arXiv subjects

Zhibin Li

Publications and source records attributed to Zhibin Li.

At least 19 recordsLinked to original sources

arXiv2026

A Chromomagnetic Mechanism for the Rotational Phase Transition of Gluonic Matter

Rotation serves as a pivotal control parameter for QCD matter, yet effective models and lattice QCD yield conflicting predictions regarding its effect on the deconfinement transition. Using a rotation-magnetic correspondence within a holographic framework, we investigate the rotational response of pure gluonic matter. Calibrated against lattice QCD data at imaginary angular velocity, we find real rotation enhances chromomagnetic string tension and raises deconfinement temperature, consistent with lattice QCD analytic-continuation predictions. The temperature dependence of chromomagnetic string tension dominates the system's Barnett response: weak low-temperature tension induces the negative Barnett effect, and slightly above the transition, spin contributions prevail to generate an anomalous negative total moment of inertia. Since growing angular velocity further strengthens chromomagnetic string tension and suppresses spin-dominated inversion, this anomalous regime only survives at weak real rotation and vanishes at large angular velocity. At high temperature, fully restored strong string tension stabilizes conventional Barnett behavior. Stemming from the melting and thermal restoration of nonperturbative chromomagnetic flux tubes, our results establish the chromomagnetic-induced inertia inversion (CII) mechanism as the microscopic origin of this anomalous rotational response.

hep-ph↗

arXiv2026

Flavor-Dependent QCD Critical Endpoint and Dual-Channel Fluctuations from Multi-Charge Holography

We construct a thermodynamically self-consistent holographic QCD framework incorporating multiple conserved charges. By introducing three independent bulk $U(1)$ gauge fields, our Einstein-Maxwells-dilaton (EMsD) model naturally accommodates the coupled chemical potential landscape $(μ_B, μ_Q, μ_S)$ inherent to realistic heavy-ion collisions. Crucially, thermodynamic consistency is enforced at the level of holographic renormalization, ensuring exact Maxwell cross-derivative relations without ad hoc patching. Calibrated exclusively at zero density, the model exhibits genuine predictive power for finite-density thermodynamics. We reveal that finite charge and strangeness densities induce pronounced nonmonotonic shifts in the critical endpoint (CEP) location. Furthermore, by mapping the freeze-out trajectories, we demonstrate that the allowed parameter bands robustly encompass empirical hadron resonance gas (HRG) fits. Within this physical regime, higher-order cumulant ratios for both net-baryon and net-charge channels exhibit coherent critical peaks at $\sqrt{s_{NN}} \approx 5\text{--}7\,\text{GeV}$. This hierarchical dual-channel signature provides a decisive, background-free strategy for the ongoing experimental search for the QCD critical point.

hep-ph↗

arXiv2026

Closing the Reality Gap: Zero-Shot Sim-to-Real Deployment for Dexterous Force-Based Grasping and Manipulation

Human-like dexterous hands with multiple fingers offer human-level manipulation capabilities but remain difficult to train the control policies that can deploy on real hardware due to contact-rich physics and imperfect actuation. We present a sim-to-real reinforcement learning method that leverages dense tactile feedback combined with joint torque sensing to explicitly regulate physical interactions. To enable effective sim-to-real transfer, we introduce (i) a computationally fast tactile simulation that computes distances between dense virtual tactile units and the object via parallel forward kinematics, providing high-rate, high-resolution touch signals needed by RL; (ii) a current-to-torque calibration that eliminates the need for torque sensors on dexterous hands by mapping motor current to joint torque; and (iii) actuator dynamics modeling with randomization to account for non-ideal torque-speed effects and bridge the actuation gaps. Using an asymmetric actor-critic PPO pipeline, we train policies entirely in simulation and deploy them directly to a five-finger hand. The resulting policies demonstrate two essential human-hand skills: (1) command-based controllable grasp force tracking and (2) reorientation of objects in the hand, both of which are robustly executed without fine-tuning on the robot. By combining tactile and torque in the observation space with scalable sensing and actuation modeling, our system provides a practical solution to achieve reliable dexterous manipulation. To our knowledge, this is the first demonstration of controllable grasping on a multi-finger dexterous hand trained entirely in simulation and transferred zero-shot on real hardware.

