Searcharxiv⌕ Search

arXiv subjects

Peng Zhang

Publications and source records attributed to Peng Zhang.

At least 109 records · Page 6Linked to original sources
arXiv2026

GLM-5V-Turbo: Toward a Native Foundation Model for Multimodal Agents

We present GLM-5V-Turbo, a step toward native foundation models for multimodal agents. As foundation models are increasingly deployed in real environments, agentic capability depends not only on language reasoning, but also on the ability to perceive, interpret, and act over heterogeneous contexts such as images, videos, webpages, documents, GUIs. GLM-5V-Turbo is built around this objective: multimodal perception is integrated as a core component of reasoning, planning, tool use, and execution, rather than as an auxiliary interface to a language model. This report summarizes the main improvements behind GLM-5V-Turbo across model design, multimodal training, reinforcement learning, toolchain expansion, and integration with agent frameworks. These developments lead to strong performance in multimodal coding, visual tool use, and framework-based agentic tasks, while preserving competitive text-only coding capability. More importantly, our development process offers practical insights for building multimodal agents, highlighting the central role of multimodal perception, hierarchical optimization, and reliable end-to-end verification.

cs.CV↗
arXiv2026

Artificial-Noise-Aided Secure Near-Field MIMO With Fluid Antenna Systems

With the evolution of mobile communication systems toward large-scale arrays, high-frequency operation, and reconfigurable antenna architectures, fluid antenna systems (FAS) operating in the near-field (NF) regime provide new degrees of freedom (DoF) for secure and privacy-sensitive mobile access. This paper proposes an artificial-noise (AN)-aided physical layer security (PLS) scheme for NF fluid-antenna multiple-input multiple-output (FA-MIMO) systems, aiming to protect high-rate mobile service links supported by compact or large arrays. An alternating-optimization (AO) framework addresses the sparsity-constrained non-convex design by splitting it into a continuous BF/AN joint-design subproblem and a discrete FAS port-selection subproblem. Closed-form fully digital beamforming (BF)/AN solutions are obtained via a generalized spectral water-filling procedure within a block coordinate descent (BCD) surrogate and realized by a hardware-consistent hybrid beamforming (HBF) architecture with a shared RF network and independent digital BF/AN branches, while preserving the target BF/AN power split under constant-modulus RF constraints. For FAS port selection, a row-energy based prune--refit rule, aligned with Karush--Kuhn--Tucker (KKT) conditions of a group-sparsity surrogate, enables efficient active-port determination under a finite RF-chain budget. Simulation results confirm that the proposed design exploits the geometry and position-domain DoF of FAS and significantly improves secrecy performance, particularly for non-extremely-large arrays where NF beam focusing alone is inadequate. These results demonstrate the potential of AN-aided NF FA-MIMO as a practical secure-transmission architecture for future location-aware and hardware-constrained mobile computing systems.

cs.IT↗
arXiv2026

Near-field Boundary Distance in mmWave and THz Communications with Misaligned Antenna Arrays

Wireless communications in the millimeter wave (mmWave) and terahertz (THz) spectrum allow harnessing large frequency bands, thus achieving ultra-high data rates. However, the inherently short wavelengths of mmWave and THz signals lead to an extended radiative near-field region, where certain canonical far-field assumptions fail. Most prior works aimed to characterize this radiative near-field region either do not consider antenna arrays on both communicating nodes or, if they do, assume perfect alignment between the arrays. However, such assumptions break down in many realistic deployments, where both sides must employ large-scale mmWave/THz antenna arrays to maintain the desired communication range, while perfect antenna alignment cannot be guaranteed particularly under nodes mobility. In this work, a generalized mathematical framework is presented to characterize the radiative near-field distance in directional mmWave and THz communication systems under various realistic array rotations and misalignments. With the use of the developed framework, compact closed-form expressions are derived for the near-field boundary distance in a wide range of antenna configurations, including array-to-array and array-to-point setups, considering both linear and planar arrays. Our numerical study reveals that the presence of antenna misalignment may significantly adjust the boundaries of the near-field region in mmWave and THz communication systems.

