arXiv subjects

Jing Zhu

Publications and source records attributed to Jing Zhu.

At least 19 recordsLinked to original sources

arXiv2026

GigaBrain-0.7: Scaling Embodied Foundation Models to Emergent Capabilities with a Three-System Architecture

Vision-language-action (VLA) models have become a dominant paradigm for generalist embodied agents, demonstrating strong complex and long-horizon task completion in structured settings. Yet it remains an open question whether current VLA systems can benefit from more effective architectural design, scale to substantially larger and more heterogeneous data regimes, and achieve broader generalization across tasks and embodiments. To this end, we present GigaBrain-0.7, an embodied foundation model with substantially improved generalization across diverse robot embodiments. Specifically, GigaBrain-0.7 unifies understanding, prediction, and action through a three-system architecture, scales pretraining to over 37,000 hours of heterogeneous embodied data, and introduces one-stage alignment training that jointly optimizes vision-language understanding and multi-embodiment action generation. Compared with the preceding GigaBrain-0 series and prior state-of-the-art models including $\pi_{0.5}$, GigaBrain-0.7 achieves substantial improvements in foundation zero-shot capabilities, language-conditioned instruction following, and post-training task success rates. In particular, on our in-house Maker H01 platform and mainstream robot embodiments, GigaBrain-0.7 demonstrates strong task adaptability and completion ability across both home and industrial scenarios. All training code and pretrained model weights will be released.

cs.RO↗

arXiv2026

M-Net: Integrating Spectral Features and Physical Field Operators into Deep Learning for Medical Image Segmentation

Purpose: Deep learning-based medical image segmentation has achieved remarkable success, yet purely data-driven approaches often fail to exploit the rich mathematical structure inherent in medical images. We investigate whether explicit mathematical inductive biases, specifically matrix spectral analysis and vector calculus operators, can enhance segmentation beyond data-driven learning alone. Methods: We propose M-Net (Math-Augmented Network), which integrates three complementary mathematical priors into U-Net: (1) continuous spectral features derived from the condition number of centered local pixel matrices, providing a differentiable measure of texture ill-conditioning; (2) physical field operators (divergence and a discrete curl-like boundary irregularity operator) computed from image gradient fields, capturing focal intensity extrema and edge non-smoothness; and (3) a Math-Attention Gate (MAG) that adaptively fuses mathematical features with CNN-extracted deep features at skip connections. Results: Experiments on three benchmarks (LiTS, KiTS, and BraTS) show that M-Net achieves Dice scores of 78.42%, 76.15%, and 83.67%, outperforming baseline U-Net by 12.37%, 3.52%, and 5.55% on liver, kidney, and brain tumor segmentation, respectively. Ablations reveal that the condition-number feature contributes a 2.14% gain over binary invertibility features, while MAG adds 1.45% over simple concatenation. Conclusion: M-Net establishes that mathematical inductive biases provide effective complementary information for medical image segmentation. The continuous condition-number feature offers superior gradient information over discrete alternatives, and MAG preserves these priors throughout the network. This work opens avenues for integrating linear algebra and vector calculus into deep architectures for medical imaging.

cs.CV↗

arXiv2026

YouZhi: Towards High-Concurrency Financial LLMs via Adaptive GQA-to-MLA Transition

