arXiv subjects

Jun Liu

Publications and source records attributed to Jun Liu.

At least 235 records · Page 13Linked to original sources

arXiv2025

Extended Triangular Method: A Generalized Algorithm for Contradiction Separation Based Automated Deduction

Automated deduction lies at the core of Artificial Intelligence (AI), underpinning theorem proving, formal verification, and logical reasoning. Despite decades of progress, reconciling deductive completeness with computational efficiency remains an enduring challenge. Traditional reasoning calculi, grounded in binary resolution, restrict inference to pairwise clause interactions and thereby limit deductive synergy among multiple clauses. The Contradiction Separation Extension (CSE) framework, introduced in 2018, proposed a dynamic multi-clause reasoning theory that redefined logical inference as a process of contradiction separation rather than sequential resolution. While that work established the theoretical foundation, its algorithmic realization remained unformalized and unpublished. This work presents the Extended Triangular Method (ETM), a generalized contradiction-construction algorithm that formalizes and extends the internal mechanisms of contradiction separation. The ETM unifies multiple contradiction-building strategies, including the earlier Standard Extension method, within a triangular geometric framework that supports flexible clause interaction and dynamic synergy. ETM serves as the algorithmic core of several high-performance theorem provers, CSE, CSE-E, CSI-E, and CSI-Enig, whose competitive results in standard first-order benchmarks (TPTP problem sets and CASC 2018-2015) empirically validate the effectiveness and generality of the proposed approach. By bridging theoretical abstraction and operational implementation, ETM advances the contradiction separation paradigm into a generalized, scalable, and practically competitive model for automated reasoning, offering new directions for future research in logical inference and theorem proving.

cs.AI↗

arXiv2025

ALISE: Annotation-Free LiDAR Instance Segmentation for Autonomous Driving

The manual annotation of outdoor LiDAR point clouds for instance segmentation is extremely costly and time-consuming. Current methods attempt to reduce this burden but still rely on some form of human labeling. To completely eliminate this dependency, we introduce ALISE, a novel framework that performs LiDAR instance segmentation without any annotations. The central challenge is to generate high-quality pseudo-labels in a fully unsupervised manner. Our approach starts by employing Vision Foundation Models (VFMs), guided by text and images, to produce initial pseudo-labels. We then refine these labels through a dedicated spatio-temporal voting module, which combines 2D and 3D semantics for both offline and online optimization. To achieve superior feature learning, we further introduce two forms of semantic supervision: a set of 2D prior-based losses that inject visual knowledge into the 3D network, and a novel prototype-based contrastive loss that builds a discriminative feature space by exploiting 3D semantic consistency. This comprehensive design results in significant performance gains, establishing a new state-of-the-art for unsupervised 3D instance segmentation. Remarkably, our approach even outperforms MWSIS, a method that operates with supervision from ground-truth (GT) 2D bounding boxes by a margin of 2.53% in mAP (50.95% vs. 48.42%).

cs.CV↗

arXiv2025

Dynamic Automated Deduction by Contradiction Separation: The Standard Extension Algorithm

Automated deduction seeks to enable machines to reason with mathematical precision and logical completeness. Classical resolution-based systems, such as Prover9, E, and Vampire, rely on binary inference, which inherently limits multi-clause synergy during proof search. The Contradiction Separation Extension (CSE) framework, introduced by Xu et al. (2018), overcame this theoretical limitation by extending deduction beyond binary inference. However, the original work did not specify how contradictions are algorithmically constructed and extended in practice. This paper presents the Standard Extension algorithm, the first explicit procedural realization of contradiction separation reasoning. The proposed method dynamically constructs contradictions through complementary literal extension, thereby operationalizing the CSE theory within a unified algorithm for satisfiability and unsatisfiability checking. The algorithm's soundness and completeness are formally proven, and its effectiveness is supported indirectly through the performance of CSE-based systems, including CSE, CSE-E, CSI-E, and CSI-Enig in major automated reasoning competitions (CASC) in the last few years. These results confirm that the Standard Extension mechanism constitutes a robust and practically validated foundation for dynamic, multi-clause automated deduction.

