arXiv subjects

Ziqi Wang

Publications and source records attributed to Ziqi Wang.

At least 91 records · Page 5Linked to original sources

arXiv2025

A Survey on Parallel Reasoning

With the increasing capabilities of Large Language Models (LLMs), parallel reasoning has emerged as a new inference paradigm that enhances reasoning robustness by concurrently exploring multiple lines of thought before converging on a final answer. It has become a significant trend to explore parallel reasoning to overcome the fragility of standard sequential methods and improve practical performance. In this paper, we aim to survey and summarize the progress and challenges of parallel reasoning. We first present a formal definition of parallel reasoning and clarify its distinction from related concepts like Chain-of-Thought. Then, we organize and discuss advanced techniques based on a novel taxonomy, including non-interactive reasoning, interactive reasoning, and efficiency-focused decoding strategies. Additionally, we explore various application scenarios, such as solving complex problems and enhancing the reliability of LLM outputs.Finally, we highlight the core challenges of parallel reasoning and suggest potential directions for future research. We hope that our work can provide a useful roadmap for beginners and encourage more research on improving parallel reasoning methods. Related source can be avaliable in https://github.com/PPPP-kaqiu/Awesome-Parallel-Reasoning.

cs.CL↗

arXiv2025

Deep Learning-based Intrusion Detection Systems: A Survey

Intrusion Detection Systems (IDS) have long been a hot topic in the cybersecurity community. In recent years, with the introduction of deep learning (DL) techniques, IDS have made great progress due to their increasing generalizability. The rationale behind this is that by learning the underlying patterns of known system behaviors, IDS detection can be generalized to intrusions that exploit zero-day vulnerabilities. In this survey, we refer to this type of IDS as DL-based IDS (DL-IDS). From the perspective of DL, this survey systematically reviews all the stages of DL-IDS, including data collection, log storage, log parsing, graph summarization, attack detection, and attack investigation. To accommodate current researchers, a section describing the publicly available benchmark datasets is included. This survey further discusses current challenges and potential future research directions, aiming to help researchers understand the basic ideas and visions of DL-IDS research, as well as to motivate their research interests.

cs.CR↗

arXiv2025

Reflective Unit Test Generation for Precise Type Error Detection with Large Language Models

Type errors in Python often lead to runtime failures, posing significant challenges to software reliability and developer productivity. Existing static analysis tools aim to detect such errors without execution but frequently suffer from high false positive rates. Recently, unit test generation techniques offer great promise in achieving high test coverage, but they often struggle to produce bug-revealing tests without tailored guidance. To address these limitations, we present RTED, a novel type-aware test generation technique for automatically detecting Python type errors. Specifically, RTED combines step-by-step type constraint analysis with reflective validation to guide the test generation process and effectively suppress false positives. We evaluated RTED on two widely-used benchmarks, BugsInPy and TypeBugs. Experimental results show that RTED can detect 22-29 more benchmarked type errors than four state-of-the-art techniques. RTED is also capable of producing fewer false positives, achieving an improvement of 173.9%-245.9% in precision. Furthermore, RTED successfully discovered 12 previously unknown type errors from six real-world open-source Python projects.

cs.SE↗

arXiv2025

Clarifying Semantics of In-Context Examples for Unit Test Generation

Recent advances in large language models (LLMs) have enabled promising performance in unit test generation through in-context learning (ICL). However, the quality of in-context examples significantly influences the effectiveness of generated tests-poorly structured or semantically unclear test examples often lead to suboptimal outputs. In this paper, we propose CLAST, a novel technique that systematically refines unit tests to improve their semantic clarity, thereby enhancing their utility as in-context examples. The approach decomposes complex tests into logically clearer ones and improves semantic clarity through a combination of program analysis and LLM-based rewriting. We evaluated CLAST on four open-source and three industrial projects. The results demonstrate that CLAST largely outperforms UTgen, the state-of-the-art refinement technique, in both preserving test effectiveness and enhancing semantic clarity. Specifically, CLAST fully retains the original effectiveness of unit tests, while UTgen reduces compilation success rate (CSR), pass rate (PR), test coverage (Cov), and mutation score (MS) by an average of 12.90%, 35.82%, 4.65%, and 5.07%, respectively. Over 85.33% of participants in our user study preferred the semantic clarity of CLAST-refined tests. Notably, incorporating CLAST-refined tests as examples effectively improves ICL-based unit test generation approaches such as RAGGen and TELPA, resulting in an average increase of 25.97% in CSR, 28.22% in PR, and 45.99% in Cov for generated tests, compared to incorporating UTgen-refined tests. The insights from the follow-up user study not only reinforce CLAST's potential impact in software testing practice but also illuminate avenues for future research.