Large language models (LLMs) drive significant financial innovations, yet their high-concurrency deployment is severely bottlenecked by KV cache memory overhead, which inflates infrastructure costs and throttles scalability. To address this, we propose YouZhi-LLM, a highly efficient financial LLM empowered by a comprehensive structural transition and training pipeline natively built on the Huawei Ascend ecosystem. At its algorithmic core, YouZhi-LLM features a layer-adaptive GQA-to-MLA transition framework that dynamically assigns per-layer FreqFold sizes, maximizing KV-cache compression while minimizing perplexity degradation. To recover representation capacity and inject domain expertise, the Ascend-based training pipeline seamlessly integrates generalized knowledge distillation with financial-specific supervised fine-tuning. Evaluations demonstrate the superiority of this systematic approach, with the adaptive transition reducing perplexity degradation by up to 35% over uniform baselines. Crucially, when evaluated on Ascend NPUs via vLLM-Ascend, the massive KV-cache reduction translates directly into deployment efficiency. Compared to their respective base models, YouZhi-7B yields a 12.3% improvement in average financial benchmark score alongside a 2.69$\times$ increase in maximum concurrency; similarly, YouZhi-14B achieves a 7.0% accuracy gain and a 2.43$\times$ concurrency boost, establishing a new paradigm for cost-effective, high-throughput financial inference.

cs.CL↗

arXiv2026

Hybrid Bit and Semantic Communications for UAV-Enabled Wireless Power Transfer Networks: A Decision-Assisted Deep Reinforcement Learning Approach

Semantic communications which can significantly reduce spectrum consumption in wireless networks, have recently become a popular research area. When combined with wireless power transfer (WPT), semantic communications can help achieve high spectral efficiency for energy-limited devices in wireless communications. In energy-constrained and link budget-limited scenarios such as UAV networks, the integration of semantic communications and WPT enables highly energyefficient transmission mechanisms. In this paper, we investigate semantic communications in UAV-enabled WPT networks. To achieve adaptability to varying signal-to-noise ratio (SNR) and task requirements, we introduce a multi-layer hybrid bit and semantic communication framework. We adopt a semantic communication efficiency metric and aim to maximize it by jointly optimizing UAV trajectory, energy harvesting base station (EHBS) selection, user association, semantic mode selection, and energy harvesting time allocation. To address this complex longterm optimization problem, we introduce the distributional soft actor-critic (DSAC) algorithm and introduce a decision assistant to further enhance the convergence performance of DSAC. Simulation results validate the effectiveness of the proposed method and framework and demonstrate that our algorithm can achieve superior long-term optimization performance in dynamic network environments.

cs.IT↗

arXiv2026

SOLARIS: Speculative Offloading of Latent-bAsed Representation for Inference Scaling

Recent advances in recommendation scaling laws have led to foundation models of unprecedented complexity. While these models offer superior performance, their computational demands make real-time serving impractical, often forcing practitioners to rely on knowledge distillation-compromising serving quality for efficiency. To address this challenge, we present SOLARIS (Speculative Offloading of Latent-bAsed Representation for Inference Scaling), a novel framework inspired by speculative decoding. SOLARIS proactively precomputes user-item interaction embeddings by predicting which user-item pairs are likely to appear in future requests, and asynchronously generating their foundation model representations ahead of time. This approach decouples the costly foundation model inference from the latency-critical serving path, enabling real-time knowledge transfer from models previously considered too expensive for online use. Deployed across Meta's advertising system serving billions of daily requests, SOLARIS achieves 0.67% revenue-driving top-line metrics gain, demonstrating its effectiveness at scale.

cs.LG↗

arXiv2026

Joint Optimization of Flexible Antenna Array Shape and Beamforming for Secure Communication

Flexible antenna arrays (FAAs) can physically reshape their geometry to add new spatial degrees of freedom, whereas transmit beamforming adjusts the complex element weights to electronically steer and shape the array's radiation pattern, thereby significantly improving communication performance. This paper is the first to explore the integration of FAA geometry control and beamforming for physical layer security enhancement, where a base station equipped with an FAA communicates with a legitimate user in the presence of passive eavesdroppers. To safeguard confidential transmissions, we formulate a new secrecy rate maximization problem that jointly optimizes the transmit beamforming vector and a continuous FAA shape control parameter. Due to the non convex nature of the problem, an alternating optimization algorithm is developed to decompose the joint design into tractable subproblems, which are solved iteratively to refine both the FAA geometry and beamforming strategy. Simulation results confirm that the proposed joint optimization framework significantly outperforms conventional fixed shape or beamforming only schemes, demonstrating the potential of FAA enabled reconfigurability for secure wireless communications.