cs.LO↗

arXiv2025

Quantum Grid Path Planning Using Parallel QAOA Circuits Based on Minimum Energy Principle

To overcome the bottleneck of classical path planning schemes in solving NP problems and address the predicament faced by current mainstream quantum path planning frameworks in the Noisy Intermediate-Scale Quantum (NISQ) era, this study attempts to construct a quantum path planning solution based on parallel Quantum Approximate Optimization Algorithm (QAOA) architecture. Specifically, the grid path planning problem is mapped to the problem of finding the minimum quantum energy state. Two parallel QAOA circuits are built to simultaneously execute two solution processes, namely connectivity energy calculation and path energy calculation. A classical algorithm is employed to filter out unreasonable solutions of connectivity energy, and finally, the approximate optimal solution to the path planning problem is obtained by merging the calculation results of the two parallel circuits. The research findings indicate that by setting appropriate filter parameters, quantum states corresponding to position points with extremely low occurrence probabilities can be effectively filtered out, thereby increasing the probability of obtaining the target quantum state. Even when the circuit layer number p is only 1, the theoretical solution of the optimal path coding combination can still be found by leveraging the critical role of the filter. Compared with serial circuits, parallel circuits exhibit a significant advantage, as they can find the optimal feasible path coding combination with the highest probability.

quant-ph↗

arXiv2025

TSLA: A Task-Specific Learning Adaptation for Semantic Segmentation on Autonomous Vehicles Platform

Autonomous driving platforms encounter diverse driving scenarios, each with varying hardware resources and precision requirements. Given the computational limitations of embedded devices, it is crucial to consider computing costs when deploying on target platforms like the NVIDIA\textsuperscript{\textregistered} DRIVE PX 2. Our objective is to customize the semantic segmentation network according to the computing power and specific scenarios of autonomous driving hardware. We implement dynamic adaptability through a three-tier control mechanism -- width multiplier, classifier depth, and classifier kernel -- allowing fine-grained control over model components based on hardware constraints and task requirements. This adaptability facilitates broad model scaling, targeted refinement of the final layers, and scenario-specific optimization of kernel sizes, leading to improved resource allocation and performance. Additionally, we leverage Bayesian Optimization with surrogate modeling to efficiently explore hyperparameter spaces under tight computational budgets. Our approach addresses scenario-specific and task-specific requirements through automatic parameter search, accommodating the unique computational complexity and accuracy needs of autonomous driving. It scales its Multiply-Accumulate Operations (MACs) for Task-Specific Learning Adaptation (TSLA), resulting in alternative configurations tailored to diverse self-driving tasks. These TSLA customizations maximize computational capacity and model accuracy, optimizing hardware utilization.

cs.CV↗

arXiv2025

Ab initio calculation of atomic solid hydrogen phases based on Gutzwiller many-body wave functions

We apply two ab initio many-body methods based on Gutzwiller wave functions, i.e., correlation matrix renormalization theory (CMRT) and Gutzwiller conjugate gradient minimization (GCGM), to the study of crystalline phases of atomic hydrogen. Both methods avoid empirical Hubbard U parameters and are free from double-counting issues. CMRT employs a Gutzwiller-type approximation that enables efficient calculations, while GCGM goes beyond this approximation to achieve higher accuracy at higher computational cost. By benchmarking against available quantum Monte Carlo results, we demonstrate that while both methods are more accurate than the widely used density-functional theory (DFT), GCGM systematically captures additional correlation energy missing in CMRT, leading to significantly improved total energy predictions. We also show that by including the correlation energy $E_c$ from LDA in the CMRT calculation, CMRT+$E_c$ produces energy in better agreement with the QMC results in these hydrogen lattice systems.

cond-mat.str-el↗

arXiv2025

Computing Control Lyapunov-Barrier Functions: Softmax Relaxation and Smooth Patching with Formal Guarantees

