arXiv subjects

Zonghao Zhang

Publications and source records attributed to Zonghao Zhang.

8 recordsLinked to original sources

arXiv2026

KiRAS: Keyframe Guided Self-Imitation for Robust and Adaptive Skill Learning in Quadruped Robots

With advances in reinforcement learning and imitation learning, quadruped robots can acquire diverse skills within a single policy by imitating multiple skill-specific datasets. However, the lack of datasets on complex terrains limits the ability of such multi-skill policies to generalize effectively in unstructured environments. Inspired by animation, we adopt keyframes as minimal and universal skill representations, relaxing dataset constraints and enabling the integration of terrain adaptability with skill diversity. We propose Keyframe Guided Self-Imitation for Robust and Adaptive Skill Learning (KiRAS), an end-to-end framework for acquiring and transitioning between diverse skill primitives on complex terrains. KiRAS first learns diverse skills on flat terrain through keyframe-guided self-imitation, eliminating the need for expert datasets; then continues training the same policy network on rough terrains to enhance robustness. To eliminate catastrophic forgetting, a proficiency-based Skill Initialization Technique is introduced. Experiments on Solo-8 and Unitree Go1 robots show that KiRAS enables robust skill acquisition and smooth transitions across challenging terrains. This framework demonstrates its potential as a lightweight platform for multi-skill generation and dataset collection. It further enables flexible skill transitions that enhance locomotion on challenging terrains.

cs.RO↗

arXiv2026

Thermal Stability and Phase Transformation of Conductive $\alpha$-$(\mathrm{Al}_{x}\mathrm{Ga}_{1-x})_{2}\mathrm{O}_{3}/\mathrm{Ga}_{2}\mathrm{O}_{3}$ Heterostructures on Sapphire Substrates

Thermal stability and phase transformation of conductive $\alpha$-$(\mathrm{Al}_{0.16}\mathrm{Ga}_{0.84})_{2}\mathrm{O}_{3}/\mathrm{Ga}_{2}\mathrm{O}_{3}$ heterostructures on sapphire substrates were investigated using in situ high-temperature X-ray diffraction (HT-XRD), scanning electron microscopy (SEM), and atomic force microscopy (AFM). Conductive $\alpha$-$(\mathrm{Al}_{0.16}\mathrm{Ga}_{0.84})_{2}\mathrm{O}_{3}/\mathrm{Ga}_{2}\mathrm{O}_{3}$ heterostructures with fluorine (F) doping were grown by mist chemical vapor deposition on sapphire substrates, achieving a Hall mobility of $28~\mathrm{cm^{2}\,V^{-1}\,s^{-1}}$ and an electron concentration of $1.4\times10^{20}~\mathrm{cm^{-3}}$. The heterostructures exhibited thermal stability up to approximately $550$--$

cond-mat.mtrl-sci↗

arXiv2025

MAP: Mitigating Hallucinations in Large Vision-Language Models with Map-Level Attention Processing

Large Vision-Language Models (LVLMs) have achieved impressive performance in multimodal tasks, but they still suffer from hallucinations, i.e., generating content that is grammatically accurate but inconsistent with visual inputs. In this work, we introduce a novel map-level perspective to mitigate hallucinations in LVLMs, interpreting the hidden states of the model as a 2D semantic map. We observe that factual information is widely distributed across this map, extending beyond the localized inter- or intra-layer regions targeted by most existing methods (e.g., contrastive decoding and layer-wise consistency). Building on this insight, we propose Map-Level Attention Processing (MAP), a training-free decoding method that effectively leverages factual information through attention-based map-level operations to improve factual consistency. Specifically, we employ Layer-Wise Criss-Cross Attention to progressively refine token representations at each decoding layer by aggregating tokens from both inter- and intra-layer dimensions. Additionally, a Global-Local Logit Fusion mechanism combines logits obtained before and after global attention to further refine predictions and improve accuracy. Our method consistently improves the truthfulness and performance of LVLMs across benchmarks, such as POPE, MME, and MMHal-Bench, demonstrating the potential of the map-level decoding strategy.

cs.CV↗

arXiv2025

STAR: Stage-Wise Attention-Guided Token Reduction for Efficient Large Vision-Language Models Inference

