arXiv subjects

Chengxi Zhang

Publications and source records attributed to Chengxi Zhang.

10 recordsLinked to original sources

arXiv2026

AutoCRAT: Within-trajectory Joint Control of Stochasticity and Compute for LLM Reasoning

Large language models (LLMs) achieve strong reasoning performance, which depends critically on inference-time decisions. Yet these decisions are commonly handled by static, one-size-fits-all policies, limiting adaptation to diverse tasks and reasoning stages. Recent adaptive methods partially address this limitation, but they primarily adapt either decoding stochasticity (how the model explores) or reasoning compute (how long the model reasons) in isolation, leaving their interaction within a single reasoning trajectory unmodeled. To address this challenge, we shift toward a within-trajectory joint control view, and instantiate it in AutoCRAT, a decoder-side controller for frozen backbones. Using only signals available during decoding, AutoCRAT jointly adjusts sampling stochasticity and reasoning budget during generation. AutoCRAT operates over a discrete action space and updates control decisions only at semantic boundaries, improving stability while remaining responsive to the evolving reasoning process. Comprehensive evaluation across 6 benchmarks demonstrates that AutoCRAT (I) uses 13.8-52.7% fewer inference tokens on average than recommended static configurations, (II) surpasses recommended static and adaptive baselines by 1.5-4.5% in relative accuracy, and (III) enjoys strong cross-backbone transferability.

cs.AI↗

arXiv2026

Poisson Tangent Limits and Critical Policy Switching for Sampled Bellman Operators

Consider a discounted Markov decision process with continuous action space in which, at each state visit, the controller draws a random pool of $N$ candidate actions and selects among them. When the optimal action set has zero mass under the sampling distribution, the value of this random-candidate model converges to the optimal value as $N$ grows, but the rate of convergence and the asymptotic selection rule are governed jointly by the geometry of the optimal set and by the transition kernels of the near-optimal candidates. This paper develops an exact first-order theory of both. The rescaled near-optimal candidates converge to a marked Poisson point process, and the leading term of the value gap is the fixed point of a nonlinear tangential Bellman operator, a stochastic generalization of the classical resolvent that emerges when several optimal actions compete. The asymptotic selection at exact ties is genuinely dynamic, driven by the transition kernels through the fixed point, and admits an explicit Mecke integral formula at the limiting Poisson level; perturbing the tie at the critical rate yields a switching layer in which the value gap and the selection interpolate continuously between the branch regimes, and in the unique-optimum heterogeneous case the critical class is propagated at the slowest global scale through the discounted reachability of the limit policy. Numerical experiments confirm the predicted rates, constants, and selection probabilities.

eess.SY↗

arXiv2025

WP-CrackNet: A Collaborative Adversarial Learning Framework for End-to-End Weakly-Supervised Road Crack Detection

Road crack detection is essential for intelligent infrastructure maintenance in smart cities. To reduce reliance on costly pixel-level annotations, we propose WP-CrackNet, an end-to-end weakly-supervised method that trains with only image-level labels for pixel-wise crack detection. WP-CrackNet integrates three components: a classifier generating class activation maps (CAMs), a reconstructor measuring feature inferability, and a detector producing pixel-wise road crack detection results. During training, the classifier and reconstructor alternate in adversarial learning to encourage crack CAMs to cover complete crack regions, while the detector learns from pseudo labels derived from post-processed crack CAMs. This mutual feedback among the three components improves learning stability and detection accuracy. To further boost detection performance, we design a path-aware attention module (PAAM) that fuses high-level semantics from the classifier with low-level structural cues from the reconstructor by modeling spatial and channel-wise dependencies. Additionally, a center-enhanced CAM consistency module (CECCM) is proposed to refine crack CAMs using center Gaussian weighting and consistency constraints, enabling better pseudo-label generation. We create three image-level datasets and extensive experiments show that WP-CrackNet achieves comparable results to supervised methods and outperforms existing weakly-supervised methods, significantly advancing scalable road inspection. The source code package and datasets are available at https://mias.group/WP-CrackNet/.

cs.CV↗

arXiv2025

Learning from Expert Factors: Trajectory-level Reward Shaping for Formulaic Alpha Mining