eess.SP↗
arXiv2026

Robust Crop Planning under Uncertainty: Aligning Economic Optimality with Agronomic Sustainability

Long-horizon agricultural planning requires optimizing crop allocation under complex spatial heterogeneity, temporal agronomic dependencies, and multi-source environmental uncertainty. Existing approaches often either address crop interactions, such as legume-cereal complementarity, only implicitly or rely on static deterministic formulations that fail to ensure resilience against market and climate volatility.To address these challenges, we propose a Multi-Layer Robust Crop Planning Framework (MLRCPF) that integrates spatial reasoning, temporal dynamics, and robust optimization. Specifically, we formalize crop-to-crop relationships through a structured interaction matrix embedded within the state-transition logic, and employ a distributionally robust optimization layer to mitigate worst-case risks defined by a data-driven ambiguity set. Evaluations on a real-world high-mix farming dataset from North China demonstrate the effectiveness of the proposed approach. The framework autonomously generates sustainable checkerboard rotation patterns that restore soil fertility, significantly increasing the legume planting ratio compared to deterministic baselines. Economically, it successfully resolves the trade-off between optimality and stability. These results highlight the importance of explicitly encoding domain-specific structural priors into optimization models for resilient decision-making in complex agricultural systems.

cs.CE↗
arXiv2026

Optimizing High-Throughput Distributed Data Pipelines for Reproducible Deep Learning at Scale

Training massive-scale deep learning models on datasets spanning tens of terabytes presents critical challenges in hardware utilization and training reproducibility. In this paper, we identify and resolve profound data-loading bottlenecks within distributed GPU training pipelines using the Petastorm data loader and Apache Parquet datasets. Through systematic profiling, we demonstrate that network I/O and CPU-bound data transformations (e.g., PyArrow to NumPy) constrain GPU utilization to as low as 10-15%. To address this, we propose an optimized architecture that features push-down worker-level transformations coupled with local-disk caching via Fanout-Cache, minimizing redundant I/O and CPU overhead across training epochs. Furthermore, we eliminate race conditions in multi-worker shared queues by implementing dedicated round-robin ventilator and result queues, alongside modernized RNG handling, achieving strict deterministic data loading. Our optimizations yield a 6x speedup, reducing end-to-end training time from 22 hours to 3 hours, increasing GPU utilization to over 60%, and drastically reducing run-to-run variance, enabling robust, high-throughput, and reproducible large-scale model training.

cs.DC↗
arXiv2026

PromptEcho: Annotation-Free Reward from Vision-Language Models for Text-to-Image Reinforcement Learning

Reinforcement learning (RL) can improve the prompt following capability of text-to-image (T2I) models, yet obtaining high-quality reward signals remains challenging: CLIP Score is too coarse-grained, while VLM-based reward models (e.g., RewardDance) require costly human-annotated preference data and additional fine-tuning. We propose PromptEcho, a reward construction method that requires \emph{no} annotation and \emph{no} reward model training. Given a generated image and a guiding query, PromptEcho computes the token-level cross-entropy loss of a frozen VLM with the original prompt as the label, directly extracting the image-text alignment knowledge encoded during VLM pretraining. The reward is deterministic, computationally efficient, and improves automatically as stronger open-source VLMs become available. For evaluation, we develop DenseAlignBench, a benchmark of concept-rich dense captions for rigorously testing prompt following capability. Experimental results on two state-of-the-art T2I models (Z-Image and QwenImage-2512) demonstrate that PromptEcho achieves substantial improvements on DenseAlignBench (+26.8pp / +16.2pp net win rate), along with consistent gains on GenEval, DPG-Bench, and TIIFBench without any task-specific training. Ablation studies confirm that PromptEcho comprehensively outperforms inference-based scoring with the same VLM, and that reward quality scales with VLM size. We will open-source the trained models and the DenseAlignBench.

