arXiv subjects

Peng Zhou

Publications and source records attributed to Peng Zhou.

At least 73 records · Page 4Linked to original sources

arXiv2025

Wurtzite AlScN/AlN Superlattice Ferroelectrics Enable Endurance Beyond 1010 Cycles

Wurtzite ferroelectrics are rapidly emerging as a promising material class for next-generation non-volatile memory technologies, owing to their large remanent polarization, intrinsically ordered three-dimensional crystal structure, and full compatibility with CMOS processes and back-end-of-line (BEOL) integration. However, their practical implementation remains critically constrained by a severe endurance bottleneck: under conditions where the remanent polarization (2Pr) reaches or exceeds 200 uC/cm^2, devices typically undergo catastrophic failure before reaching 10^8 cycles. Here, we report a vacancy-confining superlattice strategy that addresses this limitation, achieving reliable ferroelectric switching beyond 10^10 cycles while preserving saturated polarization (2Pr >= 200 uC/cm^2). This is achieved by embedding periodic ultrathin AlN layers within AlScN films, forming wurtzite AlScN/AlN superlattices, in conjunction with a dynamic recovery protocol that actively stabilizes the defect landscape throughout repeated cycling. Atomic-resolution imaging and EELS spectrum imaging technique, supported by first-principles calculations, reveal a self-regulated defect topology in which nitrogen vacancies are spatially confined by heterostructure energy barriers and dynamically re-trapped into energetically favorable lattice sites. This dual spatial-energetic confinement mechanism effectively inhibits both long-range percolative migration and local defect clustering, enabling such an ultrahigh endurance exceeding 10^10 cycles and limiting polarization degradation to below 3% after 10^9 cycles. These findings establish nitrogen vacancy topology stabilization as a foundational design principle for reliable operation of wurtzite ferroelectrics, providing a scalable and CMOS-compatible platform for future high-endurance ferroelectric memory technologies.

cond-mat.mtrl-sci↗

arXiv2025

A$^2$ATS: Retrieval-Based KV Cache Reduction via Windowed Rotary Position Embedding and Query-Aware Vector Quantization

Long context large language models (LLMs) pose significant challenges for efficient serving due to the large memory footprint and high access overhead of KV cache. Retrieval-based KV cache reduction methods can mitigate these challenges, typically by offloading the complete KV cache to CPU and retrieving necessary tokens on demand during inference. However, these methods still suffer from unsatisfactory accuracy degradation and extra retrieval overhead. To address these limitations, this paper proposes A$^2$ATS, a novel retrieval-based KV cache reduction method. A$^2$ATS aims to obtain an accurate approximation of attention scores by applying the vector quantization technique to key states, thereby enabling efficient and precise retrieval of the top-K tokens. First, we propose Windowed Rotary Position Embedding, which decouples the positional dependency from query and key states after position embedding. Then, we propose query-aware vector quantization that optimizes the objective of attention score approximation directly. Finally, we design the heterogeneous inference architecture for KV cache offloading, enabling long context serving with larger batch sizes. Experimental results demonstrate that A$^2$ATS can achieve a lower performance degradation with similar or lower overhead compared to existing methods, thereby increasing long context serving throughput by up to $2.7 \times$.

cs.CL↗

arXiv2025

Hybrid Local Causal Discovery

Local causal discovery aims to learn and distinguish the direct causes and effects of a target variable from observed data. Existing constraint-based local causal discovery methods use AND or OR rules in constructing the local causal skeleton, but using either rule alone is prone to produce cascading errors in the learned local causal skeleton, and thus impacting the inference of local causal relationships. On the other hand, directly applying score-based global causal discovery methods to local causal discovery may randomly return incorrect results due to the existence of local equivalence classes. To address the above issues, we propose a Hybrid Local Causal Discovery algorithm, called HLCD. Specifically, HLCD initially utilizes a constraint-based approach combined with the OR rule to obtain a candidate skeleton and then employs a score-based method to eliminate redundant portions in the candidate skeleton. Furthermore, during the local causal orientation phase, HLCD distinguishes between V-structures and equivalence classes by comparing the local structure scores between the two, thereby avoiding orientation interference caused by local equivalence classes. We conducted extensive experiments with seven state-of-the-art competitors on 14 benchmark Bayesian network datasets, and the experimental results demonstrate that HLCD significantly outperforms existing local causal discovery algorithms.