Reinforcement learning (RL) has successfully automated the complex process of mining formulaic alpha factors, for creating interpretable and profitable investment strategies. However, existing methods are hampered by the sparse rewards given the underlying Markov Decision Process. This inefficiency limits the exploration of the vast symbolic search space and destabilizes the training process. To address this, Trajectory-level Reward Shaping (TLRS), a novel reward shaping method, is proposed. TLRS provides dense, intermediate rewards by measuring the subsequence-level similarity between partially generated expressions and a set of expert-designed formulas. Furthermore, a reward centering mechanism is introduced to reduce training variance. Extensive experiments on six major Chinese and U.S. stock indices show that TLRS significantly improves the predictive power of mined factors, boosting the Rank Information Coefficient by 9.29% over existing potential-based shaping algorithms. Notably, TLRS achieves a major leap in computational efficiency by reducing its time complexity with respect to the feature dimension from linear to constant, which is a significant improvement over distance-based baselines.

cs.LG↗

arXiv2025

Mitigation of birefringence in cavity-based quantum networks using frequency-encoded photons

Atom-cavity systems offer unique advantages for building large-scale distributed quantum computers by providing strong atom-photon coupling while allowing for high-fidelity local operations of atomic qubits. However, in prevalent schemes where the photonic state is encoded in polarization, cavity birefringence introduces an energy splitting of the cavity eigenmodes and alters the polarization states, thus limiting the fidelity of remote entanglement generation. To address this challenge, we propose a scheme that encodes the photonic qubit in the frequency degree-of-freedom. The scheme relies on resonant coupling of multiple transverse cavity modes to different atomic transitions that are well-separated in frequency. We numerically investigate the temporal properties of the photonic wavepacket, two-photon interference visibility, and atom-atom entanglement fidelity under various cavity polarization-mode splittings and find that our scheme is less affected by cavity birefringence. Finally, we propose practical implementations in two trapped ion systems, using the fine structure splitting in the metastable D state of $\mathrm{^{40}Ca^{+}}$, and the hyperfine splitting in the ground state of $\mathrm{^{225}Ra^{+}}$. Our study presents an alternative approach for cavity-based quantum networks that is less sensitive to birefringent effects, and is applicable to a variety of atomic and solid-state emitter-cavity interfaces.

quant-ph↗

arXiv2024

Real-Time AIoT for AAV Antenna Interference Detection via Edge-Cloud Collaboration

In the fifth-generation (5G) era, eliminating communication interference sources is crucial for maintaining network performance. Interference often originates from unauthorized or malfunctioning antennas, and radio monitoring agencies must address numerous sources of such antennas annually. Unmanned aerial vehicles (UAVs) can improve inspection efficiency. However, the data transmission delay in the existing cloud-only (CO) artificial intelligence (AI) mode fails to meet the low latency requirements for real-time performance. Therefore, we propose a computer vision-based AI of Things (AIoT) system to detect antenna interference sources for UAVs. The system adopts an optimized edge-cloud collaboration (ECC+) mode, combining a keyframe selection algorithm (KSA), focusing on reducing end-to-end latency (E2EL) and ensuring reliable data transmission, which aligns with the core principles of ultra-reliable low-latency communication (URLLC). At the core of our approach is an end-to-end antenna localization scheme based on the tracking-by-detection (TBD) paradigm, including a detector (EdgeAnt) and a tracker (AntSort). EdgeAnt achieves state-of-the-art (SOTA) performance with a mean average precision (mAP) of 42.1% on our custom antenna interference source dataset, requiring only 3 million parameters and 14.7 GFLOPs. On the COCO dataset, EdgeAnt achieves 38.9% mAP with 5.4 GFLOPs. We deployed EdgeAnt on Jetson Xavier NX (TRT) and Raspberry Pi 4B (NCNN), achieving real-time inference speeds of 21.1 (1088) and 4.8 (640) frames per second (FPS), respectively. Compared with CO mode, the ECC+ mode reduces E2EL by 88.9%, increases accuracy by 28.2%. Additionally, the system offers excellent scalability for coordinated multiple UAVs inspections. The detector code is publicly available at https://github.com/SCNU-RISLAB/EdgeAnt.

eess.SP↗

arXiv2024

QuantFactor REINFORCE: Mining Steady Formulaic Alpha Factors with Variance-bounded REINFORCE

