Gholamreza Anbarjafari

Akbar Anbar Jafari, Cagri Ozcinar, Gholamreza Anbarjafari

AI systems improve by drawing on more compute, data, energy, and better training methods. This paper asks a precise, testable version of the "runaway growth" question: under what measurable conditions could capability escalate without bound in finite time, and under what conditions can that be ruled out? We develop an analytic framework for recursive self-improvement that links capability growth to resource build-out and deployment policies. Physical and information-theoretic limits from power, bandwidth, and memory define a service envelope that caps instantaneous improvement. An endogenous growth model couples capital to compute, data, and energy and defines a critical boundary separating superlinear from subcritical regimes. We derive decision rules that map observable series (facility power, IO bandwidth, training throughput, benchmark losses, and spending) into yes/no certificates for runaway versus nonsingular behavior. The framework yields falsifiable tests based on how fast improvement accelerates relative to its current level, and it provides safety controls that are directly implementable in practice, such as power caps, throughput throttling, and evaluation gates. Analytical case studies cover capped-power, saturating-data, and investment-amplified settings, illustrating when the envelope binds and when it does not. The approach is simulation-free and grounded in measurements engineers already collect. Limitations include dependence on the chosen capability metric and on regularity diagnostics; future work will address stochastic dynamics, multi-agent competition, and abrupt architectural shifts. Overall, the results replace speculation with testable conditions and deployable controls for certifying or precluding an AI singularity.

Akbar Anbar Jafari, Cagri Ozcinar, Gholamreza Anbarjafari

Modern deep neural networks achieve high predictive accuracy but remain poorly calibrated: their confidence scores do not reliably reflect the true probability of correctness. We propose a quantum-inspired classification head architecture that projects backbone features into a complex-valued Hilbert space and evolves them under a learned unitary transformation parameterised via the Cayley map. Through a controlled hybrid experimental design - training a single shared backbone and comparing lightweight interchangeable heads - we isolate the effect of complex-valued unitary representations on calibration. Our ablation study on CIFAR-10 reveals that the unitary magnitude head (complex features evolved under a Cayley unitary, read out via magnitude and softmax) achieves an Expected Calibration Error (ECE) of 0.0146, representing a 2.4x improvement over a standard softmax head (0.0355) and a 3.5x improvement over temperature scaling (0.0510). Surprisingly, replacing the softmax readout with a Born rule measurement layer - the quantum-mechanically motivated approach - degrades calibration to an ECE of 0.0819. On the CIFAR-10H human-uncertainty benchmark, the wave function head achieves the lowest KL-divergence (0.336) to human soft labels among all compared methods, indicating that complex-valued representations better capture the structure of human perceptual ambiguity. We provide theoretical analysis connecting norm-preserving unitary dynamics to calibration through feature-space geometry, report negative results on out-of-distribution detection and sentiment analysis to delineate the method's scope, and discuss practical implications for safety-critical applications. Code is publicly available.

Akbar Anbar Jafari, Cagri Ozcinar, Gholamreza Anbarjafari

The emergence of LLMs has catalyzed a paradigm shift in autonomous agent development, enabling systems capable of reasoning, planning, and executing complex multi-step tasks. However, existing agent frameworks often suffer from architectural rigidity, vendor lock-in, and prohibitive complexity that impedes rapid prototyping and deployment. This paper presents AgentForge, a lightweight, open-source Python framework designed to democratize the construction of LLM-driven autonomous agents through a principled modular architecture. AgentForge introduces three key innovations: (1) a composable skill abstraction that enables fine-grained task decomposition with formally defined input-output contracts, (2) a unified LLM backend interface supporting seamless switching between cloud-based APIs and local inference engines, and (3) a declarative YAML-based configuration system that separates agent logic from implementation details. We formalize the skill composition mechanism as a directed acyclic graph (DAG) and prove its expressiveness for representing arbitrary sequential and parallel task workflows. Comprehensive experimental evaluation across four benchmark scenarios demonstrates that AgentForge achieves competitive task completion rates while reducing development time by 62% compared to LangChain and 78% compared to direct API integration. Latency measurements confirm sub-100ms orchestration overhead, rendering the framework suitable for real-time applications. The modular design facilitates extension: we demonstrate the integration of six built-in skills and provide comprehensive documentation for custom skill development. AgentForge addresses a critical gap in the LLM agent ecosystem by providing researchers and practitioners with a production-ready foundation for constructing, evaluating, and deploying autonomous agents without sacrificing flexibility or performance.