cs.AI↗

arXiv2025

M-LLM Based Video Frame Selection for Efficient Video Understanding

Recent advances in Multi-Modal Large Language Models (M-LLMs) show promising results in video reasoning. Popular Multi-Modal Large Language Model (M-LLM) frameworks usually apply naive uniform sampling to reduce the number of video frames that are fed into an M-LLM, particularly for long context videos. However, it could lose crucial context in certain periods of a video, so that the downstream M-LLM may not have sufficient visual information to answer a question. To attack this pain point, we propose a light-weight M-LLM -based frame selection method that adaptively select frames that are more relevant to users' queries. In order to train the proposed frame selector, we introduce two supervision signals (i) Spatial signal, where single frame importance score by prompting a M-LLM; (ii) Temporal signal, in which multiple frames selection by prompting Large Language Model (LLM) using the captions of all frame candidates. The selected frames are then digested by a frozen downstream video M-LLM for visual reasoning and question answering. Empirical results show that the proposed M-LLM video frame selector improves the performances various downstream video Large Language Model (video-LLM) across medium (ActivityNet, NExT-QA) and long (EgoSchema, LongVideoBench) context video question answering benchmarks.

cs.CV↗

arXiv2025

AlignBot: Aligning VLM-powered Customized Task Planning with User Reminders Through Fine-Tuning for Household Robots

This paper presents AlignBot, a novel framework designed to optimize VLM-powered customized task planning for household robots by effectively aligning with user reminders. In domestic settings, aligning task planning with user reminders poses significant challenges due to the limited quantity, diversity, and multimodal nature of the reminders. To address these challenges, AlignBot employs a fine-tuned LLaVA-7B model, functioning as an adapter for GPT-4o. This adapter model internalizes diverse forms of user reminders-such as personalized preferences, corrective guidance, and contextual assistance-into structured instruction-formatted cues that prompt GPT-4o in generating customized task plans. Additionally, AlignBot integrates a dynamic retrieval mechanism that selects task-relevant historical successes as prompts for GPT-4o, further enhancing task planning accuracy. To validate the effectiveness of AlignBot, experiments are conducted in real-world household environments, which are constructed within the laboratory to replicate typical household settings. A multimodal dataset with over 1,500 entries derived from volunteer reminders is used for training and evaluation. The results demonstrate that AlignBot significantly improves customized task planning, outperforming existing LLM- and VLM-powered planners by interpreting and aligning with user reminders, achieving 86.8% success rate compared to the vanilla GPT-4o baseline at 21.6%, reflecting a 65% improvement and over four times greater effectiveness. Supplementary materials are available at: https://yding25.com/AlignBot/

cs.RO↗

arXiv2025

Instruction-Augmented Long-Horizon Planning: Embedding Grounding Mechanisms in Embodied Mobile Manipulation

Enabling humanoid robots to perform long-horizon mobile manipulation planning in real-world environments based on embodied perception and comprehension abilities has been a longstanding challenge. With the recent rise of large language models (LLMs), there has been a notable increase in the development of LLM-based planners. These approaches either utilize human-provided textual representations of the real world or heavily depend on prompt engineering to extract such representations, lacking the capability to quantitatively understand the environment, such as determining the feasibility of manipulating objects. To address these limitations, we present the Instruction-Augmented Long-Horizon Planning (IALP) system, a novel framework that employs LLMs to generate feasible and optimal actions based on real-time sensor feedback, including grounded knowledge of the environment, in a closed-loop interaction. Distinct from prior works, our approach augments user instructions into PDDL problems by leveraging both the abstract reasoning capabilities of LLMs and grounding mechanisms. By conducting various real-world long-horizon tasks, each consisting of seven distinct manipulatory skills, our results demonstrate that the IALP system can efficiently solve these tasks with an average success rate exceeding 80%. Our proposed method can operate as a high-level planner, equipping robots with substantial autonomy in unstructured environments through the utilization of multi-modal sensor inputs.