eess.SP↗

arXiv2026

Joint Training on AMD and NVIDIA GPUs

As large language models continue to scale, training demands on compute and system capacity grow rapidly, making single-vendor homogeneous clusters insufficient. This paper presents a technical solution for heterogeneous mixed training in AMD-NVIDIA environments. We first adopt a compatibility-oriented approach based on CPU-Forwarding Communication, with differentiated communication back-end selection across parallel groups and multi-NIC parallel data transfer. To achieve higher performance, we further propose another Device-Direct Communication approach, integrating a CPU-offloading P2P mechanism to enable direct cross-vendor GPU data transfer without host-memory staging. Experiments on LLaMA-8B and Qwen2-7B demonstrate that the proposed Device-Direct Communication approach achieves up to 98% of the throughput of an NVIDIA homogeneous system, while preserving training stability and correctness.

cs.DC↗

arXiv2026

FMMD: A multimodal open peer review dataset based on F1000Research

Automated scholarly paper review (ASPR) has entered the coexistence phase with traditional peer review, where artificial intelligence (AI) systems are increasingly incorporated into real-world manuscript evaluation. In parallel, research on automated and AI-assisted peer review has proliferated. Despite this momentum, empirical progress remains constrained by several critical limitations in existing datasets. While reviewers routinely evaluate figures, tables, and complex layouts to assess scientific claims, most existing datasets remain overwhelmingly text-centric. This bias is reinforced by a narrow focus on data from computer science venues. Furthermore, these datasets lack precise alignment between reviewer comments and specific manuscript versions, obscuring the iterative relationship between peer review and manuscript evolution. In response, we introduce FMMD, a multimodal and multidisciplinary open peer review dataset curated from F1000Research. The dataset bridges the current gap by integrating manuscript-level visual and structural data with version-specific reviewer reports and editorial decisions. By providing explicit alignment between reviewer comments and the exact article iteration under review, FMMD enables fine-grained analysis of the peer review lifecycle across diverse scientific domains. FMMD supports tasks such as multimodal issue detection and multimodal review comment generation. It provides a comprehensive empirical resource for the development of peer review research.

cs.DL↗

arXiv2025

Flexible Reconfigurable Intelligent Surface-Aided Covert Communications in UAV Networks

In recent years, unmanned aerial vehicles (UAVs) have become a key role in wireless communication networks due to their flexibility and dynamic adaptability. However, the openness of UAV-based communications leads to security and privacy concerns in wireless transmissions. This paper investigates a framework of UAV covert communications which introduces flexible reconfigurable intelligent surfaces (F-RIS) in UAV networks. Unlike traditional RIS, F-RIS provides advanced deployment flexibility by conforming to curved surfaces and dynamically reconfiguring its electromagnetic properties to enhance the covert communication performance. We establish an electromagnetic model for F-RIS and further develop a fitted model that describes the relationship between F-RIS reflection amplitude, reflection phase, and incident angle. To maximize the covert transmission rate among UAVs while meeting the covert constraint and public transmission constraint, we introduce a strategy of jointly optimizing UAV trajectories, F-RIS reflection vectors, F-RIS incident angles, and non-orthogonal multiple access (NOMA) power allocation. Considering this is a complicated non-convex optimization problem, we propose a deep reinforcement learning (DRL) algorithm-based optimization solution. Simulation results demonstrate that our proposed framework and optimization method significantly outperform traditional benchmarks, and highlight the advantages of F-RIS in enhancing covert communication performance within UAV networks.