We present a computational framework for synthesizing a single smooth Lyapunov function that certifies both asymptotic stability and safety. We show that the existence of a strictly compatible pair of control barrier and control Lyapunov functions (CBF-CLF) guarantees the existence of such a function on the exact safe set certified by the barrier. To maximize the certifiable safe domain while retaining differentiability, we employ a log-sum-exp (softmax) relaxation of the nonsmooth maximum barrier, together with a counterexample-guided refinement that inserts half-space cuts until a strict barrier condition is verifiable. We then patch the softmax barrier with a CLF via an explicit smooth bump construction, which is always feasible under the strict compatibility condition. All conditions are formally verified using a satisfiability modulo theories (SMT) solver, enabled by a reformulation of Farkas' lemma for encoding strict compatibility. On benchmark systems, including a power converter, we show that the certified safe stabilization regions obtained with the proposed approach are often less conservative than those achieved by state-of-the-art sum-of-squares (SOS) compatible CBF-CLF designs.

eess.SY↗

arXiv2025

CoFFT: Chain of Foresight-Focus Thought for Visual Language Models

Despite significant advances in Vision Language Models (VLMs), they remain constrained by the complexity and redundancy of visual input. When images contain large amounts of irrelevant information, VLMs are susceptible to interference, thus generating excessive task-irrelevant reasoning processes or even hallucinations. This limitation stems from their inability to discover and process the required regions during reasoning precisely. To address this limitation, we present the Chain of Foresight-Focus Thought (CoFFT), a novel training-free approach that enhances VLMs' visual reasoning by emulating human visual cognition. Each Foresight-Focus Thought consists of three stages: (1) Diverse Sample Generation: generates diverse reasoning samples to explore potential reasoning paths, where each sample contains several reasoning steps; (2) Dual Foresight Decoding: rigorously evaluates these samples based on both visual focus and reasoning progression, adding the first step of optimal sample to the reasoning process; (3) Visual Focus Adjustment: precisely adjust visual focus toward regions most beneficial for future reasoning, before returning to stage (1) to generate subsequent reasoning samples until reaching the final answer. These stages function iteratively, creating an interdependent cycle where reasoning guides visual focus and visual focus informs subsequent reasoning. Empirical results across multiple benchmarks using Qwen2.5-VL, InternVL-2.5, and Llava-Next demonstrate consistent performance improvements of 3.1-5.8% with controllable increasing computational overhead.

cs.CV↗

arXiv2025

All-Optical Generation of Dense, Multi-GeV, Longitudinally-Polarized Positron Beams

The production of high-yield, longitudinally polarized positron beams represents an outstanding challenge in advanced accelerator science. Laser-driven schemes offer a compact alternative but typically yield only transverse polarization, or require pre-polarized electron beams, and struggle to efficiently accelerate positrons to high energies. Here, we introduce an all-optical scheme that overcomes these limitations by integrating positron generation, acceleration, and spin manipulation in a unified framework. Through a head-on collision between an ultraintense, circularly polarized laser pulse and a counterpropagating unpolarized electron beam, we drive a robust QED cascade. The nonlinear Breit-Wheeler process within the cascade produces positrons that are born directly within the strong laser field. Crucially, these positrons are instantaneously captured and accelerated to multi-GeV energies (up to $\sim$9 GeV) via a direct laser acceleration mechanism, while their spins are simultaneously rotated to longitudinal alignment by the field dynamics. Our Monte-Carlo simulations confirm the simultaneous achievement of a high positron yield ($\sim$20 $e^+/e^-$), a high average longitudinal polarization ($\sim$50\%), and GeV-scale energies. This all-optical source, feasible at upcoming ultraintense laser facilities, presents a compact and efficient solution for applications in collider physics and fundamental high-energy experiments.

