arXiv subjects

Peng Liu

Publications and source records attributed to Peng Liu.

At least 127 records · Page 7Linked to original sources

arXiv2025

Apple Intelligence Foundation Language Models: Tech Report 2025

We introduce two multilingual, multimodal foundation language models that power Apple Intelligence features across Apple devices and services: i a 3B-parameter on-device model optimized for Apple silicon through architectural innovations such as KV-cache sharing and 2-bit quantization-aware training; and ii a scalable server model built on a novel Parallel-Track Mixture-of-Experts PT-MoE transformer that combines track parallelism, mixture-of-experts sparse computation, and interleaved global-local attention to deliver high quality with competitive cost on Apple's Private Cloud Compute platform. Both models are trained on large-scale multilingual and multimodal datasets sourced via responsible web crawling, licensed corpora, and high-quality synthetic data, then further refined with supervised fine-tuning and reinforcement learning on a new asynchronous platform. The resulting models support several additional languages while understanding images and executing tool calls. In public benchmarks and human evaluations, both the server model and the on-device model match or surpass comparably sized open baselines. A new Swift-centric Foundation Models framework exposes guided generation, constrained tool calling, and LoRA adapter fine-tuning, allowing developers to integrate these capabilities with a few lines of code. The latest advancements in Apple Intelligence models are grounded in our Responsible AI approach with safeguards like content filtering and locale-specific evaluation, as well as our commitment to protecting our users' privacy with innovations like Private Cloud Compute.

cs.LG↗

arXiv2025

Step-Audio 2 Technical Report

This paper presents Step-Audio 2, an end-to-end multi-modal large language model designed for industry-strength audio understanding and speech conversation. By integrating a latent audio encoder and reasoning-centric reinforcement learning (RL), Step-Audio 2 achieves promising performance in automatic speech recognition (ASR) and audio understanding. To facilitate genuine end-to-end speech conversation, Step-Audio 2 incorporates the generation of discrete audio tokens into language modeling, significantly enhancing its responsiveness to paralinguistic information such as speaking styles and emotions. To effectively leverage the rich textual and acoustic knowledge in real-world data, Step-Audio 2 integrates retrieval-augmented generation (RAG) and is able to call external tools such as web search to mitigate hallucination and audio search to switch timbres. Trained on millions of hours of speech and audio data, Step-Audio 2 delivers intelligence and expressiveness across diverse conversational scenarios. Evaluation results demonstrate that Step-Audio 2 achieves state-of-the-art performance on various audio understanding and conversational benchmarks compared to other open-source and commercial solutions. Please visit https://github.com/stepfun-ai/Step-Audio2 for more information.

cs.CL↗

arXiv2025

Capturing quantum phase transition in the ultraviolet region by holography

We reveal for the first time that ultraviolet (UV) observables can diagnose quantum phase transitions (QPTs). In a class of holographic models exhibiting metal-insulator transitions, we study two types of UV observables -- high-frequency conductivity and short-range entanglement. Remarkably, we find that the derivatives of these UV observables exhibit extrema near the quantum critical point. Analytical results show these critical behaviors arise from the deformation of the asymptotic bulk geometry. Moreover, these UV diagnostics show enhanced robustness to thermal fluctuations compared to typical infrared (IR) diagnostics, providing a clean method to identify quantum criticality at finite temperature. This work opens a new window for exploring quantum critical phenomena via UV physics in the laboratory.

hep-th↗

arXiv2025

Semi-supervised Image Dehazing via Expectation-Maximization and Bidirectional Brownian Bridge Diffusion Models

Existing dehazing methods deal with real-world haze images with difficulty, especially scenes with thick haze. One of the main reasons is the lack of real-world paired data and robust priors. To avoid the costly collection of paired hazy and clear images, we propose an efficient semi-supervised image dehazing method via Expectation-Maximization and Bidirectional Brownian Bridge Diffusion Models (EM-B3DM) with a two-stage learning scheme. In the first stage, we employ the EM algorithm to decouple the joint distribution of paired hazy and clear images into two conditional distributions, which are then modeled using a unified Brownian Bridge diffusion model to directly capture the structural and content-related correlations between hazy and clear images. In the second stage, we leverage the pre-trained model and large-scale unpaired hazy and clear images to further improve the performance of image dehazing. Additionally, we introduce a detail-enhanced Residual Difference Convolution block (RDC) to capture gradient-level information, significantly enhancing the model's representation capability. Extensive experiments demonstrate that our EM-B3DM achieves superior or at least comparable performance to state-of-the-art methods on both synthetic and real-world datasets.