cs.CV↗
arXiv2026

From Hidden Profiles to Governable Personalization: Recommender Systems in the Age of LLM Agents

Personalization has traditionally depended on platform-specific user models that are optimized for prediction but remain largely inaccessible to the people they describe. As LLM-based assistants increasingly mediate search, shopping, travel, and content access, this arrangement may be giving way to a new personalization stack in which user representation is no longer confined to isolated platforms. In this paper, we argue that the key issue is not simply that large language models can enhance recommendation quality, but that they reconfigure where and how user representations are produced, exposed, and acted upon. We propose a shift from hidden platform profiling toward governable personalization, where user representations may become more inspectable, revisable, portable, and consequential across services. Building on this view, we identify five research fronts for recommender systems: transparent yet privacy-preserving user modeling, intent translation and alignment, cross-domain representation and memory design, trustworthy commercialization in assistant-mediated environments, and operational mechanisms for ownership, access, and accountability. We position these not as isolated technical challenges, but as interconnected design problems created by the emergence of LLM agents as intermediaries between users and digital platforms. We argue that the future of recommender systems will depend not only on better inference, but on building personalization systems that users can meaningfully understand, shape, and govern.

cs.IR↗
arXiv2026

PortraitDirector: A Hierarchical Disentanglement Framework for Controllable and Real-time Facial Reenactment

Existing facial reenactment methods struggle with a trade-off between expressiveness and fine-grained controllability. Holistic facial reenactment models often sacrifice granular control for expressiveness, while methods designed for control may struggle with fidelity and robust disentanglement. Instead of treating facial motion as a monolithic signal, we explore an alternative compositional perspective. In this paper, we introduce PortraitDirector, a novel framework that formulates face reenactment as a hierarchical composition task, achieving high-fidelity and controllable results. We employ a Hierarchical Motion Disentanglement and Composition strategy, deconstructing facial motion into a Spatial Layer for physical movements and a Semantic Layer for emotional content. The Spatial Layer comprises: (i) global head pose, managed via a dedicated representation and injection pathway; (ii) spatially separated local facial expressions, distilled from cropped facial regions and purged of emotional cues via Emotion-Filtering Module leveraging an information bottleneck. The Semantic Layer contains a derived global emotion. The disentangled components are then recomposed into an expressive motion latent. Furthermore, we engineer the framework for real-time performance through a suite of optimizations, including diffusion distillation, causal attention and VAE acceleration. PortraitDirector achieves streaming, high-fidelity, controllable 512 x 512 face reenactment at 20 FPS with a end-to-end 800 ms latency on a single 5090 GPU.

cs.CV↗
arXiv2026

User Mobility Demands Near-Field Communications in Terahertz Band Wireless Networks Beyond 6G

Near-field propagation is often unavoidable at terahertz (THz) frequencies due to the large apertures needed for sufficient array gain, yet near-field operation complicates practical system design, especially under user mobility. This paper asks whether a mobile THz link can remain broadband, achieve the desired high rates and coverage, while operating exclusively in the radiative far field. To answer this question, we develop a proof-by-contradiction feasibility framework that jointly enforces (i) a far-field requirement based on the Fraunhofer distance and (ii) a reliability requirement specified by a target SNR at the worst-case link distance. We derive closed-form upper bounds on the far-field-feasible bandwidth for stationary and mobile links. We further incorporate practical misalignment through several UE rotation and mobility scenarios. Numerical results show that stationary THz links can remain far-field-only with physically realizable apertures while supporting extremely large bandwidths, whereas practical mobile THz systems cannot. In practically relevant mobile THz access settings, the far-field-feasible bandwidth becomes a severe limiting factor: achieving tens-of-GHz targets would require unrealistically high UE transmit power. A cross-band comparison further shows that far-field-only operation is largely attainable at sub-6~GHz and, to a significant extent, at mmWave for moderate bandwidths, while near-field-aware designs become essential for mobile THz access.