cs.RO↗

arXiv2026

Ozone: A Unified Platform for Transportation Research

Intelligent Transportation Systems increasingly depend on heterogeneous data from roadside cameras, UAV imagery, LiDAR, and in-vehicle sensors, yet the lack of unified data standards, model interfaces, and evaluation protocols across these sources hampers reproducibility, cross-dataset benchmarking, and cross-region transferability of research findings. Existing trajectory datasets follow incompatible conventions for coordinate systems, object representations, and metadata fields, forcing researchers to build custom preprocessing pipelines for each dataset and simulator combination. To address these challenges, we propose Ozone, a unified platform for transportation research organized around five interconnected layers -- Hardware, Data, Model, Evaluation, and Prototype -- each with standardized schemas, automated conversion pipelines, and interoperable interfaces. In the first release, the data schema unifies four trajectory datasets -- NGSIM, highD, CitySim, and UTE -- into a canonical format with oriented bounding boxes, kinematic variables, and pre-computed surrogate safety measures. Digital-twin maps in CARLA and calibrated traffic models provide integrated benchmarking environments. Case studies in human-factor research, traffic scene generation, and safety-critical modeling demonstrate that Ozone reduces experiment setup time by 85%, achieves 91% cross-city transfer efficiency for safety models, and improves cross-dataset reproducibility to within 3% variance. The source code and datasets are publicly available.

cs.DB↗

arXiv2026

Using large language models for embodied planning introduces systematic safety risks

Large language models are increasingly used as planners for robotic systems, yet how safely they plan remains an open question. To evaluate safe planning systematically, we introduce DESPITE, a benchmark of 12,279 tasks spanning physical and normative dangers with fully deterministic validation. Across 23 models, even near-perfect planning ability does not ensure safety: the best-planning model fails to produce a valid plan on only 0.4% of tasks but produces dangerous plans on 28.3%. Among 18 open-source models from 3B to 671B parameters, planning ability improves substantially with scale (0.4-99.3%) while safety awareness remains relatively flat (38-57%). We identify a multiplicative relationship between these two capacities, showing that larger models complete more tasks safely primarily through improved planning, not through better danger avoidance. Three proprietary reasoning models reach notably higher safety awareness (71-81%), while non-reasoning proprietary models and open-source reasoning models remain below 57%. As planning ability approaches saturation for frontier models, improving safety awareness becomes a central challenge for deploying language-model planners in robotic systems.

cs.AI↗

arXiv2026

QCD vacuum pressure and its influence on the equation of state of non-strange quark stars

Solutions of the quark gap equation and the corresponding vacuum pressure are investigated within a modified Nambu-Jona-Lasinio model, which is a basic issue for studying the QCD equation of state (EOS) and the properties of hypothetical non-strange quark stars. In this study, the coupling strength $G$ is modified as $G=G_1+G_2\langle\barψψ\rangle$ to highlight the feedback effect of the quark condensate on the gluon propagator. Our analysis reveals that the influence of the vacuum pressure on EOS stiffness critically depends on whether the chiral phase transition is a first-order transition or a smooth crossover. A small ratio $G_1/G$ $(0.74\sim0.75)$ leads to a low vacuum pressure and a first-order chiral phase transition, a scenario favored by the existence of massive pulsars. Conversely, a large $G_1/G$ $(>0.96)$ leads to a high vacuum pressure and a crossover, but the corresponding EOS is ruled out by recent pulsar mass-radius observations. The model parameter space, restricted by four constraints, indicates the current quark mass is in the range $4.08\leq m\leq4.13$ MeV, with the quark condensate feedback contribution accounting for approximately 25\%. Furthermore, it is argued that the merging compact binary in GW170817 could be non-strange quark stars, and the tidal deformability is constrained to $Λ(1.4)\leq646$.

hep-ph↗

arXiv2026

SCDP: Learning Humanoid Locomotion from Partial Observations via Mixed-Observation Distillation

Distilling humanoid locomotion control from offline datasets into deployable policies remains a challenge, as existing methods rely on privileged full-body states that require complex and often unreliable state estimation. We present Sensor-Conditioned Diffusion Policies (SCDP) that enables humanoid locomotion using only onboard sensors, eliminating the need for explicit state estimation. SCDP decouples sensing from supervision through mixed-observation training: diffusion model conditions on sensor histories while being supervised to predict privileged future state-action trajectories, enforcing the model to infer the motion dynamics under partial observability. We further develop restricted denoising, context distribution alignment, and context-aware attention masking to encourage implicit state estimation within the model and to prevent train-deploy mismatch. We validate SCDP on velocity-commanded locomotion and motion reference tracking tasks. In simulation, SCDP achieves near-perfect success on velocity control (99-100%) and 93% tracking success in AMASS test set, performing comparable to privileged baselines while using only onboard sensors. Finally, we deploy the trained policy on a real G1 humanoid at 50 Hz, demonstrating robust real robot locomotion without external sensing or state estimation.

