Deep neural networks face several challenges in hyperspectral image classification, including complex and sparse ground object distributions, small clustered structures, and elongated multi-branch features that often lead to missing detections. To better adapt to ground object distributions and achieve adaptive dynamic feature responses while skipping redundant information, this paper proposes a Spatial-Geometry Enhanced 3D Dynamic Snake Network (SG-DSCNet) based on an improved 3D-DenseNet model. The network employs Dynamic Snake Convolution (DSCConv), which introduces deformable offsets to enhance kernel flexibility through constrained self-learning, thereby improving regional perception of ground objects. Additionally, we propose a multi-view feature fusion strategy that generates multiple morphological kernel templates from DSCConv to observe target structures from different perspectives and achieve efficient feature fusion through summarizing key characteristics. This dynamic approach enables the model to focus more flexibly on critical spatial structures when processing different regions, rather than relying on fixed receptive fields of single static kernels. The DSC module enhances model representation capability through dynamic kernel aggregation without increasing network depth or width. Experimental results demonstrate superior performance on the IN, UP, and KSC datasets, outperforming mainstream hyperspectral classification methods.
Contrastive learning (CL) has become a cornerstone of self-supervised pretraining (SSP) in foundation models, however, extending CL to pixel-wise representation, crucial for medical vision, remains an open problem. Standard CL formulates SSP as a binary optimization problem (binary CL) where the excessive pursuit of feature dispersion leads to an over-dispersion problem, breaking pixel-wise feature correlation thus disrupting the intra-class distribution. Our vector CL reformulates CL as a vector regression problem, enabling dispersion quantification in pixel-wise pretraining via modeling feature distances in regressing displacement vectors. To implement this novel paradigm, we propose the COntrast in VEctor Regression (COVER) framework. COVER establishes an extendable vector-based self-learning, enforces a consistent optimization flow from vector regression to distance modeling, and leverages a vector pyramid architecture for granularity adaptation, thus preserving pixel-wise feature correlations in SSP. Extensive experiments across 8 tasks, spanning 2 dimensions and 4 modalities, show that COVER significantly improves pixel-wise SSP, advancing generalizable medical visual foundation models.
This paper presents a novel method for enhancing the adaptability of Proportional-Integral-Derivative (PID) controllers in industrial systems using event-based dynamic game theory, which enables the PID controllers to self-learn, optimize, and fine-tune themselves. In contrast to conventional self-learning approaches, our proposed framework offers an event-driven control strategy and game-theoretic learning algorithms. The players collaborate with the PID controllers to dynamically adjust their gains in response to set point changes and disturbances. We provide a theoretical analysis showing sound convergence guarantees for the game given suitable stability ranges of the PID controlled loop. We further introduce an automatic boundary detection mechanism, which helps the players to find an optimal initialization of action spaces and significantly reduces the exploration time. The efficacy of this novel methodology is validated through its implementation in the temperature control loop of a printing press machine. Eventually, the outcomes of the proposed intelligent self-tuning PID controllers are highly promising, particularly in terms of reducing overshoot and settling time.
The paper presents a method for automatic constructing a classifier for processed data obtained by decameter coherent scatter radars. Method is based only on the radar data obtained, the results of automatic modeling of radio wave propagation in the ionosphere, and mathematical criteria for estimating the quality of the models. The final classifier is the model trained at data obtained by 12 radars of the SuperDARN and SECIRA networks over two years for each radar. The number of the model coefficients is 2669. For the classification, the model uses both the calculated parameters of radio wave propagation in the model ionosphere and the parameters directly measured by the radar. Calibration of radiowave elevation measurements at each radar was made using meteor trail scattered signals. The analysis showed that the optimal number of classes in the data is 37, of which 25 are frequently observed. The analysis made it possible to choose 14 classes from them, which are confidently separated in other variants of model training. A preliminary interpretation of 10 of them was carried out. The dynamics of observation of various classes and their dependence on the geographical latitude of radars at different levels of solar and geomagnetic activity were presented, it was shown that it does not contradict with known physical mechanisms. The analysis showed that the most important parameters to identify the classes are the shape of the signal ray-tracing trajectory in its second half, the ray-traced scattering height and the Doppler velocity measured by the radar.
