arXiv subjects

Lei Liu

Publications and source records attributed to Lei Liu.

At least 109 records · Page 6Linked to original sources

arXiv2025

From Uniform to Adaptive: General Skip-Block Mechanisms for Efficient PDE Neural Operators

In recent years, Neural Operators(NO) have gradually emerged as a popular approach for solving Partial Differential Equations (PDEs). However, their application to large-scale engineering tasks suffers from significant computational overhead. And the fact that current models impose a uniform computational cost while physical fields exhibit vastly different complexities constitutes a fundamental mismatch, which is the root of this inefficiency. For instance, in turbulence flows, intricate vortex regions require deeper network processing compared to stable flows. To address this, we introduce a framework: Skip-Block Routing (SBR), a general framework designed for Transformer-based neural operators, capable of being integrated into their multi-layer architectures. First, SBR uses a routing mechanism to learn the complexity and ranking of tokens, which is then applied during inference. Then, in later layers, it decides how many tokens are passed forward based on this ranking. This way, the model focuses more processing capacity on the tokens that are more complex. Experiments demonstrate that SBR is a general framework that seamlessly integrates into various neural operators. Our method reduces computational cost by approximately 50% in terms of Floating Point Operations (FLOPs), while still delivering up to 2x faster inference without sacrificing accuracy.

cs.LG↗

arXiv2025

Bringing Private Reads to Hyperledger Fabric via Private Information Retrieval

Permissioned blockchains ensure integrity and auditability of shared data but expose query parameters to peers during read operations, creating privacy risks for organizations querying sensitive records. This paper proposes a Private Information Retrieval (PIR) mechanism to enable private reads from Hyperledger Fabric's world state, allowing endorsing peers to process encrypted queries without learning which record is accessed. We implement and benchmark a PIR-enabled chaincode that performs ciphertext-plaintext (ct-pt) homomorphic multiplication directly within evaluate transactions, preserving Fabric's endorsement and audit semantics. The prototype achieves an average end-to-end latency of 113 ms and a peer-side execution time below 42 ms, with approximately 2 MB of peer network traffic per private read in development mode--reducible by half under in-process deployment. Storage profiling across three channel configurations shows near-linear growth: block size increases from 77 kilobytes to 294 kilobytes and world-state from 112 kilobytes to 332 kilobytes as the ring dimension scales from 8,192 to 32,768 coefficients. Parameter analysis further indicates that ring size and record length jointly constrain packing capacity, supporting up to 512 records of 64 bytes each under the largest configuration. These results confirm the practicality of PIR-based private reads in Fabric for smaller, sensitive datasets and highlight future directions to optimize performance and scalability.

cs.CR↗

arXiv2025

Learning to Seek Evidence: A Verifiable Reasoning Agent with Causal Faithfulness Analysis

Explanations for AI models in high-stakes domains like medicine often lack verifiability, which can hinder trust. To address this, we propose an interactive agent that produces explanations through an auditable sequence of actions. The agent learns a policy to strategically seek external visual evidence to support its diagnostic reasoning. This policy is optimized using reinforcement learning, resulting in a model that is both efficient and generalizable. Our experiments show that this action-based reasoning process significantly improves calibrated accuracy, reducing the Brier score by 18\% compared to a non-interactive baseline. To validate the faithfulness of the agent's explanations, we introduce a causal intervention method. By masking the visual evidence the agent chooses to use, we observe a measurable degradation in its performance ($Δ$Brier=+0.029), confirming that the evidence is integral to its decision-making process. Our work provides a practical framework for building AI systems with verifiable and faithful reasoning capabilities.

cs.AI↗

arXiv2025

Super-Liouville equation with a spinorial Yamabe type term

In this paper, we study the super-Liouville equation with a spinorial Yamabe type term, a natural generalization of Liouville equation, super-Liouville equation and spinorial Yamabe type equation. We establish some refined qualitative properties for such a blow-up sequence. In particular, we show energy identities not only for the spinor part but also for the function part. Moreover, the local masses at a blow-up point are also computed. A new phenomenon is that there are two kinds of singularities and local masses due to the nonlinear spinorial Yamabe type term, which is different from super-Liouville equation.