Although large vision-language models (LVLMs) leverage rich visual token representations to achieve strong performance on multimodal tasks, these tokens also introduce significant computational overhead during inference. Existing training-free token pruning methods typically adopt a single-stage strategy, focusing either on visual self-attention or visual-textual cross-attention. However, such localized perspectives often overlook the broader information flow across the model, leading to substantial performance degradation, especially under high pruning ratios. In this work, we propose STAR (Stage-wise Attention-guided token Reduction), a training-free, plug-and-play framework that approaches token pruning from a global perspective. Instead of pruning at a single point, STAR performs attention-guided reduction in two complementary stages: an early-stage pruning based on visual self-attention to remove redundant low-level features, and a later-stage pruning guided by cross-modal attention to discard task-irrelevant tokens. This holistic approach allows STAR to significantly reduce computational cost while better preserving task-critical information. Extensive experiments across multiple LVLM architectures and benchmarks show that STAR achieves strong acceleration while maintaining comparable, and in some cases even improved performance.

cs.LG↗

arXiv2024

Taylor Modeling and Comparative Research Containing Aspect-Ratio Dependent Optimization of Three-Dimensional Hk Superjunction MOSFETs

This paper presents a comprehensive study on aspect-ratio dependent optimization for specific on-resistance of three-dimensional high-k superjunction MOSFETs. The research introduces a Taylor modeling method, overcoming the computational limitations of the Bessel method. It also employs the Chynoweth model for more accurate breakdown voltage determination. The study provides a comparative analysis of four different superjunction structures, across five aspects: electric field, impact ionization integral, aspect ratio dependent optimization, charge imbalance effect and temperature. The findings offer valuable insights for the manufacturing guidance of superjunction structure selection

physics.app-ph↗

arXiv2024

Design and Process Analysis of a Split-Gate Trench Power MOSFET with Bottom-Trench Hk-Pillar Superjunction for Enhanced Performance

In this paper, we propose a simulation-based novel Split-Gate Trench MOSFET structure with an optimized fabrication process to enhance power efficiency, switching speed, and thermal stability for high-performance semiconductor applications. Integrating high-k pillars with superjunction structures beneath the split gate enhancing breakdown performance by reducing critical field intensity by up to 35%, the device achieves a 15% improvement in Figures of Merit (FOMs) for BV2/Ron,sp. Dynamic testing reveals approximately a 25% reduction in both input and output capacitance, as well as gate-to-drain charge (QGD). This reduction, coupled with an approximately 40% improvement in Baliga's High-Frequency Figure of Merit (BHFFOM) and over 20% increase in the New High-Frequency Figure of Merit (NHFFOM), underscores the design's suitability for high-speed, high-efficiency power electronics. Simulations examining the effects of high-k pillar depth indicate that an optimal depth of 3.5 um achieves a balanced performance between BV and Ron,sp. The influence of high-k materials on BT-Hk-SJ MOSFET performance was investigated by comparing hafnium dioxide (HfO2), nitride, and oxynitride. Among these, HfO2 demonstrated optimal performance across static, dynamic, and diode characteristics due to its high dielectric constant, while material choice had minimal impact, with variations kept within 5%.

physics.app-ph↗

arXiv2024

A Robust Quadruped Robot with Twisting Waist for Flexible Motions

The waist plays a crucial role in the agile movement of many animals in nature. It provides the torso with additional degrees of freedom and flexibility, inspiring researchers to incorporate this biological feature into robotic structures to enhance robot locomotion. This paper presents a cost-effective and low-complexity waist mechanism integrated into the structure of the open-source robot solo8, adding a new degree of freedom (DOF) to its torso. We refer to this novel robot as solo9. Additionally, we propose a full-body control method for the waist-equipped quadruped robot based on generative adversarial imitation learning (GAIL). During training, the discriminator is used as input for iterative optimization of the policy and dataset, enabling solo9 to achieve flexible steering maneuvers across various gaits. Extensive tests of solo9's steering capabilities, terrain adaptability, and robustness are conducted in both simulation and real-world scenarios, with detailed comparisons to solo8 and solo12, demonstrating the effectiveness of the control algorithm and the advantages of the waist mechanism.

cs.RO↗

arXiv2024

TCAD Simulation of Novel Multi-Spacer HK/MG 28nm Planar MOSFET for Sub-threshold Swing and DIBL Optimization

This study optimizes 28 nm planar MOSFET technology to reduce device leakage current and enhance switching speed. The specific aims are to decrease subthreshold swing (S.S.) and mitigate drain induced barrier lowering (DIBL) effect. Silvaco TCAD software is used for process (Athena) and device (Atlas) simulations. For the further development of MOSFET technology, we implemented our device (planar 28 nm n-MOSFET) with high-k metal-gate (HK/MG), lightly doped drain (LDD), multiple spacers (mult-spacers), and silicide. Simulation validation shows improvements over other 28 nm devices, with lower static power consumption and notable optimizations in both S.S. (69.8 mV/dec) and DIBL effect (30.5 mV/V).

physics.app-ph↗