cs.SE↗

arXiv2025

Expanding Horizons of Level Diversity via Multi-objective Evolutionary Learning

In recent years, the generation of diverse game levels has gained increasing interest, contributing to a richer and more engaging gaming experience. A number of level diversity metrics have been proposed in literature, which are naturally multi-dimensional, leading to conflicted, complementary, or both relationships among these dimensions. However, existing level generation approaches often fail to comprehensively assess diversity across those dimensions. This paper aims to expand horizons of level diversity by considering multi-dimensional diversity when training generative models. We formulate the model training as a multi-objective learning problem, where each diversity metric is treated as a distinct objective. Furthermore, a multi-objective evolutionary learning framework that optimises multiple diversity metrics simultaneously throughout the model training process is proposed. Our case study on the commonly used benchmark Super Mario Bros. demonstrates that our proposed framework can enhance multi-dimensional diversity and identify a Pareto front of generative models, which provides a range of tradeoffs among playability and two representative diversity metrics, including a content-based one and a player-centered one. Such capability enables decision-makers to make informed choices when selecting generators accommodating a variety of scenarios and the diverse needs of players and designers.

cs.LG↗

arXiv2025

WoW: A Window-to-Window Incremental Index for Range-Filtering Approximate Nearest Neighbor Search

Given a hybrid dataset where every data object consists of a vector and an attribute value, for each query with a target vector and a range filter, range-filtering approximate nearest neighbor search (RFANNS) aims to retrieve the most similar vectors from the dataset and the corresponding attribute values fall in the query range. It is a fundamental function in vector database management systems and intelligent systems with embedding abilities. Dedicated indices for RFANNS accelerate query speed with an acceptable accuracy loss on nearest neighbors. However, they are still facing the challenges to be constructed incrementally and generalized to achieve superior query performance for arbitrary range filters. In this paper, we introduce a window graph-based RFANNS index. For incremental construction, we propose an insertion algorithm to add new vector-attribute pairs into hierarchical window graphs with varying window size. To handle arbitrary range filters, we optimize relevant window search for attribute filter checks and vector distance computations by range selectivity. Extensive experiments on real-world datasets show that for index construction, the indexing time is on par with the most building-efficient index, and 4.9x faster than the most query-efficient index with 0.4-0.5x smaller size; For RFANNS query, it is 4x faster than the most efficient incremental index, and matches the performance of the best statically-built index.

cs.DB↗

arXiv2025

A2R: An Asymmetric Two-Stage Reasoning Framework for Parallel Reasoning

Recent Large Reasoning Models have achieved significant improvements in complex task-solving capabilities by allocating more computation at the inference stage with a "thinking longer" paradigm. Even as the foundational reasoning capabilities of models advance rapidly, the persistent gap between a model's performance in a single attempt and its latent potential, often revealed only across multiple solution paths, starkly highlights the disparity between its realized and inherent capabilities. To address this, we present A2R, an Asymmetric Two-Stage Reasoning framework designed to explicitly bridge the gap between a model's potential and its actual performance. In this framework, an "explorer" model first generates potential solutions in parallel through repeated sampling. Subsequently,a "synthesizer" model integrates these references for a more refined, second stage of reasoning. This two-stage process allows computation to be scaled orthogonally to existing sequential methods. Our work makes two key innovations: First, we present A2R as a plug-and-play parallel reasoning framework that explicitly enhances a model's capabilities on complex questions. For example, using our framework, the Qwen3-8B-distill model achieves a 75% performance improvement compared to its self-consistency baseline. Second, through a systematic analysis of the explorer and synthesizer roles, we identify an effective asymmetric scaling paradigm. This insight leads to A2R-Efficient, a "small-to-big" variant that combines a Qwen3-4B explorer with a Qwen3-8B synthesizer. This configuration surpasses the average performance of a monolithic Qwen3-32B model at a nearly 30% lower cost. Collectively, these results show that A2R is not only a performance-boosting framework but also an efficient and practical solution for real-world applications.