cs.CV↗

arXiv2025

Theorem-Carrying Transactions: Runtime Verification to Ensure Interface Specifications for Smart Contract Safety

Security bugs and trapdoors in smart contracts have been impacting the Ethereum community since its inception. Conceptually, the 1.45-million Ethereum's contracts form a single "gigantic program" whose behaviors are determined by the complex compositions of contracts. Can programmers be assured that this gigantic program conforms to high-level safety specifications, despite unforeseeable code-level intricacies? Static code verification cannot be faithful to this gigantic program due to its scale and high polymorphism. In this paper, we present a viable approach to achieve this goal. Our technology, called Theorem-Carrying Transactions (TCT), combines the benefits of concrete execution and symbolic proofs. Under the TCT protocol, every transaction carries a theorem that proves its adherence to the specified properties in the invoked contracts, and the runtime system checks the theorem before executing the transaction. Once a theorem is proven, it will be reused for future transactions, so TCT's runtime overhead is minimal. As case studies, we demonstrate that TCT secures token contracts without foreseeing code-level intricacies, such as integer overflow and reentrancy. TCT is also successfully applied to a Uniswap codebase, showcasing a complex decentralized finance (DeFi) scenario. Our evaluation shows a negligible runtime overhead, two orders of magnitude lower than a state-of-the-art approach for runtime checking of contract code safety.

cs.CR↗

arXiv2025

PIVOTS: Aligning unseen Structures using Preoperative to Intraoperative Volume-To-Surface Registration for Liver Navigation

Non-rigid registration is essential for Augmented Reality guided laparoscopic liver surgery by fusing preoperative information, such as tumor location and vascular structures, into the limited intraoperative view, thereby enhancing surgical navigation. A prerequisite is the accurate prediction of intraoperative liver deformation which remains highly challenging due to factors such as large deformation caused by pneumoperitoneum, respiration and tool interaction as well as noisy intraoperative data, and limited field of view due to occlusion and constrained camera movement. To address these challenges, we introduce PIVOTS, a Preoperative to Intraoperative VOlume-To-Surface registration neural network that directly takes point clouds as input for deformation prediction. The geometric feature extraction encoder allows multi-resolution feature extraction, and the decoder, comprising novel deformation aware cross attention modules, enables pre- and intraoperative information interaction and accurate multi-level displacement prediction. We train the neural network on synthetic data simulated from a biomechanical simulation pipeline and validate its performance on both synthetic and real datasets. Results demonstrate superior registration performance of our method compared to baseline methods, exhibiting strong robustness against high amounts of noise, large deformation, and various levels of intraoperative visibility. We publish the training and test sets as evaluation benchmarks and call for a fair comparison of liver registration methods with volume-to-surface data. Code and datasets are available here https://github.com/pengliu-nct/PIVOTS.

cs.CV↗

arXiv2025

OpenHuman4D: Open-Vocabulary 4D Human Parsing

Understanding dynamic 3D human representation has become increasingly critical in virtual and extended reality applications. However, existing human part segmentation methods are constrained by reliance on closed-set datasets and prolonged inference times, which significantly restrict their applicability. In this paper, we introduce the first 4D human parsing framework that simultaneously addresses these challenges by reducing the inference time and introducing open-vocabulary capabilities. Building upon state-of-the-art open-vocabulary 3D human parsing techniques, our approach extends the support to 4D human-centric video with three key innovations: 1) We adopt mask-based video object tracking to efficiently establish spatial and temporal correspondences, avoiding the necessity of segmenting all frames. 2) A novel Mask Validation module is designed to manage new target identification and mitigate tracking failures. 3) We propose a 4D Mask Fusion module, integrating memory-conditioned attention and logits equalization for robust embedding fusion. Extensive experiments demonstrate the effectiveness and flexibility of the proposed method on 4D human-centric parsing tasks, achieving up to 93.3% acceleration compared to the previous state-of-the-art method, which was limited to parsing fixed classes.