eess.SP↗

arXiv2025

LLM Optimization Unlocks Real-Time Pairwise Reranking

Efficiently reranking documents retrieved from information retrieval (IR) pipelines to enhance overall quality of Retrieval-Augmented Generation (RAG) system remains an important yet challenging problem. Recent studies have highlighted the importance of Large Language Models (LLMs) in reranking tasks. In particular, Pairwise Reranking Prompting (PRP) has emerged as a promising plug-and-play approach due to its usability and effectiveness. However, the inherent complexity of the algorithm, coupled with the high computational demands and latency incurred due to LLMs, raises concerns about its feasibility in real-time applications. To address these challenges, this paper presents a focused study on pairwise reranking, demonstrating that carefully applied optimization methods can significantly mitigate these issues. By implementing these methods, we achieve a remarkable latency reduction of up to 166 times, from 61.36 seconds to 0.37 seconds per query, with an insignificant drop in performance measured by Recall@k. Our study highlights the importance of design choices that were previously overlooked, such as using smaller models, limiting the reranked set, using lower precision, reducing positional bias with one-directional order inference, and restricting output tokens. These optimizations make LLM-based reranking substantially more efficient and feasible for latency-sensitive, real-world deployments.

cs.CL↗

arXiv2025

Uplink SCMA-empowered Uncoordinated Random Access for Future mMTC

In this paper, a novel uncoordinated random access (URA) protocol is presented to address the pressing demand for massive connectivity with low access latency in future massive machine type communication (mMTC) scenarios. The proposed URA scheme integrates the classical slotted ALOHA (S-ALOHA) protocol with sparse code multiple access (SCMA) technique, referred to as SCMA-empowered URA. Specifically, active users randomly choose an SCMA codebook to access the communication network in an arbitrary time slot whenever they want without scheduling. However, due to the lack of central coordination in the proposed URA scheme, SCMA codebook collisions become inevitable, making decoding challenging and leading to increased access failures. To cope with the decoding issue, an interference-canceling (IC) first decoding strategy is proposed at the access point (AP), which can partially tackles collision problems, contributing to a higher system throughput. Taking the proposed IC-first decoding strategy into account, a closed-form theoretical expression of the throughput is derived. Moreover, to alleviate the throughput degradation under the congested user traffic, a user barring mechanism is introduced to manage the traffic load. Firstly, a closed-form expression of idle codebook probability is developed to help indicate the system state, i.e., congested or not. Then, in addition to the estimated real-time load, the AP adaptively adjusts the access probability and redistributes the actual access load. Finally, simulation results demonstrate that the proposed SCMA-empowered URA scheme enjoys higher maximum throughput, compared to the conventional orthogonal multiple access (OMA) based URA scheme. Moreover, the accuracy of the presented theoretical analysis and the effectiveness of the user barring mechanism are verified.

eess.SP↗

arXiv2025

Hybrid Generative Semantic and Bit Communications in Satellite Networks: Trade-offs in Latency, Generation Quality, and Computation

As satellite communications play an increasingly important role in future wireless networks, the issue of limited link budget in satellite systems has attracted significant attention in current research. Although semantic communications emerge as a promising solution to address these constraints, it introduces the challenge of increased computational resource consumption in wireless communications. To address these challenges, we propose a multi-layer hybrid bit and generative semantic communication framework which can adapt to the dynamic satellite communication networks. Furthermore, to balance the semantic communication efficiency and performance in satellite-to-ground transmissions, we introduce a novel semantic communication efficiency metric (SEM) that evaluates the trade-offs among latency, computational consumption, and semantic reconstruction quality in the proposed framework. Moreover, we utilize a novel deep reinforcement learning (DRL) algorithm group relative policy optimization (GRPO) to optimize the resource allocation in the proposed network. Simulation results demonstrate the flexibility of our proposed transmission framework and the effectiveness of the proposed metric SEM, illustrate the relationships among various semantic communication metrics.

cs.IT↗

arXiv2025

DISCO Balances the Scales: Adaptive Domain- and Difficulty-Aware Reinforcement Learning on Imbalanced Data