math.AP↗

arXiv2025

Chiron-o1: Igniting Multimodal Large Language Models towards Generalizable Medical Reasoning via Mentor-Intern Collaborative Search

Multimodal large language models (MLLMs) have begun to demonstrate robust reasoning capabilities on general tasks, yet their application in the medical domain remains in its early stages. Constructing chain-of-thought (CoT) training data is essential for bolstering the reasoning abilities of medical MLLMs. However, existing approaches exhibit a deficiency in offering a comprehensive framework for searching and evaluating effective reasoning paths towards critical diagnosis. To address this challenge, we propose Mentor-Intern Collaborative Search (MICS), a novel reasoning-path searching scheme to generate rigorous and effective medical CoT data. MICS first leverages mentor models to initialize the reasoning, one step at a time, then prompts each intern model to continue the thinking along those initiated paths, and finally selects the optimal reasoning path according to the overall reasoning performance of multiple intern models. The reasoning performance is determined by an MICS-Score, which assesses the quality of generated reasoning paths. Eventually, we construct MMRP, a multi-task medical reasoning dataset with ranked difficulty, and Chiron-o1, a new medical MLLM devised via a curriculum learning strategy, with robust visual question-answering and generalizable reasoning capabilities. Extensive experiments demonstrate that Chiron-o1, trained on our CoT dataset constructed using MICS, achieves state-of-the-art performance across a list of medical visual question answering and reasoning benchmarks. Codes are available at https://github.com/manglu097/Chiron-o1

cs.CV↗

arXiv2025

Aerial RIS-Enhanced Communications: Joint UAV Trajectory, Altitude Control, and Phase Shift Design

Reconfigurable intelligent surface (RIS) has emerged as a pivotal technology for enhancing wireless networks. Compared to terrestrial RIS deployed on building facades, aerial RIS (ARIS) mounted on quadrotor unmanned aerial vehicle (UAV) offers superior flexibility and extended coverage. However, the inevitable tilt and altitude variations of a quadrotor UAV during flight may lead to severe beam misalignment, significantly degrading ARIS's performance. To address this challenge, we propose a Euler angles-based ARIS control scheme that jointly optimizes the altitude and trajectory of the ARIS by leveraging the UAV's dynamic model. Considering the constraints on ARIS flight energy consumption, flight safety, and the transmission power of a base station (BS), we jointly design the ARIS's altitude, trajectory, phase shifts, and BS beamforming to maximize the system sum-rate. Due to the continuous control nature of ARIS flight and the strong coupling among variables, we formulate the problem as a Markov decision process and adopt a soft actor-critic algorithm with prioritized experience replay to learn efficient ARIS control policies. Based on the optimized ARIS configuration, we further employ the water-filling and bisection method to efficiently determine the optimal BS beamforming. Numerical results demonstrate that the proposed algorithm significantly outperforms benchmarks in both convergence and communication performance, achieving approximately 14.4\% improvement in sum-rate. Moreover, in comparison to the fixed-horizontal ARIS scheme, the proposed scheme yields more adaptive trajectories and significantly mitigates performance degradation caused by ARIS tilting, demonstrating strong potential for practical ARIS deployment.

eess.SP↗

arXiv2025

Enhanced Self-Distillation Framework for Efficient Spiking Neural Network Training