cs.CV↗

arXiv2025

Multicolor interband solitons in microcombs

In microcombs, solitons can drive non-soliton-forming modes to induce optical gain. Under specific conditions, a regenerative secondary temporal pulse coinciding in time and space with the exciting soliton pulse will form at a new spectral location. A mechanism involving Kerr-induced pulse interactions has been proposed theoretically, leading to multicolor solitons containing constituent phase-locked pulses. However, the occurrence of this phenomenon requires dispersion conditions that are not naturally satisfied in conventional optical microresonators. Here, we report the experimental observation of multicolor pulses from a single optical pump in a way that is closely related to the concept of multicolor solitons. The individual soliton pulses share the same repetition rate and could potentially be fully phase-locked. They are generated using interband coupling in a compound resonator.

physics.optics↗

arXiv2025

Residual Prior-driven Frequency-aware Network for Image Fusion

Image fusion aims to integrate complementary information across modalities to generate high-quality fused images, thereby enhancing the performance of high-level vision tasks. While global spatial modeling mechanisms show promising results, constructing long-range feature dependencies in the spatial domain incurs substantial computational costs. Additionally, the absence of ground-truth exacerbates the difficulty of capturing complementary features effectively. To tackle these challenges, we propose a Residual Prior-driven Frequency-aware Network, termed as RPFNet. Specifically, RPFNet employs a dual-branch feature extraction framework: the Residual Prior Module (RPM) extracts modality-specific difference information from residual maps, thereby providing complementary priors for fusion; the Frequency Domain Fusion Module (FDFM) achieves efficient global feature modeling and integration through frequency-domain convolution. Additionally, the Cross Promotion Module (CPM) enhances the synergistic perception of local details and global structures through bidirectional feature interaction. During training, we incorporate an auxiliary decoder and saliency structure loss to strengthen the model's sensitivity to modality-specific differences. Furthermore, a combination of adaptive weight-based frequency contrastive loss and SSIM loss effectively constrains the solution space, facilitating the joint capture of local details and global features while ensuring the retention of complementary information. Extensive experiments validate the fusion performance of RPFNet, which effectively integrates discriminative features, enhances texture details and salient objects, and can effectively facilitate the deployment of the high-level vision task.

cs.CV↗

arXiv2025

Latency Minimization Oriented Radio and Computation Resource Allocations for 6G V2X Networks with ISCC

Incorporating mobile edge computing (MEC) and integrated sensing and communication (ISAC) has emerged as a promising technology to enable integrated sensing, communication, and computing (ISCC) in the sixth generation (6G) networks. ISCC is particularly attractive for vehicle-to-everything (V2X) applications, where vehicles perform ISAC to sense the environment and simultaneously offload the sensing data to roadside base stations (BSs) for remote processing. In this paper, we investigate a particular ISCC-enabled V2X system consisting of multiple multi-antenna BSs serving a set of single-antenna vehicles, in which the vehicles perform their respective ISAC operations (for simultaneous sensing and offloading to the associated BS) over orthogonal sub-bands. With the focus on fairly minimizing the sensing completion latency for vehicles while ensuring the detection probability constraints, we jointly optimize the allocations of radio resources (i.e., the sub-band allocation, transmit power control at vehicles, and receive beamforming at BSs) as well as computation resources at BS MEC servers. To solve the formulated complex mixed-integer nonlinear programming (MINLP) problem, we propose an alternating optimization algorithm. In this algorithm, we determine the sub-band allocation via the branch-and-bound method, optimize the transmit power control via successive convex approximation (SCA), and derive the receive beamforming and computation resource allocation at BSs in closed form based on generalized Rayleigh entropy and fairness criteria, respectively. Simulation results demonstrate that the proposed joint resource allocation design significantly reduces the maximum task completion latency among all vehicles. Furthermore, we also demonstrate several interesting trade-offs between the system performance and resource utilizations.

eess.SP↗

arXiv2025

DHEvo: Data-Algorithm Based Heuristic Evolution for Generalizable MILP Solving

Primal heuristics play a critical role in improving the efficiency of mixed integer programming (MILP) solvers. As large language models (LLMs) have demonstrated superior code generation abilities, recent MILP works are devoted to leveraging the evolutionary computation approaches with LLMs to generate effective primal heuristics. Although the generated heuristics have achieved better solving performance than the hand-crafted ones with little adaptability, the advantage of current LLM-based methods is limited to few MILP instances in one problem class, as they fail to capture the instance characteristics in the problem class (the MILP instances generated from the same mathematical model are defined as a problem class). Since MILP instances often differ significantly in structure and feature distribution, the neglect of their characteristics in the evolution process results in poor generalization within the same problem class. To overcome this challenge, we propose a data-algorithm co-evolution framework (DHEvo) that iteratively selects representative instances and evolves corresponding heuristics. With the initial instance distribution, we develop an LLM-based multi-agent system to generate data-code pairs simultaneously. These data-code pairs are iteratively refined based on their fitness scores, leading to the identification of the most effective heuristic over the entire problem class. Extensive experiments across diverse MILP benchmarks demonstrate that our approach significantly outperforms both human-designed heuristics and existing LLM-based methods.

