arXiv subjects

Chunyu Yang

Publications and source records attributed to Chunyu Yang.

8 recordsLinked to original sources

arXiv2026

Learning from Consensus and Disagreement: Unsupervised On-Policy Self-Distillation with Minority-Trajectory Contrast

On-policy self-distillation improves language-model reasoning by querying a teacher on states actually visited by the student. Recent methods create a powerful information asymmetry by exposing the teacher to privileged context, yet they fundamentally rely on external supervision---such as gold solutions or verifiers---to construct this advantage. We introduce CoDA (Consensus and Disagreement Alignment), a fully unsupervised framework that creates reliable privileged information entirely from the latent uncertainty structure of a model's own unlabeled rollouts. CoDA extracts two complementary signals. In the positive branch, answer-level consensus identifies a stable reasoning mode, which conditions a frozen self-teacher to provide dense distributional guidance on fresh student trajectories. However, because agreement does not guarantee correctness, positive-only distillation risks amplifying correlated errors into a false consensus. To break this harmful feedback loop, CoDA incorporates a negative branch that exploits disagreement: minority trajectories are treated as unstable alternatives and gently penalized via a reference-anchored, KTO-style calibration objective. This unpaired binary feedback provides robust regularization without requiring the strong assumption that the consensus is the absolute ground truth. Empirical evaluations on competition-level mathematical benchmarks demonstrate that CoDA significantly improves reasoning, outperforming self-generated baselines and effectively stabilizing training against erroneous consensus.

cs.LG↗

arXiv2026

Agon: A Semi-Supervised Framework for Robust Satellite Interference Detection

The rapid expansion of non-geostationary orbit (NGSO) satellites alongside existing geostationary orbit (GSO) systems has intensified spectrum congestion and inter-system interference, placing stringent demands on real-time interference management to sustain reliable coexistence in next-generation communication networks. While existing machine learning (ML)-based reconstruction models have made strides, they remain constrained to an area under the curve (AUC) of 0.83 due to fixed thresholds, causing unacceptable false alarm rates that undermine critical link reliability. Additionally, their decoupled training paradigm neglects cross-domain dependencies, limiting time and frequency-domain AUCs to 0.83 and 0.71, respectively. To address these limitations, this paper introduces a semi-supervised satellite interference detection framework named Agon, employing a novel two-stage hybrid learning paradigm. Agon integrates masked autoencoder (MAE) pre-training of a dual attention transformer (DAT) with multi-task fine-tuning to optimize a direct binary classifier, effectively eliminating unstable thresholds. Furthermore, it incorporates high-order statistics (HOS)-augmented attention and wavelet regularization to bolster noise robustness and structural fidelity. Extensive validation on public NGSO-GSO dataset and a high-fidelity NGSO-NGSO dataset demonstrates that Agon achieves state-of-the-art (SOTA) detection performance, with a 25.3% improvement in AUC. Moreover, the multi-task learning (MTL) framework facilitates accurate modulation classification with accuracies exceeding 90%, while simultaneously maintaining optimal detection performance across diverse scenarios characterized by varying off-axis angles and interference-to-noise ratios (INRs).

cs.NI↗

arXiv2026

Unveil: Unified Visual-Textual Integration and Distillation for Multi-modal Document Retrieval

Document retrieval in real-world scenarios faces significant challenges due to diverse document formats and modalities. Traditional text-based approaches rely on tailored parsing techniques that disregard layout information and are prone to errors, while recent parsing-free visual methods often struggle to capture fine-grained textual semantics in text-rich scenarios. To address these limitations, we propose \textbf{Unveil}, a novel visual-textual embedding framework that effectively integrates textual and visual features for robust document representation. Through knowledge distillation, we transfer the semantic understanding capabilities from the visual-textual embedding model to a purely visual model, enabling efficient parsing-free retrieval while preserving semantic fidelity. Experimental results demonstrate that our visual-textual embedding method surpasses existing approaches, while knowledge distillation successfully bridges the performance gap between visual-textual and visual-only methods, improving both retrieval accuracy and efficiency.

cs.CL↗

arXiv2025

Genotype-Phenotype Integration through Machine Learning and Personalized Gene Regulatory Networks for Cancer Metastasis Prediction

Metastasis is the leading cause of cancer-related mortality, yet most predictive models rely on shallow architectures and neglect patient-specific regulatory mechanisms. Here, we integrate classical machine learning and deep learning to predict metastatic potential across multiple cancer types. Gene expression profiles from the Cancer Cell Line Encyclopedia were combined with a transcription factor-target prior from DoRothEA, focusing on nine metastasis-associated regulators. After selecting differential genes using the Kruskal-Wallis test, ElasticNet, Random Forest, and XGBoost models were trained for benchmarking. Personalized gene regulatory networks were then constructed using PANDA and LIONESS and analyzed through a graph attention neural network (GATv2) to learn topological and expression-based representations. While XGBoost achieved the highest AUROC (0.7051), the GNN captured non-linear regulatory dependencies at the patient level. These results demonstrate that combining traditional machine learning with graph-based deep learning enables a scalable and interpretable framework for metastasis risk prediction in precision oncology.