cs.RO↗

arXiv2025

FRT Regulation in China

This paper first introduces China's legal framework regulating facial recognition technology (FRT) and analyzes the underlying problems. Although current laws and regulations have restricted the development of FRT under some circumstances, these restrictions may function poorly when the technology is installed by the government or when it is deployed for the purpose of protecting public security. We use two cases to illustrate this asymmetric regulatory model, which can be traced to systematic preferences that existed prior to recent legislative efforts advancing personal data protection. Based on these case studies and evaluation of relevant regulations, this paper explains why China has developed this distinctive asymmetric regulatory model towards FRT specifically and personally data generally.

cs.CY↗

arXiv2025

Ferromagnetic resonance and spin Hall magnetoresistance of Tm3Fe5O12 films

Ferromagnetic insulating garnet films with perpendicular magnetic anisotropy (PMA) are of great importance for the applications in spintronics. Tm3Fe5O12 (TmIG) with magnetoelastic anisotropy has been proven to exhibit PMA more easily than Y3Fe5O12. Here, magnetic parameters of TmIG films with various thicknesses are investigated by ferromagnetic resonance. The relationship between effective magnetic magnetization, surface perpendicular anisotropy field, magnetic anisotropy constants and film thickness is established. The parameters of spin Hall angle, spin diffusion length, and real part of the spin mixing conductance are obtained from the measurements of angular dependent magnetoresistance of TmIG/Pt heterostructures.

cond-mat.mtrl-sci↗

arXiv2025

Progress of the TianQin project

TianQin is a future space-based gravitational wave observatory targeting the frequency window of $10^{-4}$ Hz $\sim 1$ Hz. A large variety of gravitational wave sources are expected in this frequency band, including the merger of massive black hole binaries, the inspiral of extreme/intermediate mass ratio systems, stellar-mass black hole binaries, Galactic compact binaries, and so on. TianQin will consist of three Earth orbiting satellites on nearly identical orbits with orbital radii of about $10^5$ km. The satellites will form a normal triangle constellation whose plane is nearly perpendicular to the ecliptic plane. The TianQin project has been progressing smoothly following the ``0123" technology roadmap. In step ``0", the TianQin laser ranging station has been constructed and it has successfully ranged to all the five retro-reflectors on the Moon. In step ``1", the drag-free control technology has been tested and demonstrated using the TianQin-1 satellite. In step ``2", the inter-satellite laser interferometry technology will be tested using the pair of TianQin-2 satellites. The TianQin-2 mission has been officially approved and the satellites will be launched around 2026. In step ``3", i.e., the TianQin-3 mission, three identical satellites will be launched around 2035 to form the space-based gravitational wave detector, TianQin, and to start gravitational wave detection in space.

gr-qc↗

arXiv2025

GKZ discriminant and Multiplicities

Let $T=(\C^*)^k$ act on $V=\C^N$ faithfully and preserving the volume form, i.e. $(\C^*)^k \into \text{SL}(V)$. On the B-side, we have toric stacks $Z_W$ (see Eq. \ref{eq:ZW})labelled by walls $W$ in the GKZ fan, and $Z_{/F}$ labelled by faces of a polytope corresponding to minimal semi-orthogonal decomposition (SOD) components. The B-side multiplicity $n^B_{W,F}$, well-defined by a result of Kite-Segal \cite{kite-segal}, is the number of times $\Coh(Z_{/F})$ appears in a complete SOD of $\Coh(Z_W)$. On the A-side, we have the GKZ discriminant loci components $\nabla_F \In (\C^*)^k$, and its tropicalization $\nabla^{trop}_{F} \In \R^k$. The A-side multiplicity $n^A_{W, F}$ is defined as the multiplicity of the tropical complex $\nabla^{trop}_{F}$ on wall $W$. We prove that $n^A_{W,F} = n^B_{W,F}$, confirming a conjecture in Kite-Segal \cite{kite-segal} inspired by \cite{aspinwall2017mirror}. Our proof is based on the result of Horja-Katzarkov \cite{horja2022discriminants} and a lemma about B-side SOD multiplicity, which allows us to reduce to lower dimension just as in A-side \cite{GKZ-book}[Ch 11].