Deep State Space Models (SSMs) reignite physics-grounded compute paradigms, as RNNs could natively be embodied into dynamical systems. This calls for dedicated learning algorithms obeying to core physical principles, with efficient techniques to simulate these systems and guide their design. We propose Recurrent Hamiltonian Echo Learning (RHEL), an algorithm which provably computes loss gradients as finite differences of physical trajectories of non-dissipative, Hamiltonian systems. In ML terms, RHEL only requires three "forward passes" irrespective of model size, without explicit Jacobian computation, nor incurring any variance in the gradient estimation. Motivated by the physical realization of our algorithm, we first introduce RHEL in continuous time and demonstrate its formal equivalence with the continuous adjoint state method. To facilitate the simulation of Hamiltonian systems trained by RHEL, we propose a discrete-time version of RHEL which is equivalent to Backpropagation Through Time (BPTT) when applied to a class of recurrent modules which we call Hamiltonian Recurrent Units (HRUs). This setting allows us to demonstrate the scalability of RHEL by generalizing these results to hierarchies of HRUs, which we call Hamiltonian SSMs (HSSMs). We apply RHEL to train HSSMs with linear and nonlinear dynamics on a variety of time-series tasks ranging from mid-range to long-range classification and regression with sequence length reaching $\sim 50k$. We show that RHEL consistently matches the performance of BPTT across all models and tasks. This work opens new doors for the design of scalable, energy-efficient physical systems endowed with self-learning capabilities for sequence modelling.
Autonomous driving promises significant advancements in mobility, road safety and traffic efficiency, yet reinforcement learning and imitation learning face safe-exploration and distribution-shift challenges. Although human-AI collaboration alleviates these issues, it often relies heavily on extensive human intervention, which increases costs and reduces efficiency. This paper develops a confidence-guided human-AI collaboration (C-HAC) strategy to overcome these limitations. First, C-HAC employs a distributional proxy value propagation method within the distributional soft actor-critic (DSAC) framework. By leveraging return distributions to represent human intentions C-HAC achieves rapid and stable learning of human-guided policies with minimal human interaction. Subsequently, a shared control mechanism is activated to integrate the learned human-guided policy with a self-learning policy that maximizes cumulative rewards. This enables the agent to explore independently and continuously enhance its performance beyond human guidance. Finally, a policy confidence evaluation algorithm capitalizes on DSAC's return distribution networks to facilitate dynamic switching between human-guided and self-learning policies via a confidence-based intervention function. This ensures the agent can pursue optimal policies while maintaining safety and performance guarantees. Extensive experiments across diverse driving scenarios reveal that C-HAC significantly outperforms conventional methods in terms of safety, efficiency, and overall performance, achieving state-of-the-art results. The effectiveness of the proposed method is further validated through real-world road tests in complex traffic conditions. The videos and code are available at: https://github.com/lzqw/C-HAC.
The rapid evolution of large language models in natural language processing has substantially elevated their semantic understanding and logical reasoning capabilities. Such proficiencies have been leveraged in autonomous driving systems, contributing to significant improvements in system performance. Models such as OpenAI o1 and DeepSeek-R1, leverage Chain-of-Thought (CoT) reasoning, an advanced cognitive method that simulates human thinking processes, demonstrating remarkable reasoning capabilities in complex tasks. By structuring complex driving scenarios within a systematic reasoning framework, this approach has emerged as a prominent research focus in autonomous driving, substantially improving the system's ability to handle challenging cases. This paper investigates how CoT methods improve the reasoning abilities of autonomous driving models. Based on a comprehensive literature review, we present a systematic analysis of the motivations, methodologies, challenges, and future research directions of CoT in autonomous driving. Furthermore, we propose the insight of combining CoT with self-learning to facilitate self-evolution in driving systems. To ensure the relevance and timeliness of this study, we have compiled a dynamic repository of literature and open-source projects, diligently updated to incorporate forefront developments. The repository is publicly available at https://github.com/cuiyx1720/Awesome-CoT4AD.