Spiking Neural Networks (SNNs) exhibit exceptional energy efficiency on neuromorphic hardware due to their sparse activation patterns. However, conventional training methods based on surrogate gradients and Backpropagation Through Time (BPTT) not only lag behind Artificial Neural Networks (ANNs) in performance, but also incur significant computational and memory overheads that grow linearly with the temporal dimension. To enable high-performance SNN training under limited computational resources, we propose an enhanced self-distillation framework, jointly optimized with rate-based backpropagation. Specifically, the firing rates of intermediate SNN layers are projected onto lightweight ANN branches, and high-quality knowledge generated by the model itself is used to optimize substructures through the ANN pathways. Unlike traditional self-distillation paradigms, we observe that low-quality self-generated knowledge may hinder convergence. To address this, we decouple the teacher signal into reliable and unreliable components, ensuring that only reliable knowledge is used to guide the optimization of the model. Extensive experiments on CIFAR-10, CIFAR-100, CIFAR10-DVS, and ImageNet demonstrate that our method reduces training complexity while achieving high-performance SNN training. Our code is available at https://github.com/Intelli-Chip-Lab/enhanced-self-distillation-framework-for-snn.

cs.CV↗

arXiv2025

4DGS-Craft: Consistent and Interactive 4D Gaussian Splatting Editing

Recent advances in 4D Gaussian Splatting (4DGS) editing still face challenges with view, temporal, and non-editing region consistency, as well as with handling complex text instructions. To address these issues, we propose 4DGS-Craft, a consistent and interactive 4DGS editing framework. We first introduce a 4D-aware InstructPix2Pix model to ensure both view and temporal consistency. This model incorporates 4D VGGT geometry features extracted from the initial scene, enabling it to capture underlying 4D geometric structures during editing. We further enhance this model with a multi-view grid module that enforces consistency by iteratively refining multi-view input images while jointly optimizing the underlying 4D scene. Furthermore, we preserve the consistency of non-edited regions through a novel Gaussian selection mechanism, which identifies and optimizes only the Gaussians within the edited regions. Beyond consistency, facilitating user interaction is also crucial for effective 4DGS editing. Therefore, we design an LLM-based module for user intent understanding. This module employs a user instruction template to define atomic editing operations and leverages an LLM for reasoning. As a result, our framework can interpret user intent and decompose complex instructions into a logical sequence of atomic operations, enabling it to handle intricate user commands and further enhance editing performance. Compared to related works, our approach enables more consistent and controllable 4D scene editing. Our code will be made available upon acceptance.

cs.CV↗

arXiv2025

Autoregressive End-to-End Planning with Time-Invariant Spatial Alignment and Multi-Objective Policy Refinement

The inherent sequential modeling capabilities of autoregressive models make them a formidable baseline for end-to-end planning in autonomous driving. Nevertheless, their performance is constrained by a spatio-temporal misalignment, as the planner must condition future actions on past sensory data. This creates an inconsistent worldview, limiting the upper bound of performance for an otherwise powerful approach. To address this, we propose a Time-Invariant Spatial Alignment (TISA) module that learns to project initial environmental features into a consistent ego-centric frame for each future time step, effectively correcting the agent's worldview without explicit future scene prediction. In addition, we employ a kinematic action prediction head (i.e., acceleration and yaw rate) to ensure physically feasible trajectories. Finally, we introduce a multi-objective post-training stage using Direct Preference Optimization (DPO) to move beyond pure imitation. Our approach provides targeted feedback on specific driving behaviors, offering a more fine-grained learning signal than the single, overall objective used in standard DPO. Our model achieves a state-of-the-art 89.8 PDMS on the NAVSIM dataset among autoregressive models. The video document is available at https://tisa-dpo-e2e.github.io/.

cs.RO↗

arXiv2025

Enhanced Survival Trees

We introduce a new survival tree method for censored failure time data that incorporates three key advancements over traditional approaches. First, we develop a more computationally efficient splitting procedure that effectively mitigates the end-cut preference problem, and we propose an intersected validation strategy to reduce the variable selection bias inherent in greedy searches. Second, we present a novel framework for determining tree structures through fused regularization. In combination with conventional pruning, this approach enables the merging of non-adjacent terminal nodes, producing more parsimonious and interpretable models. Third, we address inference by constructing valid confidence intervals for median survival times within the subgroups identified by the final tree. To achieve this, we apply bootstrap-based bias correction to standard errors. The proposed method is assessed through extensive simulation studies and illustrated with data from the Alzheimer's Disease Neuroimaging Initiative (ADNI) study.