Alpha factor mining aims to discover investment signals from the historical financial market data, which can be used to predict asset returns and gain excess profits. Powerful deep learning methods for alpha factor mining lack interpretability, making them unacceptable in the risk-sensitive real markets. Formulaic alpha factors are preferred for their interpretability, while the search space is complex and powerful explorative methods are urged. Recently, a promising framework is proposed for generating formulaic alpha factors using deep reinforcement learning, and quickly gained research focuses from both academia and industries. This paper first argues that the originally employed policy training method, i.e., Proximal Policy Optimization (PPO), faces several important issues in the context of alpha factors mining. Herein, a novel reinforcement learning algorithm based on the well-known REINFORCE algorithm is proposed. REINFORCE employs Monte Carlo sampling to estimate the policy gradient-yielding unbiased but high variance estimates. The minimal environmental variability inherent in the underlying state transition function, which adheres to the Dirac distribution, can help alleviate this high variance issue, making REINFORCE algorithm more appropriate than PPO. A new dedicated baseline is designed to theoretically reduce the commonly suffered high variance of REINFORCE. Moreover, the information ratio is introduced as a reward shaping mechanism to encourage the generation of steady alpha factors that can better adapt to changes in market volatility. Evaluations on real assets data indicate the proposed algorithm boosts correlation with returns by 3.83\%, and a stronger ability to obtain excess returns compared to the latest alpha factors mining methods, which meets the theoretical results well.

q-fin.CP↗

arXiv2024

YOLO-Ant: A Lightweight Detector via Depthwise Separable Convolutional and Large Kernel Design for Antenna Interference Source Detection

In the era of 5G communication, removing interference sources that affect communication is a resource-intensive task. The rapid development of computer vision has enabled unmanned aerial vehicles to perform various high-altitude detection tasks. Because the field of object detection for antenna interference sources has not been fully explored, this industry lacks dedicated learning samples and detection models for this specific task. In this article, an antenna dataset is created to address important antenna interference source detection issues and serves as the basis for subsequent research. We introduce YOLO-Ant, a lightweight CNN and transformer hybrid detector specifically designed for antenna interference source detection. Specifically, we initially formulated a lightweight design for the network depth and width, ensuring that subsequent investigations were conducted within a lightweight framework. Then, we propose a DSLK-Block module based on depthwise separable convolution and large convolution kernels to enhance the network's feature extraction ability, effectively improving small object detection. To address challenges such as complex backgrounds and large interclass differences in antenna detection, we construct DSLKVit-Block, a powerful feature extraction module that combines DSLK-Block and transformer structures. Considering both its lightweight design and accuracy, our method not only achieves optimal performance on the antenna dataset but also yields competitive results on public datasets.

cs.CV↗

arXiv2024

MF-MOS: A Motion-Focused Model for Moving Object Segmentation

Moving object segmentation (MOS) provides a reliable solution for detecting traffic participants and thus is of great interest in the autonomous driving field. Dynamic capture is always critical in the MOS problem. Previous methods capture motion features from the range images directly. Differently, we argue that the residual maps provide greater potential for motion information, while range images contain rich semantic guidance. Based on this intuition, we propose MF-MOS, a novel motion-focused model with a dual-branch structure for LiDAR moving object segmentation. Novelly, we decouple the spatial-temporal information by capturing the motion from residual maps and generating semantic features from range images, which are used as movable object guidance for the motion branch. Our straightforward yet distinctive solution can make the most use of both range images and residual maps, thus greatly improving the performance of the LiDAR-based MOS task. Remarkably, our MF-MOS achieved a leading IoU of 76.7% on the MOS leaderboard of the SemanticKITTI dataset upon submission, demonstrating the current state-of-the-art performance. The implementation of our MF-MOS has been released at https://github.com/SCNU-RISLAB/MF-MOS.

cs.CV↗

arXiv2021

BoningKnife: Joint Entity Mention Detection and Typing for Nested NER via prior Boundary Knowledge

While named entity recognition (NER) is a key task in natural language processing, most approaches only target flat entities, ignoring nested structures which are common in many scenarios. Most existing nested NER methods traverse all sub-sequences which is both expensive and inefficient, and also don't well consider boundary knowledge which is significant for nested entities. In this paper, we propose a joint entity mention detection and typing model via prior boundary knowledge (BoningKnife) to better handle nested NER extraction and recognition tasks. BoningKnife consists of two modules, MentionTagger and TypeClassifier. MentionTagger better leverages boundary knowledge beyond just entity start/end to improve the handling of nesting levels and longer spans, while generating high quality mention candidates. TypeClassifier utilizes a two-level attention mechanism to decouple different nested level representations and better distinguish entity types. We jointly train both modules sharing a common representation and a new dual-info attention layer, which leads to improved representation focus on entity-related information. Experiments over different datasets show that our approach outperforms previous state of the art methods and achieves 86.41, 85.46, and 94.2 F1 scores on ACE2004, ACE2005, and NNE, respectively.

cs.CL↗