math.AG↗

arXiv2025

Angular dependent ferromagnetic resonance of exfoliated yttrium iron garnet film under stress

Yttrium iron garnet (Y3Fe5O12, YIG) plays a significant role in the field of spintronics due to its low magnetic damping and insulating characteristics. However, most studies have focused on YIG in bulk form or as film grown on rigid substrates. In this study, YIG film has been exfoliated from two-layer-graphene covered (111) Gd3Ga5O12 (GGG) substrate. Magnetic properties of YIG film under stress are investigated in detail via angular dependent ferromagnetic resonance. The relationship between magnetic parameters and compressive/tensile stress has been established. The findings of this work will be beneficial for the applications of flexible YIG film.

cond-mat.mtrl-sci↗

arXiv2025

Iterative Shaping of Multi-Particle Aggregates based on Action Trees and VLM

In this paper, we address the problem of manipulating multi-particle aggregates using a bimanual robotic system. Our approach enables the autonomous transport of dispersed particles through a series of shaping and pushing actions using robotically-controlled tools. Achieving this advanced manipulation capability presents two key challenges: high-level task planning and trajectory execution. For task planning, we leverage Vision Language Models (VLMs) to enable primitive actions such as tool affordance grasping and non-prehensile particle pushing. For trajectory execution, we represent the evolving particle aggregate's contour using truncated Fourier series, providing efficient parametrization of its closed shape. We adaptively compute trajectory waypoints based on group cohesion and the geometric centroid of the aggregate, accounting for its spatial distribution and collective motion. Through real-world experiments, we demonstrate the effectiveness of our methodology in actively shaping and manipulating multi-particle aggregates while maintaining high system cohesion.

cs.RO↗

arXiv2025

Threshold Neuron: A Brain-inspired Artificial Neuron for Efficient On-device Inference

Enhancing the computational efficiency of on-device Deep Neural Networks (DNNs) remains a significant challengein mobile and edge computing. As we aim to execute increasingly complex tasks with constrained computational resources, much of the research has focused on compressing neural network structures and optimizing systems. Although many studies have focused on compressing neural network structures and parameters or optimizing underlying systems, there has been limited attention on optimizing the fundamental building blocks of neural networks: the neurons. In this study, we deliberate on a simple but important research question: Can we design artificial neurons that offer greater efficiency than the traditional neuron paradigm? Inspired by the threshold mechanisms and the excitation-inhibition balance observed in biological neurons, we propose a novel artificial neuron model, Threshold Neurons. Using Threshold Neurons, we can construct neural networks similar to those with traditional artificial neurons, while significantly reducing hardware implementation complexity. Our extensive experiments validate the effectiveness of neural networks utilizing Threshold Neurons, achieving substantial power savings of 7.51x to 8.19x and area savings of 3.89x to 4.33x at the kernel level, with minimal loss in precision. Furthermore, FPGA-based implementations of these networks demonstrate 2.52x power savings and 1.75x speed enhancements at the system level. The source code will be made available upon publication.

cs.LG↗

arXiv2024

Sharper Error Bounds in Late Fusion Multi-view Clustering Using Eigenvalue Proportion

Multi-view clustering (MVC) aims to integrate complementary information from multiple views to enhance clustering performance. Late Fusion Multi-View Clustering (LFMVC) has shown promise by synthesizing diverse clustering results into a unified consensus. However, current LFMVC methods struggle with noisy and redundant partitions and often fail to capture high-order correlations across views. To address these limitations, we present a novel theoretical framework for analyzing the generalization error bounds of multiple kernel $k$-means, leveraging local Rademacher complexity and principal eigenvalue proportions. Our analysis establishes a convergence rate of $\mathcal{O}(1/n)$, significantly improving upon the existing rate in the order of $\mathcal{O}(\sqrt{k/n})$. Building on this insight, we propose a low-pass graph filtering strategy within a multiple linear $k$-means framework to mitigate noise and redundancy, further refining the principal eigenvalue proportion and enhancing clustering accuracy. Experimental results on benchmark datasets confirm that our approach outperforms state-of-the-art methods in clustering performance and robustness. The related codes is available at https://github.com/csliangdu/GMLKM .