eess.SP↗
arXiv2026

SkillX: Automatically Constructing Skill Knowledge Bases for Agents

Learning from experience is critical for building capable large language model (LLM) agents, yet prevailing self-evolving paradigms remain inefficient: agents learn in isolation, repeatedly rediscover similar behaviors from limited experience, resulting in redundant exploration and poor generalization. To address this problem, we propose SkillX, a fully automated framework for constructing a \textbf{plug-and-play skill knowledge base} that can be reused across agents and environments. SkillX operates through a fully automated pipeline built on three synergistic innovations: \textit{(i) Multi-Level Skills Design}, which distills raw trajectories into three-tiered hierarchy of strategic plans, functional skills, and atomic skills; \textit{(ii) Iterative Skills Refinement}, which automatically revises skills based on execution feedback to continuously improve library quality; and \textit{(iii) Exploratory Skills Expansion}, which proactively generates and validates novel skills to expand coverage beyond seed training data. Using a strong backbone agent (GLM-4.6), we automatically build a reusable skill library and evaluate its transferability on challenging long-horizon, user-interactive benchmarks, including AppWorld, BFCL-v3, and $τ^2$-Bench. Experiments show that SkillKB consistently improves task success and execution efficiency when plugged into weaker base agents, highlighting the importance of structured, hierarchical experience representations for generalizable agent learning. Our code will be publicly available soon at https://github.com/zjunlp/SkillX.

cs.CL↗
arXiv2026

Transparent and Controllable Recommendation Filtering via Multimodal Multi-Agent Collaboration

While personalized recommender systems excel at content discovery, they frequently expose users to undesirable or discomforting information, highlighting the critical need for user-centric filtering tools. Current methods leveraging Large Language Models (LLMs) struggle with two major bottlenecks: they lack multimodal awareness to identify visually inappropriate content, and they are highly prone to "over-association" -- incorrectly generalizing a user's specific dislike (e.g., anxiety-inducing marketing) to block benign, educational materials. These unconstrained hallucinations lead to a high volume of false positives, ultimately undermining user agency. To overcome these challenges, we introduce a novel framework that integrates end-to-cloud collaboration, multimodal perception, and multi-agent orchestration. Our system employs a fact-grounded adjudication pipeline to eliminate inferential hallucinations. Furthermore, it constructs a dynamic, two-tier preference graph that allows for explicit, human-in-the-loop modifications (via Delta-adjustments), explicitly preventing the algorithm from catastrophically forgetting fine-grained user intents. Evaluated on an adversarial dataset comprising 473 highly confusing samples, the proposed architecture effectively curbed over-association, decreasing the false positive rate by 74.3% and achieving nearly twice the F1-Score of traditional text-only baselines. Additionally, a 7-day longitudinal field study with 19 participants demonstrated robust intent alignment and enhanced governance efficiency. User feedback confirmed that the framework drastically improves algorithmic transparency, rebuilds user control, and alleviates the fear of missing out (FOMO), paving the way for transparent human-AI co-governance in personalized feeds.

cs.IR↗
arXiv2026

SGA-MCTS: Decoupling Planning from Execution via Training-Free Atomic Experience Retrieval

LLM-powered systems require complex multi-step decision-making abilities to solve real-world tasks, yet current planning approaches face a trade-off between the high latency of inference-time search and the limited generalization of supervised fine-tuning. To address this limitation, we introduce \textbf{SGA-MCTS}, a framework that casts LLM planning as non-parametric retrieval. Offline, we leverage Monte Carlo Tree Search (MCTS) to explore the solution space and distill high-fidelity trajectories into State-Goal-Action (SGA) atoms. These atoms are de-lexicalized primitives that abstract concrete entities into symbolic slots, preserving reusable causal logic while discarding domain-specific noise. Online, a retrieval-augmented agent employs a hybrid symbolic-semantic mechanism to fetch relevant SGAs and re-ground them into the current context as soft reasoning hints. Empirical results on complex benchmarks demonstrate that this paradigm enables frozen, open-weights models to match the performance of SOTA systems (e.g., GPT-5) without task-specific fine-tuning. By effectively amortizing the heavy computational cost of search, SGA-MCTS achieves System 2 reasoning depth at System 1 inference speeds, rendering autonomous planning both scalable and real-time feasible.