cs.NE↗

arXiv2025

A Decade of Deep Learning for Remote Sensing Spatiotemporal Fusion: Advances, Challenges, and Opportunities

Remote sensing spatiotemporal fusion (STF) addresses the fundamental trade-off between temporal and spatial resolution by combining high temporal-low spatial and high spatial-low temporal imagery. This paper presents the first comprehensive survey of deep learning advances in remote sensing STF over the past decade. We establish a systematic taxonomy of deep learning architectures including Convolutional Neural Networks (CNNs), Transformers, Generative Adversarial Networks (GANs), diffusion models, and sequence models, revealing significant growth in deep learning adoption for STF tasks. Our analysis reveals that CNN-based methods dominate spatial feature extraction, while Transformer architectures show superior performance in capturing long-range temporal dependencies. GAN and diffusion models demonstrate exceptional capability in detail reconstruction, substantially outperforming traditional methods in structural similarity and spectral fidelity. Through comprehensive experiments on seven benchmark datasets comparing ten representative methods, we validate these findings and quantify the performance trade-offs between different approaches. We identify five critical challenges: time-space conflicts, limited generalization across datasets, computational efficiency for large-scale processing, multi-source heterogeneous fusion, and insufficient benchmark diversity. The survey highlights promising opportunities in foundation models, hybrid architectures, and self-supervised learning approaches that could address current limitations and enable multimodal applications. The specific models, datasets, and other information mentioned in this article have been collected in: https://github.com/yc-cui/Deep-Learning-Spatiotemporal-Fusion-Survey.

cs.CV↗

arXiv2025

Timing results of 22 years for PSR J0922+0638

We conducted a timing analysis of PSR J0922+0638 (B0919+06) using data from the Nanshan 26 m radio telescope and the MeerKAT telescope, spanning from January 2001 to March 2023. During this 22-year period, we discovered a previously unreported small glitch (glitch 1) before the well-known large glitch (glitch 2), occurring at ${\rm MJD} \sim 53325(3)$, with a frequency jump amplitude of $Δν/ν\sim 0.79(6) \times 10^{-9}$. We also identified ten slow glitch events, half of which were newly detected. These slow glitches occurred quasi-periodically, with an average interval of approximately 553(21) days, fractional frequency changes ranging from $Δν/ν\sim 1.13(1) \times 10^{-9}$ to $4.08(5) \times 10^{-9}$, and a maximum fractional change in the first derivative of the frequency of $Δ\dotν/\dotν \sim -4.6 \times 10^{-3}$. Additionally, our timing noise analysis reveals a change in the spectral index for noise power before and after glitch 2, with values of $-6.0$ and $-5.3$, respectively, likely due to this large glitch. Throughout the entire observation period, the first derivative of the spin frequency ($\dotν$) showed a periodic structure. The possible modulation period was estimated to be 537(24) days before the 700-day data gap at MJD 56716 and 600(58) days afterward. We discuss the periodic oscillations in pulsar rotation as a possible manifestation of spin-down noise and quasi-periodic slow glitches.

astro-ph.HE↗

arXiv2025

Indeterminate Probability Theory

Complex continuous or mixed joint distributions (e.g., P(Y | z_1, z_2, ..., z_N)) generally lack closed-form solutions, often necessitating approximations such as MCMC. This paper proposes Indeterminate Probability Theory (IPT), which makes the following contributions: (1) An observer-centered framework in which experimental outcomes are represented as distributions combining ground truth with observation error; (2) The introduction of three independence candidate axioms that enable a two-phase probabilistic inference framework; (3) The derivation of closed-form solutions for arbitrary complex joint distributions under this framework. Both the Indeterminate Probability Neural Network (IPNN) model and the non-neural multivariate time series forecasting application demonstrate IPT's effectiveness in modeling high-dimensional distributions, with successful validation up to 1000 dimensions. Importantly, IPT is consistent with classical probability theory and subsumes the frequentist equation in the limit of vanishing observation error.