stat.ME↗

arXiv2025

Joint Channel Estimation and Computation Offloading in Fluid Antenna-assisted MEC Networks

With the emergence of fluid antenna (FA) in wireless communications, the capability to dynamically adjust port positions offers substantial benefits in spatial diversity and spectrum efficiency, which are particularly valuable for mobile edge computing (MEC) systems. Therefore, we propose an FA-assisted MEC offloading framework to minimize system delay. This framework faces two severe challenges, which are the complexity of channel estimation due to dynamic port configuration and the inherent non-convexity of the joint optimization problem. Firstly, we propose Information Bottleneck Metric-enhanced Channel Compressed Sensing (IBM-CCS), which advances FA channel estimation by integrating information relevance into the sensing process and capturing key features of FA channels effectively. Secondly, to address the non-convex and high-dimensional optimization problem in FA-assisted MEC systems, which includes FA port selection, beamforming, power control, and resource allocation, we propose a game theory-assisted Hierarchical Twin-Dueling Multi-agent Algorithm (HiTDMA) based offloading scheme, where the hierarchical structure effectively decouples and coordinates the optimization tasks between the user side and the base station side. Crucially, the game theory effectively reduces the dimensionality of power control variables, allowing deep reinforcement learning (DRL) agents to achieve improved optimization efficiency. Numerical results confirm that the proposed scheme significantly reduces system delay and enhances offloading performance, outperforming benchmarks. Additionally, the IBM-CCS channel estimation demonstrates superior accuracy and robustness under varying port densities, contributing to efficient communication under imperfect CSI.

eess.SP↗

arXiv2025

3D Gaussian Splatting Data Compression with Mixture of Priors

3D Gaussian Splatting (3DGS) data compression is crucial for enabling efficient storage and transmission in 3D scene modeling. However, its development remains limited due to inadequate entropy models and suboptimal quantization strategies for both lossless and lossy compression scenarios, where existing methods have yet to 1) fully leverage hyperprior information to construct robust conditional entropy models, and 2) apply fine-grained, element-wise quantization strategies for improved compression granularity. In this work, we propose a novel Mixture of Priors (MoP) strategy to simultaneously address these two challenges. Specifically, inspired by the Mixture-of-Experts (MoE) paradigm, our MoP approach processes hyperprior information through multiple lightweight MLPs to generate diverse prior features, which are subsequently integrated into the MoP feature via a gating mechanism. To enhance lossless compression, the resulting MoP feature is utilized as a hyperprior to improve conditional entropy modeling. Meanwhile, for lossy compression, we employ the MoP feature as guidance information in an element-wise quantization procedure, leveraging a prior-guided Coarse-to-Fine Quantization (C2FQ) strategy with a predefined quantization step value. Specifically, we expand the quantization step value into a matrix and adaptively refine it from coarse to fine granularity, guided by the MoP feature, thereby obtaining a quantization step matrix that facilitates element-wise quantization. Extensive experiments demonstrate that our proposed 3DGS data compression framework achieves state-of-the-art performance across multiple benchmarks, including Mip-NeRF360, BungeeNeRF, DeepBlending, and Tank&Temples.

cs.CV↗

arXiv2025

Random Modulation: Achieving Asymptotic Replica Optimality over Arbitrary Norm-Bounded and Spectrally Convergent Channel Matrices