Diverse language model responses are crucial for creative generation, open-ended tasks, and self-improvement training. We show that common diversity metrics, and even reward models used for preference optimization, systematically bias models toward shorter outputs, limiting expressiveness. To address this, we introduce Diverse, not Short (Diverse-NS), a length-controlled self-learning framework that improves response diversity while maintaining length parity. By generating and filtering preference data that balances diversity, quality, and length, Diverse-NS enables effective training using only 3,000 preference pairs. Applied to LLaMA-3.1-8B and the Olmo-2 family, Diverse-NS substantially enhances lexical and semantic diversity. We show consistent improvement in diversity with minor reduction or gains in response quality on four creative generation tasks: Divergent Associations, Persona Generation, Alternate Uses, and Creative Writing. Surprisingly, experiments with the Olmo-2 model family (7B, and 13B) show that smaller models like Olmo-2-7B can serve as effective "diversity teachers" for larger models. By explicitly addressing length bias, our method efficiently pushes models toward more diverse and expressive outputs.
Hyperspectral and multispectral image (HSI-MSI) fusion involves combining a low-resolution hyperspectral image (LR-HSI) with a high-resolution multispectral image (HR-MSI) to generate a high-resolution hyperspectral image (HR-HSI). Most deep learning-based methods for HSI-MSI fusion rely on large amounts of hyperspectral data for supervised training, which is often scarce in practical applications. In this paper, we propose a self-learning Adaptive Residual Guided Subspace Diffusion Model (ARGS-Diff), which only utilizes the observed images without any extra training data. Specifically, as the LR-HSI contains spectral information and the HR-MSI contains spatial information, we design two lightweight spectral and spatial diffusion models to separately learn the spectral and spatial distributions from them. Then, we use these two models to reconstruct HR-HSI from two low-dimensional components, i.e, the spectral basis and the reduced coefficient, during the reverse diffusion process. Furthermore, we introduce an Adaptive Residual Guided Module (ARGM), which refines the two components through a residual guided function at each sampling step, thereby stabilizing the sampling process. Extensive experimental results demonstrate that ARGS-Diff outperforms existing state-of-the-art methods in terms of both performance and computational efficiency in the field of HSI-MSI fusion. Code is available at https://github.com/Zhu1116/ARGS-Diff.
While large language models demonstrate impressive performance on static benchmarks, the true potential of large language models as self-learning and reasoning agents in dynamic environments remains unclear. This study systematically evaluates the efficacy of self-reflection, heuristic mutation, and planning as prompting techniques to test the adaptive capabilities of agents. We conduct experiments with various open-source language models in dynamic environments and find that larger models generally outperform smaller ones, but that strategic prompting can close this performance gap. Second, a too-long prompt can negatively impact smaller models on basic reactive tasks, while larger models show more robust behaviour. Third, advanced prompting techniques primarily benefit smaller models on complex games, but offer less improvement for already high-performing large language models. Yet, we find that advanced reasoning methods yield highly variable outcomes: while capable of significantly improving performance when reasoning and decision-making align, they also introduce instability and can lead to big performance drops. Compared to human performance, our findings reveal little evidence of true emergent reasoning. Instead, large language model performance exhibits persistent limitations in crucial areas such as planning, reasoning, and spatial coordination, suggesting that current-generation large language models still suffer fundamental shortcomings that may not be fully overcome through self-reflective prompting alone. Reasoning is a multi-faceted task, and while reasoning methods like Chain of thought improves multi-step reasoning on math word problems, our findings using dynamic benchmarks highlight important shortcomings in general reasoning capabilities, indicating a need to move beyond static benchmarks to capture the complexity of reasoning.