cs.AI↗

arXiv2025

Flow-driven hysteresis in the transition boiling regime

Transition boiling is an intermediate regime occurring between nucleate boiling, where bubbles at the surface efficiently carry heat away, and film boiling, where a layer of vapor formed over the surface insulates the system reducing heat transfer. This regime is inherently unstable and typically occurs near the boiling crisis, where the system approaches the maximum heat flux. Transition boiling hysteresis remains a central open problem in phase-change heat transfer, with critical implications for industrial cooling systems and nuclear reactor safety, since entering this regime sharply reduces heat removal potentially leading to overheating or component damage. We investigate the mechanisms driving hysteresis in the transition boiling regime through large-scale three-dimensional numerical simulations, providing clearcut evidence that hysteresis occurs even under idealized conditions of pool boiling on flat surfaces at constant temperature. This demonstrates that hysteresis arises purely from the flow dynamics of the liquid-vapor system, rather than from surface properties or defects. Moreover, we disclose strong asymmetries in the transition dynamics between nucleate and film boiling. During heating, the transition is abrupt and memory-less, whereas, upon decreasing the surface temperature, it is more complex, with the emergence of metastable coexisting states that can delay the transition.

physics.flu-dyn↗

arXiv2025

Design and Control of a Perching Drone Inspired by the Prey-Capturing Mechanism of Venus Flytrap

The endurance and energy efficiency of drones remain critical challenges in their design and operation. To extend mission duration, numerous studies explored perching mechanisms that enable drones to conserve energy by temporarily suspending flight. This paper presents a new perching drone that utilizes an active flexible perching mechanism inspired by the rapid predation mechanism of the Venus flytrap, achieving perching in less than 100 ms. The proposed system is designed for high-speed adaptability to the perching targets. The overall drone design is outlined, followed by the development and validation of the biomimetic perching structure. To enhance the system stability, a cascade extended high-gain observer (EHGO) based control method is developed, which can estimate and compensate for the external disturbance in real time. The experimental results demonstrate the adaptability of the perching structure and the superiority of the cascaded EHGO in resisting wind and perching disturbances.

cs.RO↗

arXiv2025

Stochastic resonance of rotating particles in turbulence

The chaotic dynamics of small-scale vorticity plays a key role in understanding and controlling turbulence, with direct implications for energy transfer, mixing, and coherent structure evolution. However, measuring or controlling its dynamics remains a major conceptual and experimental challenge due to its transient and chaotic nature. Here we use a combination of experiments, theory and simulations to show that small magnetic particles of different densities, exploring flow regions of distinct vorticity statistics, can act as effective probes for measuring and forcing turbulence at its smallest scale. The interplay between the magnetic torque, from an externally controllable magnetic field, and hydrodynamic stresses, from small-scale turbulent vorticity, reveals an extremely rich phenomenology. Notably, we present the first observation of stochastic resonance for particles in turbulence: turbulent fluctuations, effectively acting as noise, counterintuitively enhance the particle rotational response to external forcing. We identify a pronounced resonant peak in particle rotational phase-lag when the applied magnetic field matches the characteristic intensity of small-scale vortices. Furthermore, we uncover a novel symmetry-breaking mechanism: an oscillating magnetic field with zero-mean angular velocity remarkably induces net particle rotation in turbulence with zero-mean vorticity, as turbulent fluctuations aid the particle in "surfing" the magnetic field. Our findings offer insights into flexible particle manipulation in complex flows and open up a novel magnetic resonance-based approach for measuring vorticity: magnetic particles as probes emit detectable magnetic fields, enabling turbulence quantification even under optically-inaccessible conditions.

physics.flu-dyn↗

arXiv2025

Understanding Emergent In-Context Learning from a Kernel Regression Perspective

Large language models (LLMs) have initiated a paradigm shift in transfer learning. In contrast to the classic pretraining-then-finetuning procedure, in order to use LLMs for downstream prediction tasks, one only needs to provide a few demonstrations, known as in-context examples, without adding more or updating existing model parameters. This in-context learning (ICL) capability of LLMs is intriguing, and it is not yet fully understood how pretrained LLMs acquire such capabilities. In this paper, we investigate the reason why a transformer-based language model can accomplish in-context learning after pre-training on a general language corpus by proposing a kernel-regression perspective of understanding LLMs' ICL bahaviors when faced with in-context examples. More concretely, we first prove that Bayesian inference on in-context prompts can be asymptotically understood as kernel regression $\hat y = \sum_i y_i K(x, x_i)/\sum_i K(x, x_i)$ as the number of in-context demonstrations grows. Then, we empirically investigate the in-context behaviors of language models. We find that during ICL, the attention and hidden features in LLMs match the behaviors of a kernel regression. Finally, our theory provides insights into multiple phenomena observed in the ICL field: why retrieving demonstrative samples similar to test samples can help, why ICL performance is sensitive to the output formats, and why ICL accuracy benefits from selecting in-distribution and representative samples. Code and resources are publicly available at https://github.com/Glaciohound/Explain-ICL-As-Kernel-Regression.