cs.AI↗
arXiv2026

Data-driven Learning of Probabilistic Model of Binary Droplet Collision for Spray Simulation

Binary droplet collisions are ubiquitous in dense sprays. Traditional deterministic models cannot adequately represent transitional and stochastic behaviors of binary droplet collision. To bridge this gap, we developed a probabilistic model by using a machine learning approach, the Light Gradient-Boosting Machine (LightGBM). The model was trained on a comprehensive dataset of 33,540 experimental cases covering eight collision regimes across broad ranges of Weber number, Ohnesorge number, impact parameter, size ratio, and ambient pressure. The resulting machine learning classifier captures highly nonlinear regime boundaries with 99.2% accuracy and retains sensitivity in transitional regions. To facilitate its implementation in spray simulation, the model was translated into a probabilistic form, a multinomial logistic regression, which preserves 93.2% accuracy and maps continuous inter-regime transitions. A biased-dice sampling mechanism then converts these probabilities into definite yet stochastic outcomes. This work presents the first probabilistic, high-dimensional droplet collision model derived from experimental data, offering a physically consistent, comprehensive, and user-friendly solution for spray simulation.

physics.flu-dyn↗
arXiv2026

Aerial IRS Deployment-Aided Secure Computation Offloading Against DISCO Jamming Attacks

With the rapid growth of Multi-access Edge Computing (MEC), secure and efficient computation offloading from user equipment (UEs) to edge access points (APs) is critical. However, DISCO intelligent reflective surface-based fully-passive jammers (DIRS-based FPJs) use random time-varying phase shifts to launch DISCO jamming attacks, disrupting offloading performance. This paper leverages an aerial intelligent reflective surface (AIRS) to enable secure computation offloading against DISCO jamming by jointly optimizing offloading ratios, AIRS phase shifts, and deployment. A two-timescale (2Ts) framework is proposed to address the optimization challenge caused by the distinct update frequencies of different strategies. Specifically, AIRS deployment is adjusted on a long timescale to boost antijamming capability due to the impracticality of frequent physical adjustment, while offloading ratios and phase shifts are optimized on a short timescale to adapt to DIRS-jammed dynamic channel conditions. We propose a dual-agent deep reinforcement learning (DRL)-based AIRS deployment-aided secure computation offloading (DDADSO) scheme to maximize the secure offloading utility under DISCO jamming. Simulation results verify that the proposed DDADSO scheme outperforms benchmark schemes, demonstrating the effectiveness of AIRS deployment in improving offloading performance against DISCO jamming attacks.

eess.SP↗
arXiv2026

Joint Observation of SGR J1935+2154 with \textit{Insight}-HXMT and KM40m during the active episode of October 2022

SGR J1935+2154 is the unique magnetar so far from which fast radio bursts have been detected. In October 2022, it resumed its burst activity, and we implemented a dedicated target-of-opportunity (ToO) observation on it from Oct. 13th to Nov. 1st, 2022 (about 940 ks in total) with \textit{Insight}-HXMT, while the KM40m radio telescope observed this source for about 1400 hours since Oct. 15th. We searched the LE, ME, and HE data of \textit{Insight}-HXMT in the overlapping observation time windows with the KM40m radio telescope and revealed 60 magnetar X-ray bursts (MXBs), while KM40m only detected 1 radio burst. In particular, we find that there is an X-ray burst on October 21 (denoted as MXB 221021) temporally associated with this radio burst. Interestingly, this association event shows very different morphology from those X-ray and radio association events from this source reported before (e.g., MXB/FRB 200428). Moreover, we systematically analyzed the temporal and spectral properties of the sample of MXBs during this observation and found that % the (radio-associated) MXB 221021 shows some different properties from other MXBs without associated radio bursts. These findings shed new light on the physical mechanisms of X-ray bursts and radio burst emission in magnetars.