Large Language Models (LLMs) are increasingly aligned with human preferences through Reinforcement Learning from Human Feedback (RLHF). Among RLHF methods, Group Relative Policy Optimization (GRPO) has gained attention for its simplicity and strong performance, notably eliminating the need for a learned value function. However, GRPO implicitly assumes a balanced domain distribution and uniform semantic alignment across groups, assumptions that rarely hold in real-world datasets. When applied to multi-domain, imbalanced data, GRPO disproportionately optimizes for dominant domains, neglecting underrepresented ones and resulting in poor generalization and fairness. We propose Domain-Informed Self-Consistency Policy Optimization (DISCO), a principled extension to GRPO that addresses inter-group imbalance with two key innovations. Domain-aware reward scaling counteracts frequency bias by reweighting optimization based on domain prevalence. Difficulty-aware reward scaling leverages prompt-level self-consistency to identify and prioritize uncertain prompts that offer greater learning value. Together, these strategies promote more equitable and effective policy learning across domains. Extensive experiments across multiple LLMs and skewed training distributions show that DISCO improves generalization, outperforms existing GRPO variants by 5% on Qwen3 models, and sets new state-of-the-art results on multi-domain alignment benchmarks. Our code and data are available at https://github.com/Tonyzhou98/disco_grpo.

cs.CL↗

arXiv2025

Hybrid Beamforming for RIS-Assisted Multiuser Fluid Antenna Systems

Recent advances in reconfigurable antennas have led to the new concept of the fluid antenna system (FAS) for shape and position flexibility, as another degree of freedom for wireless communication enhancement. This paper explores the integration of a transmit FAS array for hybrid beamforming (HBF) into a reconfigurable intelligent surface (RIS)-assisted communication architecture for multiuser communications in the downlink, corresponding to the downlink RIS-assisted multiuser multiple-input single-output (MISO) FAS model (Tx RIS-assisted-MISO-FAS). By considering Rician channel fading, we formulate a sum-rate maximization optimization problem to alternately optimize the HBF matrix, the RIS phase-shift matrix, and the FAS position. Due to the strong coupling of multiple optimization variables, the multi-fractional summation in the sum-rate expression, the modulus-1 limitation of analog phase shifters and RIS, and the antenna position variables appearing in the exponent, this problem is highly non-convex, which is addressed through the block coordinate descent (BCD) framework in conjunction with semidefinite relaxation (SDR) and majorization-minimization (MM) methods. To reduce the computational complexity, we then propose a low-complexity grating-lobe (GL)-based telescopic-FAS (TFA) with multiple delicately deployed RISs under the sub-connected HBF architecture and the line-of-sight (LoS)-dominant channel condition, to allow closed-form solutions for the HBF and TFA position. Our simulation results illustrate that the former optimization scheme significantly enhances the achievable rate of the proposed system, while the GL-based TFA scheme also provides a considerable gain over conventional fixed-position antenna (FPA) systems, requiring statistical channel state information (CSI) only and with low computational complexity.

eess.SP↗

arXiv2025

Beyond Unimodal Boundaries: Generative Recommendation with Multimodal Semantics

Generative recommendation (GR) has become a powerful paradigm in recommendation systems that implicitly links modality and semantics to item representation, in contrast to previous methods that relied on non-semantic item identifiers in autoregressive models. However, previous research has predominantly treated modalities in isolation, typically assuming item content is unimodal (usually text). We argue that this is a significant limitation given the rich, multimodal nature of real-world data and the potential sensitivity of GR models to modality choices and usage. Our work aims to explore the critical problem of Multimodal Generative Recommendation (MGR), highlighting the importance of modality choices in GR nframeworks. We reveal that GR models are particularly sensitive to different modalities and examine the challenges in achieving effective GR when multiple modalities are available. By evaluating design strategies for effectively leveraging multiple modalities, we identify key challenges and introduce MGR-LF++, an enhanced late fusion framework that employs contrastive modality alignment and special tokens to denote different modalities, achieving a performance improvement of over 20% compared to single-modality alternatives.