This paper introduces a random modulation technique that is decoupled from the channel matrix, allowing it to be applied to arbitrary norm-bounded and spectrally convergent channel matrices. The proposed random modulation constructs an equivalent dense and random channel matrix, ensuring that the signals undergo sufficient statistical channel fading. It also guarantees the asymptotic replica maximum a posteriori (MAP) bit-error rate (BER) optimality of approximate message passing (AMP)-type detectors for linear systems with arbitrary norm-bounded and spectrally convergent channel matrices when their state evolution has a unique fixed point. Then, a low-complexity cross-domain memory approximate message passing (CD-MAMP) detector is proposed for random modulation, leveraging the sparsity of the time-domain channel and the randomness of the random transform-domain channel. Furthermore, the optimal power allocation schemes are derived to minimize the replica MAP BER and maximize the replica constrained capacity of random-modulated linear systems, assuming the availability of channel state information (CSI) at the transceiver. Numerical results show that the proposed random modulation can achieve BER and block-error rate (BLER) performance gains of up to 2 - 3 dB compared to existing OFDM/OTFS/AFDM with 5G-NR LDPC codes, under both average and optimized power allocation.

cs.IT↗

arXiv2025

AnomalyControl: Learning Cross-modal Semantic Features for Controllable Anomaly Synthesis

Anomaly synthesis is a crucial approach to augment abnormal data for advancing anomaly inspection. Based on the knowledge from the large-scale pre-training, existing text-to-image anomaly synthesis methods predominantly focus on textual information or coarse-aligned visual features to guide the entire generation process. However, these methods often lack sufficient descriptors to capture the complicated characteristics of realistic anomalies (e.g., the fine-grained visual pattern of anomalies), limiting the realism and generalization of the generation process. To this end, we propose a novel anomaly synthesis framework called AnomalyControl to learn cross-modal semantic features as guidance signals, which could encode the generalized anomaly cues from text-image reference prompts and improve the realism of synthesized abnormal samples. Specifically, AnomalyControl adopts a flexible and non-matching prompt pair (i.e., a text-image reference prompt and a targeted text prompt), where a Cross-modal Semantic Modeling (CSM) module is designed to extract cross-modal semantic features from the textual and visual descriptors. Then, an Anomaly-Semantic Enhanced Attention (ASEA) mechanism is formulated to allow CSM to focus on the specific visual patterns of the anomaly, thus enhancing the realism and contextual relevance of the generated anomaly features. Treating cross-modal semantic features as the prior, a Semantic Guided Adapter (SGA) is designed to encode effective guidance signals for the adequate and controllable synthesis process. Extensive experiments indicate that AnomalyControl can achieve state-of-the-art results in anomaly synthesis compared with existing methods while exhibiting superior performance for downstream tasks.

cs.CV↗

arXiv2025

High-Capacity and Real-Time Acoustic Communication by Multiplexing Velocity

Acoustic communication is indispensable for underwater networks, deep ocean exploration, and biological monitoring, environments where electromagnetic waves become impractical. However, unlike the latter, whose vector polarization naturally supports multiple information channels, acoustic waves are longitudinal and have traditionally relied almost exclusively on a single scalar pressure channel, posing a fundamental limit on their data-carrying capacity. Here, we theoretically and experimentally demonstrate that the vector velocity of acoustic waves can serve as a polarization-like physical degree of freedom. Using its three components as mutually independent communication channels and demodulating them with a single vector sensor, we achieve reliable, high-capacity, and real-time information transmission. Multiplexing velocity adds a new dimension to acoustic communication. When combined with other physical degrees of freedom (frequency, phase, etc.), this approach can significantly enhance the information capacity, opening new avenues for next-generation acoustic technology.

physics.app-ph↗

arXiv2025

Asymptotic behaviors and dynamics of degenerate and mixed solitons for the coupled Hirota system with strong coherent coupling effects