cs.LG↗

arXiv2025

Computation Capacity Maximization for Pinching Antennas-Assisted Wireless Powered MEC Systems

In this paper,we investigate a novel wireless powered mobile edge computing (MEC) system assisted by pinching antennas (PAs), where devices first harvest energy from a base station and then offload computation-intensive tasks to an MEC server. As an emerging technology, PAs utilize long dielectric waveguides embedded with multiple localized dielectric particles, which can be spatially configured through a pinching mechanism to effectively reduce large-scale propagation loss. This capability facilitates both efficient downlink energy transfer and uplink task offloading. To fully exploit these advantages, we adopt a non-orthogonal multiple access (NOMA) framework and formulate a joint optimization problem to maximize the system's computational capacity by jointly optimizing device transmit power, time allocation, PA positions in both uplink and downlink, and radiation control. To address the resulting non-convexity caused by variable coupling, we develop an alternating optimization algorithm that integrates particle swarm optimization (PSO) with successive convex approximation. Simulation results demonstrate that the proposed PA-assisted design substantially improves both energy harvesting efficiency and computational performance compared to conventional antenna systems.

eess.SP↗

arXiv2025

Unsupervised Skill Discovery through Skill Regions Differentiation

Unsupervised Reinforcement Learning (RL) aims to discover diverse behaviors that can accelerate the learning of downstream tasks. Previous methods typically focus on entropy-based exploration or empowerment-driven skill learning. However, entropy-based exploration struggles in large-scale state spaces (e.g., images), and empowerment-based methods with Mutual Information (MI) estimations have limitations in state exploration. To address these challenges, we propose a novel skill discovery objective that maximizes the deviation of the state density of one skill from the explored regions of other skills, encouraging inter-skill state diversity similar to the initial MI objective. For state-density estimation, we construct a novel conditional autoencoder with soft modularization for different skill policies in high-dimensional space. Meanwhile, to incentivize intra-skill exploration, we formulate an intrinsic reward based on the learned autoencoder that resembles count-based exploration in a compact latent space. Through extensive experiments in challenging state and image-based tasks, we find our method learns meaningful skills and achieves superior performance in various downstream tasks.

cs.LG↗

arXiv2025

Step-Audio-AQAA: a Fully End-to-End Expressive Large Audio Language Model

Large Audio-Language Models (LALMs) have significantly advanced intelligent human-computer interaction, yet their reliance on text-based outputs limits their ability to generate natural speech responses directly, hindering seamless audio interactions. To address this, we introduce Step-Audio-AQAA, a fully end-to-end LALM designed for Audio Query-Audio Answer (AQAA) tasks. The model integrates a dual-codebook audio tokenizer for linguistic and semantic feature extraction, a 130-billion-parameter backbone LLM and a neural vocoder for high-fidelity speech synthesis. Our post-training approach employs interleaved token-output of text and audio to enhance semantic coherence and combines Direct Preference Optimization (DPO) with model merge to improve performance. Evaluations on the StepEval-Audio-360 benchmark demonstrate that Step-Audio-AQAA excels especially in speech control, outperforming the state-of-art LALMs in key areas. This work contributes a promising solution for end-to-end LALMs and highlights the critical role of token-based vocoder in enhancing overall performance for AQAA tasks.

cs.SD↗

arXiv2025

To Protect the LLM Agent Against the Prompt Injection Attack with Polymorphic Prompt

LLM agents are widely used as agents for customer support, content generation, and code assistance. However, they are vulnerable to prompt injection attacks, where adversarial inputs manipulate the model's behavior. Traditional defenses like input sanitization, guard models, and guardrails are either cumbersome or ineffective. In this paper, we propose a novel, lightweight defense mechanism called Polymorphic Prompt Assembling (PPA), which protects against prompt injection with near-zero overhead. The approach is based on the insight that prompt injection requires guessing and breaking the structure of the system prompt. By dynamically varying the structure of system prompts, PPA prevents attackers from predicting the prompt structure, thereby enhancing security without compromising performance. We conducted experiments to evaluate the effectiveness of PPA against existing attacks and compared it with other defense methods.

cs.CR↗