cs.RO↗

arXiv2026

Closing the Reality Gap: Zero-Shot Sim-to-Real Deployment for Dexterous Force-Based Grasping and Manipulation

Human-like dexterous hands with multiple fingers offer human-level manipulation capabilities, but training control policies that can directly deploy on real hardware remains difficult due to contact-rich physics and imperfect actuation. We close this gap with a practical sim-to-real reinforcement learning (RL) framework that utilizes dense tactile feedback combined with joint torque sensing to explicitly regulate physical interactions. To enable effective sim-to-real transfer, we introduce (i) a computationally fast tactile simulation that computes distances between dense virtual tactile units and the object via parallel forward kinematics, providing high-rate, high-resolution touch signals needed by RL; (ii) a current-to-torque calibration that eliminates the need for torque sensors on dexterous hands by mapping motor current to joint torque; and (iii) actuator dynamics modeling to bridge the actuation gaps with randomization of non-ideal effects such as backlash, torque-speed saturation. Using an asymmetric actor-critic PPO pipeline trained entirely in simulation, our policies deploy directly to a five-finger hand. The resulting policies demonstrated two essential skills: (1) command-based, controllable grasp force tracking, and (2) reorientation of objects in the hand, both of which were robustly executed without fine-tuning on the robot. By combining tactile and torque in the observation space with effective sensing/actuation modeling, our system provides a practical solution to achieve reliable dexterous manipulation. To our knowledge, this is the first demonstration of controllable grasping on a multi-finger dexterous hand trained entirely in simulation and transferred zero-shot on real hardware.

cs.RO↗

arXiv2026

DemoBot: Efficient Learning of Bimanual Manipulation with Dexterous Hands From Third-Person Human Videos

This work presents DemoBot, a learning framework that enables a dual-arm, multi-finger robotic system to acquire complex manipulation skills from a single unannotated RGB-D video demonstration. The method extracts structured motion trajectories of both hands and objects from raw video data. These trajectories serve as motion priors for a novel reinforcement learning (RL) pipeline that learns to refine them through contact-rich interactions, thereby eliminating the need to learn from scratch. To address the challenge of learning long-horizon manipulation skills, we introduce: (1) Temporal-segment based RL to enforce temporal alignment of the current state with demonstrations; (2) Success-Gated Reset strategy to balance the refinement of readily acquired skills and the exploration of subsequent task stages; and (3) Event-Driven Reward curriculum with adaptive thresholding to guide the RL learning of high-precision manipulation. The novel video processing and RL framework successfully achieved long-horizon synchronous and asynchronous bimanual assembly tasks, offering a scalable approach for direct skill acquisition from human videos.

cs.RO↗

arXiv2025

End-to-End Dexterous Arm-Hand VLA Policies via Shared Autonomy: VR Teleoperation Augmented by Autonomous Hand VLA Policy for Efficient Data Collection

Achieving human-like dexterous manipulation remains a major challenge for general-purpose robots. While Vision-Language-Action (VLA) models show potential in learning skills from demonstrations, their scalability is limited by scarce high-quality training data. Existing data collection methods face inherent constraints: manual teleoperation overloads human operators, while automated planning often produces unnatural motions. We propose a Shared Autonomy framework that divides control between macro and micro motions. A human operator guides the robot's arm pose through intuitive VR teleoperation, while an autonomous DexGrasp-VLA policy handles fine-grained hand control using real-time tactile and visual feedback. This division significantly reduces cognitive load and enables efficient collection of high-quality coordinated arm-hand demonstrations. Using this data, we train an end-to-end VLA policy enhanced with our novel Arm-Hand Feature Enhancement module, which captures both distinct and shared representations of macro and micro movements for more natural coordination. Our Corrective Teleoperation system enables continuous policy improvement through human-in-the-loop failure recovery. Experiments demonstrate that our framework generates high-quality data with minimal manpower and achieves a 90% success rate across diverse objects, including unseen instances. Comprehensive evaluations validate the system's effectiveness in developing dexterous manipulation capabilities.

cs.RO↗

arXiv2025

RObotic MAnipulation Network (ROMAN) -- Hybrid Hierarchical Learning for Solving Complex Sequential Tasks