astro-ph.HE↗
arXiv2026

Precise $^{136}$Xe Double Beta Decay Measurement in PandaX-4T with Implications on the Nuclear Matrix Elements and Majorons

The continuous spectrum of double beta decay ($ββ$) provides a sensitive probe to test the predictions of the standard model and to search for signatures of new physics beyond it. We present a comprehensive analysis of the $^{136}$Xe $ββ$ spectrum utilizing $39.1 \pm 0.7~\textrm{kg}\cdot\textrm{yr}$ of $^{136}$Xe exposure from the PandaX-4T experiment. The analysis yields the most precise measurement to date of the $^{136}$Xe two-neutrino double beta decay ($2νββ$) half-life, $(2.14 \pm 0.05) \times 10^{21}$ years, the uncertainty of which is reduced by a factor of 2 compared to our previous result. We measure the parameter $ξ_{31}^{2ν}$, defined as the ratio between the subleading and leading components of the $^{136}$Xe $2νββ$ nuclear matrix element, to be $0.59^{+0.41}_{-0.38}$, which is consistent with theoretical predictions. We also search for Majoron-emitting modes of $^{136}$Xe $ββ$, establishing the most stringent limit for the spectral index $n=7$.

nucl-ex↗
arXiv2026

Beauty in the Eye of AI: Aligning LLMs and Vision Models with Human Aesthetics in Network Visualization

Network visualization has traditionally relied on heuristic metrics, such as stress, under the assumption that optimizing them leads to aesthetic and informative layouts. However, no single metric consistently produces the most effective results. A data-driven alternative is to learn from human preferences, where annotators select their favored visualization among multiple layouts of the same graphs. These human-preference labels can then be used to train a generative model that approximates human aesthetic preferences. However, obtaining human labels at scale is costly and time-consuming. As a result, this generative approach has so far been tested only with machine-labeled data. In this paper, we explore the use of large language models (LLMs) and vision models (VMs) as proxies for human judgment. Through a carefully designed user study involving 27 participants, we curated a large set of human preference labels. We used this data both to better understand human preferences and to bootstrap LLM/VM labelers. We show that prompt engineering that combines few-shot examples and diverse input formats, such as image embeddings, significantly improves LLM-human alignment, and additional filtering by the confidence score of the LLM pushes the alignment to human-human levels. Furthermore, we demonstrate that carefully trained VMs can achieve VM-human alignment at a level comparable to that between human annotators. Our results suggest that AI can feasibly serve as a scalable proxy for human labelers.

cs.LG↗
arXiv2026

GECAM discovery of a peculiar magnetar X-ray burst (MXB 221120) from SGR J1935+2154 associated with a fast radio burst

Fast radio bursts (FRBs) are enigmatic cosmic transients of millisecond duration observed in the radio band. The identification of FRB-associated magnetar X-ray bursts (MXBs) from galactic magnetar SGR J1935+2154 suggests that at least a fraction of FRBs can be produced from magnetar activity. However, the sample size of FRB-associated MXBs is still very small. Here we report a bright and peculiar FRB-associated MXB from SGR J1935+2154 detected by GECAM on November 20, 2022, dubbed MXB 221120. We find that both temporal and spectral properties of MXB 221120 exhibit distinctive features. Its light curve could be generally described by a single FRED function with superposition of several narrow pulses. Interestingly, we identify a possible QPO feature with center frequency of ~18 Hz in this MXB. The time-integrated spectrum is best fitted by a blackbody model with temperature (kT ) of 18.6 keV, rendering it the first thermal spectrum FRB-associated MXB from SGR J1935+2154. Compared to other MXBs with single emission episode, MXB 221120 has longer duration and higher blackbody temperature, making it an outlier in the burst sample. These results indicate that MXB 221120 may be produced by a special mechanism with extreme physical conditions.

astro-ph.HE↗