physics.acc-ph↗

arXiv2025

Brain Tumor Classification on MRI in Light of Molecular Markers

In research findings, co-deletion of the 1p/19q gene is associated with clinical outcomes in low-grade gliomas. The ability to predict 1p19q status is critical for treatment planning and patient follow-up. This study aims to utilize a specially MRI-based convolutional neural network for brain cancer detection. Although public networks such as RestNet and AlexNet can effectively diagnose brain cancers using transfer learning, the model includes quite a few weights that have nothing to do with medical images. As a result, the diagnostic results are unreliable by the transfer learning model. To deal with the problem of trustworthiness, we create the model from the ground up, rather than depending on a pre-trained model. To enable flexibility, we combined convolution stacking with a dropout and full connect operation, it improved performance by reducing overfitting. During model training, we also supplement the given dataset and inject Gaussian noise. We use three--fold cross-validation to train the best selection model. Comparing InceptionV3, VGG16, and MobileNetV2 fine-tuned with pre-trained models, our model produces better results. On an validation set of 125 codeletion vs. 31 not codeletion images, the proposed network achieves 96.37\% percent F1-score, 97.46\% percent precision, and 96.34\% percent recall when classifying 1p/19q codeletion and not codeletion images.

eess.IV↗

arXiv2025

End-to-End On-Device Quantization-Aware Training for LLMs at Inference Cost

Quantization is an effective technique to reduce the deployment cost of large language models (LLMs), and post-training quantization (PTQ) has been widely studied due to its efficiency. However, existing PTQ methods are limited by their inability to fine-tune model parameters and often suffer significant accuracy loss in low-bit scenarios. Quantization-aware training (QAT) provides a more principled solution, but its reliance on backpropagation incurs prohibitive memory costs, limiting its practicality for LLM deployment. To address these challenges, we propose ZeroQAT, a zeroth-order optimization-based QAT framework that supports both weight and activation quantization. ZeroQAT leverages forward-only gradient estimation to eliminate backpropagation, substantially reducing computational and memory overhead while retaining the benefits of end-to-end optimization. We further introduce a lightweight variant of ZeroQAT for quantized fine-tuning, which freezes and pre-quantizes most parameters to further cut memory usage. Experiments show that ZeroQAT consistently outperforms representative PTQ and QAT baselines while requiring significantly less memory. For example, ZeroQAT enables fine-tuning of a 13B model at extremely low bit-widths (e.g., 2-4 bits) on a single 8GB GPU, and even allows fine-tuning a 6.7B model on a OnePlus 12 smartphone, demonstrating its practicality for end-to-end QAT on resource-limited edge devices.

cs.LG↗

arXiv2025

From Static to Dynamic: Adaptive Monte Carlo Search for Mathematical Process Supervision

The quality of process data plays a key role in training a Process Reward Model (PRM), which can enhance the complex mathematical reasoning capability of large language models. Existing methods estimate the quality of reasoning steps based on a fixed-budget sampling strategy and navigate a vast search space to perform path expansion during the automated data generation process, resulting in their inefficiency and inflexibility. To address these issues, we propose Adaptive Monte Carlo Search (AMCS), a framework that transforms data generation from fixed, static to adaptive, dynamic search at the level of node value estimation and path expansion. On one hand, AMCS adaptively refines estimation by allocating more samples to uncertain reasoning steps while using fewer samples for those that are easier to estimate. On the other hand, it enhances the path expansion through a Monte Carlo algorithm with a temporally adaptive policy that begins with broad exploration and gradually shifts toward exploiting the most promising directions. With AMCS, we construct a large-scale dataset MathSearch-200K of about 200K process supervision examples for training PRMs. To verify the effectiveness of our method, we conduct extensive experiments on four mathematical reasoning benchmarks. Experimental results show that Qwen2.5-Math-7B-PRM-AMCS achieves up to 76.2% accuracy on MATH500 with GLM-4-9B, outperforming all baseline PRMs. Notably, a 7B model supervised by Qwen2.5-Math-7B-PRM-AMCS surpasses a 72B model with weaker supervision. Moreover, Qwen2.5-Math-7B-PRM-AMCS maintains consistent advantages on out-of-distribution problems, demonstrating strong generalization capability. Our code is available at https://github.com/reml-group/AMCS.