Solving long sequential tasks poses a significant challenge in embodied artificial intelligence. Enabling a robotic system to perform diverse sequential tasks with a broad range of manipulation skills is an active area of research. In this work, we present a Hybrid Hierarchical Learning framework, the Robotic Manipulation Network (ROMAN), to address the challenge of solving multiple complex tasks over long time horizons in robotic manipulation. ROMAN achieves task versatility and robust failure recovery by integrating behavioural cloning, imitation learning, and reinforcement learning. It consists of a central manipulation network that coordinates an ensemble of various neural networks, each specialising in distinct re-combinable sub-tasks to generate their correct in-sequence actions for solving complex long-horizon manipulation tasks. Experimental results show that by orchestrating and activating these specialised manipulation experts, ROMAN generates correct sequential activations for accomplishing long sequences of sophisticated manipulation tasks and achieving adaptive behaviours beyond demonstrations, while exhibiting robustness to various sensory noises. These results demonstrate the significance and versatility of ROMAN's dynamic adaptability featuring autonomous failure recovery capabilities, and highlight its potential for various autonomous manipulation tasks that demand adaptive motor skills.

cs.RO↗

arXiv2025

Spiking Neural Network for Cross-Market Portfolio Optimization in Financial Markets: A Neuromorphic Computing Approach

Cross-market portfolio optimization has become increasingly complex with the globalization of financial markets and the growth of high-frequency, multi-dimensional datasets. Traditional artificial neural networks, while effective in certain portfolio management tasks, often incur substantial computational overhead and lack the temporal processing capabilities required for large-scale, multi-market data. This study investigates the application of Spiking Neural Networks (SNNs) for cross-market portfolio optimization, leveraging neuromorphic computing principles to process equity data from both the Indian (Nifty 500) and US (S&P 500) markets. A five-year dataset comprising approximately 1,250 trading days of daily stock prices was systematically collected via the Yahoo Finance API. The proposed framework integrates Leaky Integrate-andFire neuron dynamics with adaptive thresholding, spike-timingdependent plasticity, and lateral inhibition to enable event-driven processing of financial time series. Dimensionality reduction is achieved through hierarchical clustering, while populationbased spike encoding and multiple decoding strategies support robust portfolio construction under realistic trading constraints, including cardinality limits, transaction costs, and adaptive risk aversion. Experimental evaluation demonstrates that the SNN-based framework delivers superior risk-adjusted returns and reduced volatility compared to ANN benchmarks, while substantially improving computational efficiency. These findings highlight the promise of neuromorphic computation for scalable, efficient, and robust portfolio optimization across global financial markets.

q-fin.PM↗

arXiv2025

RoboBallet: Planning for Multi-Robot Reaching with Graph Neural Networks and Reinforcement Learning

Modern robotic manufacturing requires collision-free coordination of multiple robots to complete numerous tasks in shared, obstacle-rich workspaces. Although individual tasks may be simple in isolation, automated joint task allocation, scheduling, and motion planning under spatio-temporal constraints remain computationally intractable for classical methods at real-world scales. Existing multi-arm systems deployed in the industry rely on human intuition and experience to design feasible trajectories manually in a labor-intensive process. To address this challenge, we propose a reinforcement learning (RL) framework to achieve automated task and motion planning, tested in an obstacle-rich environment with eight robots performing 40 reaching tasks in a shared workspace, where any robot can perform any task in any order. Our approach builds on a graph neural network (GNN) policy trained via RL on procedurally-generated environments with diverse obstacle layouts, robot configurations, and task distributions. It employs a graph representation of scenes and a graph policy neural network trained through reinforcement learning to generate trajectories of multiple robots, jointly solving the sub-problems of task allocation, scheduling, and motion planning. Trained on large randomly generated task sets in simulation, our policy generalizes zero-shot to unseen settings with varying robot placements, obstacle geometries, and task poses. We further demonstrate that the high-speed capability of our solution enables its use in workcell layout optimization, improving solution times. The speed and scalability of our planner also open the door to new capabilities such as fault-tolerant planning and online perception-based re-planning, where rapid adaptation to dynamic task sets is required.

cs.RO↗

arXiv2025

3D Feature Distillation with Object-Centric Priors

Grounding natural language to the physical world is a ubiquitous topic with a wide range of applications in computer vision and robotics. Recently, 2D vision-language models such as CLIP have been widely popularized, due to their impressive capabilities for open-vocabulary grounding in 2D images. Recent works aim to elevate 2D CLIP features to 3D via feature distillation, but either learn neural fields that are scene-specific and hence lack generalization, or focus on indoor room scan data that require access to multiple camera views, which is not practical in robot manipulation scenarios. Additionally, related methods typically fuse features at pixel-level and assume that all camera views are equally informative. In this work, we show that this approach leads to sub-optimal 3D features, both in terms of grounding accuracy, as well as segmentation crispness. To alleviate this, we propose a multi-view feature fusion strategy that employs object-centric priors to eliminate uninformative views based on semantic information, and fuse features at object-level via instance segmentation masks. To distill our object-centric 3D features, we generate a large-scale synthetic multi-view dataset of cluttered tabletop scenes, spawning 15k scenes from over 3300 unique object instances, which we make publicly available. We show that our method reconstructs 3D CLIP features with improved grounding capacity and spatial consistency, while doing so from single-view RGB-D, thus departing from the assumption of multiple camera views at test time. Finally, we show that our approach can generalize to novel tabletop domains and be re-purposed for 3D instance segmentation without fine-tuning, and demonstrate its utility for language-guided robotic grasping in clutter.