This paper addresses the challenges of resource allocation in vehicular networks enhanced by Intelligent Reflecting Surfaces (IRS), considering the uncertain Channel State Information (CSI) typical of vehicular environments due to the Doppler shift. Leveraging the 3GPP's Mode 1 cellular V2X architecture, our system model facilitates efficient subcarrier usage and interference reduction through coordinated V2I and V2V communications. Each Cellular User Equipment (CUE) shares its spectrum with at most one Vehicular User Equipment (VUE) in a one-to-one reuse pattern. We formulate a joint optimization problem for vehicular transmit power, Multi-User Detection (MUD) matrices, V2V link spectrum reuse, and IRS reflection coefficients in IRS-aided V2X communication with imperfect CSI. To tackle this, a novel robust resource allocation algorithm is developed by first decomposing the problem into manageable sub-problems such as power allocation, MUD matrices optimization and IRS phase shifts, and then using the Block Coordinate Descent (BCD) method to alternately optimize these subproblems for optimal resource allocation. Our contributions include efficient approaches for self-learning based power allocation and phase shift optimization that adapt to CSI uncertainties, significantly enhancing the reliability and efficiency of vehicular communications. Simulation results validate the effectiveness of the proposed solutions in improving the Quality of Service (QoS) and managing the complex interference inherent in dense vehicular networks.
Cloud-based battery management system (BMS) requires accurate terminal voltage measurement data to ensure optimal and safe charging of Lithium-ion batteries. Unfortunately, an adversary can corrupt the battery terminal voltage data as it passes from the local-BMS to the cloud-BMS through the communication network, with the objective of under- or over-charging the battery. To ensure accurate terminal voltage data under such malicious sensor attacks, this paper investigates a Koopman-based secure terminal voltage estimation scheme using a two-stage error-compensated self-learning feedback. During the first stage of error correction, the potential Koopman prediction error is estimated to compensate for the error accumulation due to the linear approximation of Koopman operator. The second stage of error compensation aims to recover the error amassing from the higher-order dynamics of the Lithium-ion batteries missed by the self-learning strategy. Specifically, we have proposed two different methods for this second stage error compensation. First, an interpretable empirical correction strategy has been obtained using the open circuit voltage to state-of-charge mapping for the battery. Second, a Gaussian process regression-based data-driven method has been explored. Finally, we demonstrate the efficacy of the proposed secure estimator using both empirical and data-driven corrections.
This paper introduces a self-learning agent that integrates LLaMA 3.2 with a Progressive Neural Network (PNN) for continual learning in conversational AI and code generation. The framework dynamically collects data, fine-tunes tasks with minimal samples, and leverages Meta-Learning for rapid adaptation. LoRA optimizes fine-tuning, while Elastic Weight Consolidation (EWC) enhances knowledge retention. Experimental results demonstrate improved adaptability and memory stability, positioning this approach as a scalable step toward Artificial General Intelligence (AGI).
Equilibrium Propagation (EP) is a supervised learning algorithm that trains network parameters using local neuronal activity. This is in stark contrast to backpropagation, where updating the parameters of the network requires significant data shuffling. Avoiding data movement makes EP particularly compelling as a learning framework for energy-efficient training on neuromorphic systems. In this work, we assess the ability of EP to learn on hardware that contain physical uncertainties. This is particularly important for researchers concerned with hardware implementations of self-learning systems that utilize EP. Our results demonstrate that deep, multi-layer neural network architectures can be trained successfully using EP in the presence of finite uncertainties, up to a critical limit. This limit is independent of the training dataset, and can be scaled through sampling the network according to the central limit theorem. Additionally, we demonstrate improved model convergence and performance for finite levels of uncertainty on the MNIST, KMNIST and FashionMNIST datasets. Optimal performance is found for networks trained with uncertainties close to the critical limit. Our research supports future work to build self-learning hardware in situ with EP.