cs.CL↗

arXiv2025

LLM Alignment as Retriever Optimization: An Information Retrieval Perspective

Large Language Models (LLMs) have revolutionized artificial intelligence with capabilities in reasoning, coding, and communication, driving innovation across industries. Their true potential depends on effective alignment to ensure correct, trustworthy and ethical behavior, addressing challenges like misinformation, hallucinations, bias and misuse. While existing Reinforcement Learning (RL)-based alignment methods are notoriously complex, direct optimization approaches offer a simpler alternative. In this work, we introduce a novel direct optimization approach for LLM alignment by drawing on established Information Retrieval (IR) principles. We present a systematic framework that bridges LLM alignment and IR methodologies, mapping LLM generation and reward models to IR's retriever-reranker paradigm. Building on this foundation, we propose LLM Alignment as Retriever Preference Optimization (LarPO), a new alignment method that enhances overall alignment quality. Extensive experiments validate LarPO's effectiveness with 38.9 % and 13.7 % averaged improvement on AlpacaEval2 and MixEval-Hard respectively. Our work opens new avenues for advancing LLM alignment by integrating IR foundations, offering a promising direction for future research.

cs.CL↗

arXiv2025

Advancing Code Coverage: Incorporating Program Analysis with Large Language Models

Automatic test generation plays a critical role in software quality assurance. While the recent advances in Search-Based Software Testing (SBST) and Large Language Models (LLMs) have shown promise in generating useful tests, these techniques still struggle to cover certain branches. Reaching these hard-to-cover branches usually requires constructing complex objects and resolving intricate inter-procedural dependencies in branch conditions, which poses significant challenges for existing test generation techniques. In this work, we propose TELPA, a novel technique aimed at addressing these challenges. Its key insight lies in extracting real usage scenarios of the target method under test to learn how to construct complex objects and extracting methods entailing inter-procedural dependencies with hard-to-cover branches to learn the semantics of branch constraints. To enhance efficiency and effectiveness, TELPA identifies a set of ineffective tests as counter-examples for LLMs and employs a feedback-based process to iteratively refine these counter-examples. Then, TELPA integrates program analysis results and counter-examples into the prompt, guiding LLMs to gain deeper understandings of the semantics of the target method and generate diverse tests that can reach the hard-to-cover branches. Our experimental results on 27 open-source Python projects demonstrate that TELPA significantly outperforms the state-of-the-art SBST and LLM-based techniques, achieving an average improvement of 31.39% and 22.22% in terms of branch coverage.

cs.SE↗

arXiv2025

SMoLoRA: Exploring and Defying Dual Catastrophic Forgetting in Continual Visual Instruction Tuning

Visual instruction tuning (VIT) enables multimodal large language models (MLLMs) to effectively handle a wide range of vision tasks by framing them as language-based instructions. Building on this, continual visual instruction tuning (CVIT) extends the capability of MLLMs to incrementally learn new tasks, accommodating evolving functionalities. While prior work has advanced CVIT through the development of new benchmarks and approaches to mitigate catastrophic forgetting, these efforts largely follow traditional continual learning paradigms, neglecting the unique challenges specific to CVIT. We identify a dual form of catastrophic forgetting in CVIT, where MLLMs not only forget previously learned visual understanding but also experience a decline in instruction following abilities as they acquire new tasks. To address this, we introduce the Separable Mixture of Low-Rank Adaptation (SMoLoRA) framework, which employs separable routing through two distinct modules-one for visual understanding and another for instruction following. This dual-routing design enables specialized adaptation in both domains, preventing forgetting while improving performance. Furthermore, we propose a new CVIT benchmark that goes beyond existing benchmarks by additionally evaluating a model's ability to generalize to unseen tasks and handle diverse instructions across various tasks. Extensive experiments demonstrate that SMoLoRA outperforms existing methods in mitigating dual forgetting, improving generalization to unseen tasks, and ensuring robustness in following diverse instructions. Code is available at https://github.com/Minato-Zackie/SMoLoRA.

cs.CV↗

arXiv2025

UMDATrack: Unified Multi-Domain Adaptive Tracking Under Adverse Weather Conditions