cs.CV↗

arXiv2025

Real-time Digital Double Framework to Predict Collapsible Terrains for Legged Robots

Inspired by the digital twinning systems, a novel real-time digital double framework is developed to enhance robot perception of the terrain conditions. Based on the very same physical model and motion control, this work exploits the use of such simulated digital double synchronized with a real robot to capture and extract discrepancy information between the two systems, which provides high dimensional cues in multiple physical quantities to represent differences between the modelled and the real world. Soft, non-rigid terrains cause common failures in legged locomotion, whereby visual perception solely is insufficient in estimating such physical properties of terrains. We used digital double to develop the estimation of the collapsibility, which addressed this issue through physical interactions during dynamic walking. The discrepancy in sensory measurements between the real robot and its digital double are used as input of a learning-based algorithm for terrain collapsibility analysis. Although trained only in simulation, the learned model can perform collapsibility estimation successfully in both simulation and real world. Our evaluation of results showed the generalization to different scenarios and the advantages of the digital double to reliably detect nuances in ground conditions.

cs.RO↗

arXiv2025

Scaling functions in the soft-wall AdS/QCD models

We investigate the static scaling behavior of the chiral condensate near the two-flavor critical point within the framework of the soft-wall AdS/QCD. The scaling functions are extracted from the chiral order parameters and are found to precisely match those obtained through mean-field calculations. Additionally, it is also checked that the scaling functions are independent of the specific construction of the holographic model. Furthermore, we develop the formalism for calculating the chiral susceptibility and demonstrate that the pseudo-critical temperatures obey the scaling law for moderate quark masses. It is shown that the temperature scaling could be comparable with those obtained from Dyson-Schwinger equations and lattice simulations. These findings could help improve the effectiveness of the soft-wall AdS/QCD.

hep-ph↗

arXiv2025

Towards Generalist Robot Learning from Internet Video: A Survey

Scaling deep learning to massive and diverse internet data has driven remarkable breakthroughs in domains such as video generation and natural language processing. Robot learning, however, has thus far failed to replicate this success and remains constrained by a scarcity of available data. Learning from videos (LfV) methods aim to address this data bottleneck by augmenting traditional robot data with large-scale internet video. This video data provides foundational information regarding physical dynamics, behaviours, and tasks, and can be highly informative for general-purpose robots. This survey systematically examines the emerging field of LfV. We first outline essential concepts, including detailing fundamental LfV challenges such as distribution shift and missing action labels in video data. Next, we comprehensively review current methods for extracting knowledge from large-scale internet video, overcoming LfV challenges, and improving robot learning through video-informed training. The survey concludes with a critical discussion of future opportunities. Here, we emphasize the need for scalable foundation model approaches that can leverage the full range of available internet video and enhance the learning of robot policies and dynamics models. Overall, the survey aims to inform and catalyse future LfV research, driving progress towards general-purpose robots.

cs.RO↗

arXiv2025

Phase transition of hot dense QCD Matter from a refined holographic EMD model

In this study, we begin by delineating the Einstein-Maxwell-Dilaton (EMD) model within the holographic QCD framework and deriving the equation of state through holographic renormalization. Subsequently, we utilize the Wald method to determine the first law of thermodynamics for a five-dimensional black hole, thereby confirming the alignment of our EMD model with the thermodynamics of the grand canonical ensemble in the boundary field theory. By employing the $n-2$ form in the Wald method, we proceed to calculate the shear viscosity in Gauss-Bonnet gravity. The results we obtain demonstrate consistency with those from first-order metric perturbation. Furthermore, we construct a refined EMD model that attains quantitative agreement with the lattice QCD equation of state and baryon number susceptibility data at finite density. Using this enhanced model, we delve into the investigation of signals related to the QCD phase transition critical endpoint. At present, no non-monotonic changes in $κσ^2$ have been observed within the 7$\sim$200 GeV collision energy range at STAR. However, our theoretical analysis suggests that if the chemical freeze-out line does not intersect the first-order phase transition line, a peak-like structure in $κσ^2$ is anticipated within the 3$\sim$5 GeV range.

hep-ph↗