cs.AI↗

arXiv2025

Plan before Solving: Problem-Aware Strategy Routing for Mathematical Reasoning with LLMs

Existing methods usually leverage a fixed strategy, such as natural language reasoning, code-augmented reasoning, tool-integrated reasoning, or ensemble-based reasoning, to guide Large Language Models (LLMs) to perform mathematical reasoning. Our analysis reveals that the single strategy cannot adapt to problem-specific requirements and thus overlooks the trade-off between effectiveness and efficiency. To address these issues, we propose Planning and Routing through Instance-Specific Modeling (PRISM), a novel framework that decouples mathematical reasoning into two stages: strategy planning and targeted execution. Specifically, we first curate a multi-strategy preference dataset, which we call MathStrat, capturing correctness, process quality, and computational efficiency for each problem--strategy pair. Then, we train a lightweight Strategy Adapter based on the dataset to obtain confidence distributions over the mentioned four reasoning strategies. At inference time, an adaptive routing policy dynamically tailors the reasoning approach based on predictor confidence. It directs the model to use single-strategy execution for high-confidence predictions, dual-strategy verification for competitive scenarios, or comprehensive multi-strategy exploration for uncertain cases. Extensive experiments across five mathematical reasoning benchmarks demonstrate that PRISM consistently outperforms individual strategies and ensemble baselines, achieving improvements ranging from 0.9% to 7.6% across different base models. The adaptive routing approach shows particularly strong benefits for mathematical reasoning tasks across diverse model architectures. Our code is released at https://github.com/reml-group/PRISM.

cs.AI↗

arXiv2025

Socio-Economic Model of AI Agents

Modern socio-economic systems are undergoing deep integration with artificial intelligence technologies. This paper constructs a heterogeneous agent-based modeling framework that incorporates both human workers and autonomous AI agents, to study the impact of AI collaboration under resource constraints on aggregate social output. We build five progressively extended models: Model 1 serves as the baseline of pure human collaboration; Model 2 introduces AI as collaborators; Model 3 incorporates network effects among agents; Model 4 treats agents as independent producers; and Model 5 integrates both network effects and independent agent production. Through theoretical derivation and simulation analysis, we find that the introduction of AI agents can significantly increase aggregate social output. When considering network effects among agents, this increase exhibits nonlinear growth far exceeding the simple sum of individual contributions. Under the same resource inputs, treating agents as independent producers provides higher long-term growth potential; introducing network effects further demonstrates strong characteristics of increasing returns to scale.

cs.AI↗

arXiv2025

Time-frequency representations on Lorentz spaces over locally compact Abelian groups

Let $G$ be a locally compact Abelian group with a fixed Haar measure and, denote by $\widehat{G}$ its dual group. In this article, the authors obtain various boundedness of the short-time Fourier transform on Lorentz spaces: $$L^{p_1,u}(G)\times L^{p_2,v}(G)\to L^{q,w}(G\times\widehat{G})$$ with the indexes satisfying appropriate relations. These results are then used to prove the corresponding boundedness of $τ$-Wigner transforms and $τ$-Weyl operators. As an application, the Lieb's uncertainty principle in the context of Lorentz spaces is finally investigated. All these results are new even for the case when $G$ is finite.

math.CA↗

arXiv2025

MLF-4DRCNet: Multi-Level Fusion with 4D Radar and Camera for 3D Object Detection in Autonomous Driving