cs.IR↗

arXiv2025

Amplitude-Domain Reflection Modulation for Active RIS-Assisted Wireless Communications

In this paper, we propose a novel active reconfigurable intelligent surface (RIS)-assisted amplitude-domain reflection modulation (ADRM) transmission scheme, termed as ARIS-ADRM. This innovative approach leverages the additional degree of freedom (DoF) provided by the amplitude domain of the active RIS to perform index modulation (IM), thereby enhancing spectral efficiency (SE) without increasing the costs associated with additional radio frequency (RF) chains. Specifically, the ARIS-ADRM scheme transmits information bits through both the modulation symbol and the index of active RIS amplitude allocation patterns (AAPs). To evaluate the performance of the proposed ARIS-ADRM scheme, we provide an achievable rate analysis and derive a closed-form expression for the upper bound on the average bit error probability (ABEP). Furthermore, we formulate an optimization problem to construct the AAP codebook, aiming to minimize the ABEP. Simulation results demonstrate that the proposed scheme significantly improves error performance under the same SE conditions compared to its benchmarks. This improvement is due to its ability to flexibly adapt the transmission rate by fully exploiting the amplitude domain DoF provided by the active RIS.

eess.SP↗

arXiv2025

Joint Sparse Graph for Enhanced MIMO-AFDM Receiver Design

Affine frequency division multiplexing (AFDM) is a promising chirp-assisted multicarrier waveform for future high-mobility communications. This paper is devoted to enhanced receiver design for multiple input and multiple output AFDM (MIMO-AFDM) systems. Firstly, we introduce a unified variational inference (VI) approach to approximate the target posterior distribution, under which the belief propagation (BP) and expectation propagation (EP)-based algorithms are derived. As both VI-based detection and low-density parity-check (LDPC) decoding can be expressed by bipartite graphs in MIMO-AFDM systems, we construct a joint sparse graph (JSG) by merging the graphs of these two for low-complexity receiver design. Then, based on this graph model, we present the detailed message propagation of the proposed JSG. Additionally, we propose an enhanced JSG (E-JSG) receiver based on the linear constellation encoding model. The proposed E-JSG eliminates the need for interleavers, de-interleavers, and log-likelihood ratio transformations, thus leading to concurrent detection and decoding over the integrated sparse graph. To further reduce detection complexity, we introduce a sparse channel method by approaximating multiple graph edges with insignificant channel coefficients into a single edge on the VI graph. Simulation results show the superiority of the proposed receivers in terms of computational complexity, detection and decoding latency, and error rate performance compared to the conventional ones.

eess.SP↗

arXiv2025

Single Sparse Graph Enhanced Expectation Propagation Algorithm Design for Uplink MIMO-SCMA

Sparse code multiple access (SCMA) and multiple input multiple output (MIMO) are considered as two efficient techniques to provide both massive connectivity and high spectrum efficiency for future machine-type wireless networks. This paper proposes a single sparse graph (SSG) enhanced expectation propagation algorithm (EPA) receiver, referred to as SSG-EPA, for uplink MIMO-SCMA systems. Firstly, we reformulate the sparse codebook mapping process using a linear encoding model, which transforms the variable nodes (VNs) of SCMA from symbol-level to bit-level VNs. Such transformation facilitates the integration of the VNs of SCMA and low-density parity-check (LDPC), thereby emerging the SCMA and LDPC graphs into a SSG. Subsequently, to further reduce the detection complexity, the message propagation between SCMA VNs and function nodes (FNs) are designed based on EPA principles. Different from the existing iterative detection and decoding (IDD) structure, the proposed EPA-SSG allows a simultaneously detection and decoding at each iteration, and eliminates the use of interleavers, de-interleavers, symbol-to-bit, and bit-to-symbol LLR transformations. Simulation results show that the proposed SSG-EPA achieves better error rate performance compared to the state-of-the-art schemes.

eess.SP↗