q-bio.OT↗

arXiv2025

PromptTea: Let Prompts Tell TeaCache the Optimal Threshold

Despite recent progress in video generation, inference speed remains a major bottleneck. A common acceleration strategy involves reusing model outputs via caching mechanisms at fixed intervals. However, we find that such fixed-frequency reuse significantly degrades quality in complex scenes, while manually tuning reuse thresholds is inefficient and lacks robustness. To address this, we propose Prompt-Complexity-Aware (PCA) caching, a method that automatically adjusts reuse thresholds based on scene complexity estimated directly from the input prompt. By incorporating prompt-derived semantic cues, PCA enables more adaptive and informed reuse decisions than conventional caching methods. We also revisit the assumptions behind TeaCache and identify a key limitation: it suffers from poor input-output relationship modeling due to an oversimplified prior. To overcome this, we decouple the noisy input, enhance the contribution of meaningful textual information, and improve the model's predictive accuracy through multivariate polynomial feature expansion. To further reduce computational cost, we replace the static CFGCache with DynCFGCache, a dynamic mechanism that selectively reuses classifier-free guidance (CFG) outputs based on estimated output variations. This allows for more flexible reuse without compromising output quality. Extensive experiments demonstrate that our approach achieves significant acceleration-for example, 2.79x speedup on the Wan2.1 model-while maintaining high visual fidelity across a range of scenes.

cs.CV↗

arXiv2025

DualAttWaveNet: Multiscale Attention Networks for Satellite Interference Detection

The escalating overlap between non-geostationary orbit (NGSO) and geostationary orbit (GSO) satellite frequency allocations necessitates accurate interference detection methods that address two pivotal technical gaps: computationally efficient signal analysis for real-time operation, and robust anomaly discrimination under varying interference patterns. Existing deep learning approaches employ encoder-decoder anomaly detectors that threshold input-output discrepancies for robustness. While the transformer-based TrID model achieves state-of-the-art performance (AUC: 0.8318, F1: 0.8321), its multi-head attention incurs prohibitive computation time, and its decoupled training of time-frequency models overlooks cross-domain dependencies. To overcome these problems, we propose DualAttWaveNet. A bidirectional attention fusion layer dynamically correlates time-domain samples using parameter-efficient cross-attention routing. A wavelet-regularized reconstruction loss enforces multi-scale consistency. We train the model on public dataset which consists of 48 hours of satellite signals. Experiments show that compared to TrID, DualAttWaveNet improves AUC by 12% and reduces inference time by 50% to 540ms per batch while maintaining F1-score.

eess.SP↗

arXiv2025

CTSAC: Curriculum-Based Transformer Soft Actor-Critic for Goal-Oriented Robot Exploration

With the increasing demand for efficient and flexible robotic exploration solutions, Reinforcement Learning (RL) is becoming a promising approach in the field of autonomous robotic exploration. However, current RL-based exploration algorithms often face limited environmental reasoning capabilities, slow convergence rates, and substantial challenges in Sim-To-Real (S2R) transfer. To address these issues, we propose a Curriculum Learning-based Transformer Reinforcement Learning Algorithm (CTSAC) aimed at improving both exploration efficiency and transfer performance. To enhance the robot's reasoning ability, a Transformer is integrated into the perception network of the Soft Actor-Critic (SAC) framework, leveraging historical information to improve the farsightedness of the strategy. A periodic review-based curriculum learning is proposed, which enhances training efficiency while mitigating catastrophic forgetting during curriculum transitions. Training is conducted on the ROS-Gazebo continuous robotic simulation platform, with LiDAR clustering optimization to further reduce the S2R gap. Experimental results demonstrate the CTSAC algorithm outperforms the state-of-the-art non-learning and learning-based algorithms in terms of success rate and success rate-weighted exploration time. Moreover, real-world experiments validate the strong S2R transfer capabilities of CTSAC.

cs.RO↗

arXiv2023

When Mining Electric Locomotives Meet Reinforcement Learning

As the most important auxiliary transportation equipment in coal mines, mining electric locomotives are mostly operated manually at present. However, due to the complex and ever-changing coal mine environment, electric locomotive safety accidents occur frequently these years. A mining electric locomotive control method that can adapt to different complex mining environments is needed. Reinforcement Learning (RL) is concerned with how artificial agents ought to take actions in an environment so as to maximize reward, which can help achieve automatic control of mining electric locomotive. In this paper, we present how to apply RL to the autonomous control of mining electric locomotives. To achieve more precise control, we further propose an improved epsilon-greedy (IEG) algorithm which can better balance the exploration and exploitation. To verify the effectiveness of this method, a co-simulation platform for autonomous control of mining electric locomotives is built which can complete closed-loop simulation of the vehicles. The simulation results show that this method ensures the locomotives following the front vehicle safely and responding promptly in the event of sudden obstacles on the road when the vehicle in complex and uncertain coal mine environments.

eess.SY↗