Akbar Anbar Jafari, Cagri Ozcinar, Gholamreza Anbarjafari

The rapid proliferation of artificial intelligence across organizational contexts has generated profound strategic opportunities while introducing significant ethical and operational risks. Despite growing scholarly attention to responsible AI, extant literature remains fragmented and is often adopting either an optimistic stance emphasizing value creation or an excessively cautious perspective fixated on potential harms. This paper addresses this gap by presenting a comprehensive examination of AI's dual nature through the lens of strategic information systems. Drawing upon a systematic synthesis of the responsible AI literature and grounded in paradox theory, we develop the Paradox-based Responsible AI Governance (PRAIG) framework that articulates: (1) the strategic benefits of AI adoption, (2) the inherent risks and unintended consequences, and (3) governance mechanisms that enable organizations to navigate these tensions. Our framework advances theoretical understanding by conceptualizing responsible AI governance as the dynamic management of paradoxical tensions between value creation and risk mitigation. We provide formal propositions demonstrating that trade-off approaches amplify rather than resolve these tensions, and we develop a taxonomy of paradox management strategies with specified contingency conditions. For practitioners, we offer actionable guidance for developing governance structures that neither stifle innovation nor expose organizations to unacceptable risks. The paper concludes with a research agenda for advancing responsible AI governance scholarship.

Akbar Anbar Jafari, Cagri Ozcinar, Gholamreza Anbarjafari

Contemporary machine learning models, including large language models, exhibit remarkable capabilities in static tasks yet falter in non-stationary environments due to rigid architectures that hinder continual adaptation and lifelong learning. Building upon the nested learning paradigm, which decomposes models into multi-level optimization problems with fixed update frequencies, this work proposes dynamic nested hierarchies as the next evolutionary step in advancing artificial intelligence and machine learning. Dynamic nested hierarchies empower models to autonomously adjust the number of optimization levels, their nesting structures, and update frequencies during training or inference, inspired by neuroplasticity to enable self-evolution without predefined constraints. This innovation addresses the anterograde amnesia in existing models, facilitating true lifelong learning by dynamically compressing context flows and adapting to distribution shifts. Through rigorous mathematical formulations, theoretical proofs of convergence, expressivity bounds, and sublinear regret in varying regimes, alongside empirical demonstrations of superior performance in language modeling, continual learning, and long-context reasoning, dynamic nested hierarchies establish a foundational advancement toward adaptive, general-purpose intelligence.

Akbar Anbar Jafari, Gholamreza Anbarjafari

Contemporary autoregressive transformers operate in open loop: each hidden state is computed in a single forward pass and never revised, causing errors to propagate uncorrected through the sequence. We identify this open-loop bottleneck as a fundamental architectural limitation underlying well-documented failures in long-range reasoning, factual consistency, and multi-step planning. To address this limitation, we introduce the closed-loop prediction principle, which requires that models iteratively refine latent representations until reaching a self-consistent equilibrium before committing to each token. We instantiate this principle as Equilibrium Transformers (EqT), which augment standard transformer layers with an Equilibrium Refinement Module that minimizes a learned energy function via gradient descent in latent space. The energy function enforces bidirectional prediction consistency, episodic memory coherence, and output confidence, all computed without external supervision. Theoretically, we prove that EqT performs approximate MAP inference in a latent energy-based model, establish linear convergence guarantees, and show that refinement improves predictions precisely on hard instances where one-shot inference is suboptimal. The framework unifies deep equilibrium models, diffusion language models, and test-time training as special cases. Preliminary experiments on the binary parity task demonstrate +3.28% average improvement on challenging sequences, with gains reaching +8.07% where standard transformers approach random performance, validating that the benefit of deliberation scales with task difficulty. Just as attention mechanisms resolved the sequential bottleneck of recurrent networks, we propose that closed-loop equilibrium may resolve the commitment bottleneck of open-loop autoregression, representing a foundational step toward language models.