Visual object tracking has gained promising progress in past decades. Most of the existing approaches focus on learning target representation in well-conditioned daytime data, while for the unconstrained real-world scenarios with adverse weather conditions, e.g. nighttime or foggy environment, the tremendous domain shift leads to significant performance degradation. In this paper, we propose UMDATrack, which is capable of maintaining high-quality target state prediction under various adverse weather conditions within a unified domain adaptation framework. Specifically, we first use a controllable scenario generator to synthesize a small amount of unlabeled videos (less than 2% frames in source daytime datasets) in multiple weather conditions under the guidance of different text prompts. Afterwards, we design a simple yet effective domain-customized adapter (DCA), allowing the target objects' representation to rapidly adapt to various weather conditions without redundant model updating. Furthermore, to enhance the localization consistency between source and target domains, we propose a target-aware confidence alignment module (TCA) following optimal transport theorem. Extensive experiments demonstrate that UMDATrack can surpass existing advanced visual trackers and lead new state-of-the-art performance by a significant margin. Our code is available at https://github.com/Z-Z188/UMDATrack.

cs.CV↗

arXiv2025

Model Extrapolation Expedites Alignment

Given the high computational cost of preference alignment training of large language models (LLMs), exploring efficient methods to reduce the training overhead remains an important and compelling research problem. Motivated by the observation that alignment training typically involves only small parameter changes without injecting new knowledge into models, we propose a straightforward method called ExPO (model extrapolation) to expedite LLMs' alignment with human preferences. Given a partially-trained model and its initial SFT checkpoint, ExPO improves the implicit optimization objective of alignment training by simply amplifying the parameter change based on a first-order approximation, without any additional training overhead. Through controlled experiments, we demonstrate that ExPO boosts a DPO model trained with only 20% steps to outperform the fully-trained one. Moreover, we show that ExPO notably improves existing open-source LLMs (ranging from 1.8B to 70B parameters) on the leading AlpacaEval 2.0 and MT-Bench benchmarks, which highlights ExPO's broader utility in efficiently enhancing LLM alignment.

cs.LG↗

arXiv2025

Embodied Neuromorphic Control Applied on a 7-DOF Robotic Manipulator

The development of artificial intelligence towards real-time interaction with the environment is a key aspect of embodied intelligence and robotics. Inverse dynamics is a fundamental robotics problem, which maps from joint space to torque space of robotic systems. Traditional methods for solving it rely on direct physical modeling of robots which is difficult or even impossible due to nonlinearity and external disturbance. Recently, data-based model-learning algorithms are adopted to address this issue. However, they often require manual parameter tuning and high computational costs. Neuromorphic computing is inherently suitable to process spatiotemporal features in robot motion control at extremely low costs. However, current research is still in its infancy: existing works control only low-degree-of-freedom systems and lack performance quantification and comparison. In this paper, we propose a neuromorphic control framework to control 7 degree-of-freedom robotic manipulators. We use Spiking Neural Network to leverage the spatiotemporal continuity of the motion data to improve control accuracy, and eliminate manual parameters tuning. We validated the algorithm on two robotic platforms, which reduces torque prediction error by at least 60% and performs a target position tracking task successfully. This work advances embodied neuromorphic control by one step forward from proof of concept to applications in complex real-world tasks.

cs.RO↗

arXiv2025

Spike-Kal: A Spiking Neuron Network Assisted Kalman Filter

Kalman filtering can provide an optimal estimation of the system state from noisy observation data. This algorithm's performance depends on the accuracy of system modeling and noise statistical characteristics, which are usually challenging to obtain in practical applications. The powerful nonlinear modeling capabilities of deep learning, combined with its ability to extract features from large amounts of data automatically, offer new opportunities for improving the Kalman filter. This paper proposes a novel method that leverages the Spiking Neural Network to optimize the Kalman filter. Our approach aims to reduce the reliance on prior knowledge of system and observation noises, allowing for adaptation to varying statistical characteristics of time-varying noise. Furthermore, we investigate the potential of SNNs in improving the computational efficiency of the Kalman filter. In our method, we design an integration strategy between the SNN and the Kalman filter. The SNN is trained to directly approximate the optimal gain matrix from observation data, thereby alleviating the computational burden of complex matrix operations inherent in traditional Kalman filtering while maintaining the accuracy and robustness of state estimation. Its average error has been reduced by 18\%-65\% compared with other methods.

eess.SY↗