Decarbonization of the transport sector sets increasingly strict demands to maximize thermal efficiency and minimize greenhouse gas emissions of Internal Combustion Engines. This has led to complex engines with a surge in the number of corresponding tunable parameters in actuator set points and control settings. Automated calibration is therefore essential to keep development time and costs at acceptable levels. In this work, an innovative self-learning calibration method is presented based on in-cylinder pressure curve shaping. This method combines Principal Component Decomposition with constrained Bayesian Optimization. To realize maximal thermal engine efficiency, the optimization problem aims at minimizing the difference between the actual in-cylinder pressure curve and an Idealized Thermodynamic Cycle. By continuously updating a Gaussian Process Regression model of the pressure's Principal Components weights using measurements of the actual operating conditions, the mean in-cylinder pressure curve as well as its uncertainty bounds are learned. This information drives the optimization of calibration parameters, which are automatically adapted while dealing with the risks and uncertainties associated with operational safety and combustion stability. This data-driven method does not require prior knowledge of the system. The proposed method is successfully demonstrated in simulation using a Reactivity Controlled Compression Ignition engine model. The difference between the Gross Indicated Efficiency of the optimal solution found and the true optimum is 0.017%. For this complex engine, the optimal solution was found after 64.4s, which is relatively fast compared to conventional calibration methods.
Recent progress in (multimodal) large language models ((M)LLMs) has shifted focus from pre-training to inference-time compute scaling and post-training optimization, driven by concerns over limited high-quality real-world data. However, these strategies alone are insufficient for advancing model capabilities. We hypothesize that effective model improvement requires a strong synergy among pre-training, inference-time compute scaling, and post-training optimization. In this paper, we validate this hypothesis in the context of multimodal pre-training for foundation MLLM construction. We introduce Self-Improving cognition (SIcog), a self-learning framework for constructing next-generation foundation MLLMs by imparting multimodal knowledge and enhancing their systematic cognitive capabilities through multimodal pre-training with self-generated data. Specifically, we introduce Chain-of-Description, a step-by-step visual understanding method to improve comprehensive perception, and integrate structured chain-of-thought (CoT) reasoning to support in-depth multimodal reasoning. SIcog first equips a base model with systematic perception and reasoning using minimal external supervision. The enhanced model then generates candidate image captions and CoT-style reasoning responses for unlabeled images and image-question pairs across diverse tasks, which are curated through a self-consistency mechanism. These curated samples are subsequently used for large-scale multimodal pre-training, completing a self-learning cycle that strengthens the model's cognitive foundation. Extensive experiments demonstrate that SIcog produces next-generation foundation MLLMs with substantially improved multimodal cognition, outperforming prevailing pre-training approaches. These findings empirically establish SIcog as a promising framework for realizing a complete self-improving paradigm.
Large reasoning models (LRMs) like OpenAI-o1 and DeepSeek-R1 have demonstrated remarkable capabilities in complex reasoning tasks through the utilization of long Chain-of-thought (CoT). However, these models often suffer from hallucinations and inefficiencies due to their reliance solely on internal reasoning processes. In this paper, we introduce START (Self-Taught Reasoner with Tools), a novel tool-integrated long CoT reasoning LLM that significantly enhances reasoning capabilities by leveraging external tools. Through code execution, START is capable of performing complex computations, self-checking, exploring diverse methods, and self-debugging, thereby addressing the limitations of LRMs. The core innovation of START lies in its self-learning framework, which comprises two key techniques: 1) Hint-infer: We demonstrate that inserting artificially designed hints (e.g., ``Wait, maybe using Python here is a good idea.'') during the inference process of a LRM effectively stimulates its ability to utilize external tools without the need for any demonstration data. Hint-infer can also serve as a simple and effective sequential test-time scaling method; 2) Hint Rejection Sampling Fine-Tuning (Hint-RFT): Hint-RFT combines Hint-infer and RFT by scoring, filtering, and modifying the reasoning trajectories with tool invocation generated by a LRM via Hint-infer, followed by fine-tuning the LRM. Through this framework, we have fine-tuned the QwQ-32B model to achieve START. On PhD-level science QA (GPQA), competition-level math benchmarks (AMC23, AIME24, AIME25), and the competition-level code benchmark (LiveCodeBench), START achieves accuracy rates of 63.6%, 95.0%, 66.7%, 47.1%, and 47.3%, respectively. It significantly outperforms the base QwQ-32B and achieves performance comparable to the state-of-the-art open-weight model R1-Distill-Qwen-32B and the proprietary model o1-Preview.