cs.LG↗

arXiv2024

Deployment Pipeline from Rockpool to Xylo for Edge Computing

Deploying Spiking Neural Networks (SNNs) on the Xylo neuromorphic chip via the Rockpool framework represents a significant advancement in achieving ultra-low-power consumption and high computational efficiency for edge applications. This paper details a novel deployment pipeline, emphasizing the integration of Rockpool's capabilities with Xylo's architecture, and evaluates the system's performance in terms of energy efficiency and accuracy. The unique advantages of the Xylo chip, including its digital spiking architecture and event-driven processing model, are highlighted to demonstrate its suitability for real-time, power-sensitive applications.

cs.NE↗

arXiv2024

Unsupervised Feature Selection Algorithm Based on Graph Filtering and Self-representation

Aiming at the problem that existing methods could not fully capture the intrinsic structure of data without considering the higher-order neighborhood information of the data, we proposed an unsupervised feature selection algorithm based on graph filtering and self-representation. Firstly,a higher-order graph filter was applied to the data to obtain its smooth representation,and a regularizer was designed to combine the higher-order graph information for the self-representation matrix learning to capture the intrinsic structure of the data. Secondly,l2,1 norm was used to reconstruct the error term and feature selection matrix to enhance the robustness and row sparsity of the model to select the discriminant features. Finally, an iterative algorithm was applied to effectively solve the proposed objective function and simulation experiments were carried out to verify the effectiveness of the proposed algorithm.

cs.LG↗

arXiv2024

Gated Slot Attention for Efficient Linear-Time Sequence Modeling

Linear attention Transformers and their gated variants, celebrated for enabling parallel training and efficient recurrent inference, still fall short in recall-intensive tasks compared to traditional Transformers and demand significant resources for training from scratch. This paper introduces Gated Slot Attention (GSA), which enhances Attention with Bounded-memory-Control (ABC) by incorporating a gating mechanism inspired by Gated Linear Attention (GLA). Essentially, GSA comprises a two-layer GLA linked via $\operatorname{softmax}$, utilizing context-aware memory reading and adaptive forgetting to improve memory capacity while maintaining compact recurrent state size. This design greatly enhances both training and inference efficiency through GLA's hardware-efficient training algorithm and reduced state size. Additionally, retaining the $\operatorname{softmax}$ operation is particularly beneficial in "finetuning pretrained Transformers to RNNs" (T2R) settings, reducing the need for extensive training from scratch. Extensive experiments confirm GSA's superior performance in scenarios requiring in-context recall and in T2R settings.

cs.CL↗

arXiv2024

Clustering ensemble algorithm with high-order consistency learning

Most of the research on clustering ensemble focuses on designing practical consistency learning algorithms.To solve the problems that the quality of base clusters varies and the low-quality base clusters have an impact on the performance of the clustering ensemble, from the perspective of data mining, the intrinsic connections of data were mined based on the base clusters, and a high-order information fusion algorithm was proposed to represent the connections between data from different dimensions, namely Clustering Ensemble with High-order Consensus learning (HCLCE). Firstly, each high-order information was fused into a new structured consistency matrix. Then, the obtained multiple consistency matrices were fused together. Finally, multiple information was fused into a consistent result. Experimental results show that LCLCE algorithm has the clustering accuracy improved by an average of 7.22%, and the Normalized Mutual Information (NMI) improved by an average of 9.19% compared with the suboptimal Locally Weighted Evidence Accumulation (LWEA) algorithm. It can be seen that the proposed algorithm can obtain better clustering results compared with clustering ensemble algorithms and using one information alone.

cs.LG↗