FDIA) detection in smart grids due to their ability to capture unstructured and sparse features. However, the increasing system scale and data dimensionality introduce significant computational and memory burdens, particularly in large-scale industrial datasets, limiting detection efficiency. To address these issues, this paper proposes Rec-AD, a computationally efficient framework that integrates Tensor Train decomposition with the Deep Learning Recommendation Model (DLRM). Rec-AD enhances training and inference efficiency through embedding compression, optimized data access via index reordering, and a pipeline training mechanism that reduces memory communication overhead. Fully compatible with PyTorch, Rec-AD can be integrated into existing FDIA detection systems without code modifications. Experimental results show that Rec-AD significantly improves computational throughput and real-time detection performance, narrowing the attack window and increasing attacker cost. These advancements strengthen edge computing capabilities and scalability, providing robust technical support for smart grid security.

cs.LG↗

arXiv2025

Clustered Federated Learning for Generalizable FDIA Detection in Smart Grids with Heterogeneous Data

False Data Injection Attacks (FDIAs) pose severe security risks to smart grids by manipulating measurement data collected from spatially distributed devices such as SCADA systems and PMUs. These measurements typically exhibit Non-Independent and Identically Distributed (Non-IID) characteristics across different regions, which significantly challenges the generalization ability of detection models. Traditional centralized training approaches not only face privacy risks and data sharing constraints but also incur high transmission costs, limiting their scalability and deployment feasibility. To address these issues, this paper proposes a privacy-preserving federated learning framework, termed Federated Cluster Average (FedClusAvg), designed to improve FDIA detection in Non-IID and resource-constrained environments. FedClusAvg incorporates cluster-based stratified sampling and hierarchical communication (client-subserver-server) to enhance model generalization and reduce communication overhead. By enabling localized training and weighted parameter aggregation, the algorithm achieves accurate model convergence without centralizing sensitive data. Experimental results on benchmark smart grid datasets demonstrate that FedClusAvg not only improves detection accuracy under heterogeneous data distributions but also significantly reduces communication rounds and bandwidth consumption. This work provides an effective solution for secure and efficient FDIA detection in large-scale distributed power systems.

cs.LG↗

arXiv2025

Online distributed optimization for spatio-temporally constrained real-time peer-to-peer energy trading

The proliferation of distributed renewable energy triggers the peer-to-peer (P2P) energy market formations. To make profits, prosumers equipped with photovoltaic (PV) panels and even the energy storage system (ESS) can actively participate in the real-time P2P energy market and trade energy. However, in real situations, system states such as energy demands and renewable energy power generation are highly uncertain, making it difficult for prosumers to make optimal real-time decisions. Moreover, severe problems with the physical network can arise from the real-time P2P energy trading, such as bus voltage violations and line overload. To handle these problems, this work first formulates the real-time P2P energy trading problem as a spatio-temporally constrained stochastic optimization problem by considering ESS and the spatial physical network constraints. To deal with the uncertainties online, a modified Lyapunov optimization method is innovatively proposed to approximately reformulate the stochastic optimization problem into an online one by relaxing the time-coupling constraints. Compared with the state-of-the-art online methods, the proposed one renders more flexibility and better performance for the real-time P2P energy market operation. Additionally, to protect the prosumers' privacy, an online distributed algorithm based on the consensus alternating direction method of multipliers (ADMM) is developed to solve the reformulated online problem by decoupling the spatial constraints. The theoretical near-optimal performance guarantee of the proposed online distributed algorithm is derived, and its performance can be further improved by minimizing the performance gap. Simulation results demonstrate that the proposed online distributed algorithm can guarantee the fast, stable, and safe long-term operation of the real-time P2P energy market.

eess.SY↗

arXiv2025

Privacy-Preserving Peer-to-Peer Energy Trading via Hybrid Secure Computations

The massive integration of uncertain distributed renewable energy resources into power systems raises power imbalance concerns. Peer-to-peer (P2P) energy trading provides a promising way to balance the prosumers' volatile energy power generation and demands locally. Particularly, to protect the privacy of prosumers, distributed P2P energy trading is broadly advocated. However, severe privacy leakage issues can emerge in the realistic fully distributed P2P energy trading paradigm. Meanwhile, in this paradigm, two-party and multi-party computations coexist, challenging the naive privacy-preserving techniques. To tackle privacy leakage issues arising from the fully distributed P2P energy trading, this paper proposes a privacy-preserving approach via hybrid secure computations. A secure multi-party computation mechanism consisting of offline and online phases is developed to ensure the security of shared data by leveraging the tailored secret sharing method. In addition, the Paillier encryption method based on the Chinese Remainder Theorem is proposed for both the secure two-party computation and the offline phase of the multi-party computation. The random encryption coefficient is designed to enhance the security of the two-party computation and simultaneously guarantee the convergence of the distributed optimization. The feasible range for the encryption coefficient is derived with a strict mathematical proof. Numerical simulations demonstrate the exactness, effectiveness, and scalability of the proposed privacy-preserving approach.

eess.SY↗

arXiv2025

Byzantine-Resilient Distributed P2P Energy Trading via Spatial-Temporal Anomaly Detection

Distributed peer-to-peer (P2P) energy trading mandates an escalating coupling between the physical power network and communication network, necessitating high-frequency sharing of real-time data among prosumers. However, this data-sharing scheme renders the system vulnerable to various malicious behaviors, as Byzantine agents can initiate cyberattacks by injecting sophisticated false data. To better investigate the impacts of malicious Byzantine faults, this paper develops a fully distributed P2P energy trading model by accounting for the high-fidelity physical network constraints. To further detect Byzantine faults and mitigate their impacts on distributed P2P energy trading problem, we propose an online spatial-temporal anomaly detection approach by leveraging the tensor learning method, which is informed by the domain knowledge to enable awesome detection performance. Moreover, to enhance its computational efficiency, we further develop closed-form solutions for the proposed detection approach. Subsequently, we derive theoretical conditions for guaranteeing optimality and convergence of the distributed P2P energy trading problem with anomaly detection mechanisms. Results from numerical simulations validate the effectiveness, optimality, and scalability of the proposed approach.

eess.SY↗

arXiv2025

Building floorspace and stock measurement: A review of global efforts, knowledge gaps, and research priorities

Despite a substantial body of research-evidenced by our analysis of 2,628 peer-reviewed papers-global building floorspace data remain fragmented, inconsistent, and methodologically diverse. The lack of high-quality and openly accessible datasets poses major challenges to accurately assessing building carbon neutrality. This review focuses on global building floorspace, especially its nexus with energy and emissions. The key research areas include energy modeling, emissions analysis, building retrofits, and life cycle assessments. Each measurement approach-top-down, bottom-up, and hybrid-has its own limitations: top-down methods provide broad estimates but low accuracy, whereas bottom-up approaches are more precise but data intensive. Our simulations reveal a surge in floorspace growth across emerging economies-most notably in India, Indonesia, and Africa-with India's per capita floorspace projected to triple by 2070. We emphasize the need for a high-resolution global floorspace imagery database to compare energy efficiency, track decarbonization progress, and assess renovation impacts while promoting building sufficiency and accelerating the transition to net-zero building systems.

physics.soc-ph↗