In this work, we study the asymptotic behaviors and dynamics of degenerate and mixed solitons for the coupled Hirota system with strong coherent coupling effects in the isotropic nonlinear medium. Using the binary Darboux transformation, we derive the solutions to represent the degenerate solitons with two eigenvalues that are conjugate to each other. We obtain three types of degenerate solitons and provide their asymptotic expressions. Notably, these degenerate solitons exhibit time-dependent velocities, and the relative distance between the two asymptotic solitons increases logarithmically with the higher-order perturbation parameter $|\varepsilon|$ increasing. We also asymptotically reveal four interaction mechanisms between a degenerate soliton and a bell-shaped soliton: (1) elastic interaction with a position shift; (2) inelastic interaction for the degenerate soliton but elastic for the bell-shaped one; (3) elastic interaction for the degenerate soliton but inelastic for the bell-shaped one; and (4) the coherent interaction during a longer interaction region and elastic interaction based on specific parameter conditions. Besides, we analyze a special degenerate vector soliton that exhibits significant coherence effects, and numerically study the relationship between the robustness of such solitons and parameter $\varepsilon$. Our results indicate that $\varepsilon$ significantly affects the coherence of these solitons, and their robustness decreases when $|\varepsilon|$ increases.

nlin.PS↗

arXiv2025

CX-Mind: A Pioneering Multimodal Large Language Model for Interleaved Reasoning in Chest X-ray via Curriculum-Guided Reinforcement Learning

Chest X-ray (CXR) imaging is one of the most widely used diagnostic modalities in clinical practice, encompassing a broad spectrum of diagnostic tasks. Recent advancements have seen the extensive application of reasoning-based multimodal large language models (MLLMs) in medical imaging to enhance diagnostic efficiency and interpretability. However, existing multimodal models predominantly rely on "one-time" diagnostic approaches, lacking verifiable supervision of the reasoning process. This leads to challenges in multi-task CXR diagnosis, including lengthy reasoning, sparse rewards, and frequent hallucinations. To address these issues, we propose CX-Mind, the first generative model to achieve interleaved "think-answer" reasoning for CXR tasks, driven by curriculum-based reinforcement learning and verifiable process rewards (CuRL-VPR). Specifically, we constructed an instruction-tuning dataset, CX-Set, comprising 708,473 images and 2,619,148 samples, and generated 42,828 high-quality interleaved reasoning data points supervised by clinical reports. Optimization was conducted in two stages under the Group Relative Policy Optimization framework: initially stabilizing basic reasoning with closed-domain tasks, followed by transfer to open-domain diagnostics, incorporating rule-based conditional process rewards to bypass the need for pretrained reward models. Extensive experimental results demonstrate that CX-Mind significantly outperforms existing medical and general-domain MLLMs in visual understanding, text generation, and spatiotemporal alignment, achieving an average performance improvement of 25.1% over comparable CXR-specific models. On real-world clinical dataset (Rui-CXR), CX-Mind achieves a mean recall@1 across 14 diseases that substantially surpasses the second-best results, with multi-center expert evaluations further confirming its clinical utility across multiple dimensions.

cs.LG↗

arXiv2025

EnTao-GPM: DNA Foundation Model for Predicting the Germline Pathogenic Mutations

Distinguishing pathogenic mutations from benign polymorphisms remains a critical challenge in precision medicine. EnTao-GPM, developed by Fudan University and BioMap, addresses this through three innovations: (1) Cross-species targeted pre-training on disease-relevant mammalian genomes (human, pig, mouse), leveraging evolutionary conservation to enhance interpretation of pathogenic motifs, particularly in non-coding regions; (2) Germline mutation specialization via fine-tuning on ClinVar and HGMD, improving accuracy for both SNVs and non-SNVs; (3) Interpretable clinical framework integrating DNA sequence embeddings with LLM-based statistical explanations to provide actionable insights. Validated against ClinVar, EnTao-GPM demonstrates superior accuracy in mutation classification. It revolutionizes genetic testing by enabling faster, more accurate, and accessible interpretation for clinical diagnostics (e.g., variant assessment, risk identification, personalized treatment) and research, advancing personalized medicine.

q-bio.GN↗