We develop a self-learning approach for conjecturing of induction predicates on a dataset of 16197 problems derived from the OEIS. These problems are hard for today's SMT and ATP systems because they require a combination of inductive and arithmetical reasoning. Starting from scratch, our approach consists of a feedback loop that iterates between (i) training a neural translator to learn the correspondence between the problems solved so far and the induction predicates useful for them, (ii) using the trained neural system to generate many new induction predicates for the problems, (iii) fast runs of the z3 prover attempting to prove the problems using the generated predicates, (iv) using heuristics such as predicate size and solution speed on the proved problems to choose the best predicates for the next iteration of training. The algorithm discovers on its own many interesting induction predicates, ultimately solving 5565 problems, compared to 2265 problems solved by CVC5, Vampire or Z3 in 60 seconds.
Zero-shot named entity recognition (NER) aims to develop entity recognition systems from unannotated text corpora. This task presents substantial challenges due to minimal human intervention. Recent work has adapted large language models (LLMs) for zero-shot NER by crafting specialized prompt templates. It advances model self-learning abilities by incorporating self-annotated demonstrations. However, two important challenges persist: (i) Correlations between contexts surrounding entities are overlooked, leading to wrong type predictions or entity omissions. (ii) The indiscriminate use of task demonstrations, retrieved through shallow similarity-based strategies, severely misleads LLMs during inference. In this paper, we introduce the cooperative multi-agent system (CMAS), a novel framework for zero-shot NER that uses the collective intelligence of multiple agents to address the challenges outlined above. CMAS has four main agents: (i) a self-annotator, (ii) a type-related feature (TRF) extractor, (iii) a demonstration discriminator, and (iv) an overall predictor. To explicitly capture correlations between contexts surrounding entities, CMAS reformulates NER into two subtasks: recognizing named entities and identifying entity type-related features within the target sentence. To enable controllable utilization of demonstrations, a demonstration discriminator is established to incorporate the self-reflection mechanism, automatically evaluating helpfulness scores for the target sentence. Experimental results show that CMAS significantly improves zero-shot NER performance across six benchmarks, including both domain-specific and general-domain scenarios. Furthermore, CMAS demonstrates its effectiveness in few-shot settings and with various LLM backbones.
Lung cancer is the second most common cancer and the leading cause of cancer-related deaths worldwide. Survival largely depends on tumor stage at diagnosis, and early detection with low-dose CT can significantly reduce mortality in high-risk patients. AI can improve the detection, measurement, and characterization of pulmonary nodules while reducing assessment time. However, the training data, functionality, and performance of available AI systems vary considerably, complicating software selection and regulatory evaluation. Manufacturers must specify intended use and provide test statistics, but they can choose their training and test data, limiting standardization and comparability. Under the EU AI Act, consistent quality assurance is required for AI-based nodule detection, measurement, and characterization. This position paper proposes systematic quality assurance grounded in a validated reference dataset, including real screening cases plus phantom data to verify volume and growth rate measurements. Regular updates shall reflect demographic shifts and technological advances, ensuring ongoing relevance. Consequently, ongoing AI quality assurance is vital. Regulatory challenges are also adressed. While the MDR and the EU AI Act set baseline requirements, they do not adequately address self-learning algorithms or their updates. A standardized, transparent quality assessment - based on sensitivity, specificity, and volumetric accuracy - enables an objective evaluation of each AI solution's strengths and weaknesses. Establishing clear testing criteria and systematically using updated reference data lay the groundwork for comparable performance metrics, informing tenders, guidelines, and recommendations.