The emerging 4D millimeter-wave radar, measuring the range, azimuth, elevation, and Doppler velocity of objects, is recognized for its cost-effectiveness and robustness in autonomous driving. Nevertheless, its point clouds exhibit significant sparsity and noise, restricting its standalone application in 3D object detection. Recent 4D radar-camera fusion methods have provided effective perception. Most existing approaches, however, adopt explicit Bird's-Eye-View fusion paradigms originally designed for LiDAR-camera fusion, neglecting radar's inherent drawbacks. Specifically, they overlook the sparse and incomplete geometry of radar point clouds and restrict fusion to coarse scene-level integration. To address these problems, we propose MLF-4DRCNet, a novel two-stage framework for 3D object detection via multi-level fusion of 4D radar and camera images. Our model incorporates the point-, scene-, and proposal-level multi-modal information, enabling comprehensive feature representation. It comprises three crucial components: the Enhanced Radar Point Encoder (ERPE) module, the Hierarchical Scene Fusion Pooling (HSFP) module, and the Proposal-Level Fusion Enhancement (PLFE) module. Operating at the point-level, ERPE densities radar point clouds with 2D image instances and encodes them into voxels via the proposed Triple-Attention Voxel Feature Encoder. HSFP dynamically integrates multi-scale voxel features with 2D image features using deformable attention to capture scene context and adopts pooling to the fused features. PLFE refines region proposals by fusing image features, and further integrates with the pooled features from HSFP. Experimental results on the View-of-Delft (VoD) and TJ4DRadSet datasets demonstrate that MLF-4DRCNet achieves the state-of-the-art performance. Notably, it attains performance comparable to LiDAR-based models on the VoD dataset.

cs.CV↗

arXiv2025

Ultra-short-term solar power forecasting by deep learning and data reconstruction

The integration of solar power has been increasing as the green energy transition rolls out. The penetration of solar power challenges the grid stability and energy scheduling, due to its intermittent energy generation. Accurate and near real-time solar power prediction is of critical importance to tolerant and support the permeation of distributed and volatile solar power production in the energy system. In this paper, we propose a deep-learning based ultra-short-term solar power prediction with data reconstruction. We decompose the data for the prediction to facilitate extensive exploration of the spatial and temporal dependencies within the data. Particularly, we reconstruct the data into low- and high-frequency components, using ensemble empirical model decomposition with adaptive noise (CEEMDAN). We integrate meteorological data with those two components, and employ deep-learning models to capture long- and short-term dependencies towards the target prediction period. In this way, we excessively exploit the features in historical data in predicting a ultra-short-term solar power production. Furthermore, as ultra-short-term prediction is vulnerable to local optima, we modify the optimization in our deep-learning training by penalizing long prediction intervals. Numerical experiments with diverse settings demonstrate that, compared to baseline models, the proposed method achieves improved generalization in data reconstruction and higher prediction accuracy for ultra-short-term solar power production.

cs.LG↗

arXiv2025

Reinforcement Learning Meets Large Language Models: A Survey of Advancements and Applications Across the LLM Lifecycle

In recent years, training methods centered on Reinforcement Learning (RL) have markedly enhanced the reasoning and alignment performance of Large Language Models (LLMs), particularly in understanding human intents, following user instructions, and bolstering inferential strength. Although existing surveys offer overviews of RL augmented LLMs, their scope is often limited, failing to provide a comprehensive summary of how RL operates across the full lifecycle of LLMs. We systematically review the theoretical and practical advancements whereby RL empowers LLMs, especially Reinforcement Learning with Verifiable Rewards (RLVR). First, we briefly introduce the basic theory of RL. Second, we thoroughly detail application strategies for RL across various phases of the LLM lifecycle, including pre-training, alignment fine-tuning, and reinforced reasoning. In particular, we emphasize that RL methods in the reinforced reasoning phase serve as a pivotal driving force for advancing model reasoning to its limits. Next, we collate existing datasets and evaluation benchmarks currently used for RL fine-tuning, spanning human-annotated datasets, AI-assisted preference data, and program-verification-style corpora. Subsequently, we review the mainstream open-source tools and training frameworks available, providing clear practical references for subsequent research. Finally, we analyse the future challenges and trends in the field of RL-enhanced LLMs. This survey aims to present researchers and practitioners with the latest developments and frontier trends at the intersection of RL and LLMs, with the goal of fostering the evolution of LLMs that are more intelligent, generalizable, and secure.

cs.CL↗