Artem Domnich, Gholamreza Anbarjafari

Rapid development of artificial intelligence (AI) systems amplify many concerns in society. These AI algorithms inherit different biases from humans due to mysterious operational flow and because of that it is becoming adverse in usage. As a result, researchers have started to address the issue by investigating deeper in the direction towards Responsible and Explainable AI. Among variety of applications of AI, facial expression recognition might not be the most important one, yet is considered as a valuable part of human-AI interaction. Evolution of facial expression recognition from the feature based methods to deep learning drastically improve quality of such algorithms. This research work aims to study a gender bias in deep learning methods for facial expression recognition by investigating six distinct neural networks, training them, and further analysed on the presence of bias, according to the three definition of fairness. The main outcomes show which models are gender biased, which are not and how gender of subject affects its emotion recognition. More biased neural networks show bigger accuracy gap in emotion recognition between male and female test sets. Furthermore, this trend keeps for true positive and false positive rates. In addition, due to the nature of the research, we can observe which types of emotions are better classified for men and which for women. Since the topic of biases in facial expression recognition is not well studied, a spectrum of continuation of this research is truly extensive, and may comprise detail analysis of state-of-the-art methods, as well as targeting other biases.

Egils Avots, Klavs Jermakovs, Maie Bachmann et al.

Depression is a public health issue which severely affects one's well being and cause negative social and economic effect for society. To rise awareness of these problems, this publication aims to determine if long lasting effects of depression can be determined from electoencephalographic (EEG) signals. The article contains accuracy comparison for SVM, LDA, NB, kNN and D3 binary classifiers which were trained using linear (relative band powers, APV, SASI) and non-linear (HFD, LZC, DFA) EEG features. The age and gender matched dataset consisted of 10 healthy subjects and 10 subjects with depression diagnosis at some point in their lifetime. Several of the proposed feature selection and classifier combinations reached accuracy of 90% where all models where evaluated using 10-fold cross validation and averaged over 100 repetitions with random sample permutations.

Mohamed Maher, Perseverance Munga Ngoy, Aleksandrs Rebriks et al.

Boosting sales of e-commerce services is guaranteed once users find more matching items to their interests in a short time. Consequently, recommendation systems have become a crucial part of any successful e-commerce services. Although various recommendation techniques could be used in e-commerce, a considerable amount of attention has been drawn to session-based recommendation systems during the recent few years. This growing interest is due to the security concerns in collecting personalized user behavior data, especially after the recent general data protection regulations. In this work, we present a comprehensive evaluation of the state-of-the-art deep learning approaches used in the session-based recommendation. In session-based recommendation, a recommendation system counts on the sequence of events made by a user within the same session to predict and endorse other items that are more likely to correlate with his/her preferences. Our extensive experiments investigate baseline techniques (\textit{e.g.,} nearest neighbors and pattern mining algorithms) and deep learning approaches (\textit{e.g.,} recurrent neural networks, graph neural networks, and attention-based networks). Our evaluations show that advanced neural-based models and session-based nearest neighbor algorithms outperform the baseline techniques in most of the scenarios. However, we found that these models suffer more in case of long sessions when there exists drift in user interests, and when there is no enough data to model different items correctly during training. Our study suggests that using hybrid models of different approaches combined with baseline algorithms could lead to substantial results in session-based recommendations based on dataset characteristics. We also discuss the drawbacks of current session-based recommendation algorithms and further open research directions in this field.

Jun Wan, Chi Lin, Longyin Wen et al.

The ChaLearn large-scale gesture recognition challenge has been run twice in two workshops in conjunction with the International Conference on Pattern Recognition (ICPR) 2016 and International Conference on Computer Vision (ICCV) 2017, attracting more than $200$ teams round the world. This challenge has two tracks, focusing on isolated and continuous gesture recognition, respectively. This paper describes the creation of both benchmark datasets and analyzes the advances in large-scale gesture recognition based on these two datasets. We discuss the challenges of collecting large-scale ground-truth annotations of gesture recognition, and provide a detailed analysis of the current state-of-the-art methods for large-scale isolated and continuous gesture recognition based on RGB-D video sequences. In addition to recognition rate and mean jaccard index (MJI) as evaluation metrics used in our previous challenges, we also introduce the corrected segmentation rate (CSR) metric to evaluate the performance of temporal segmentation for continuous gesture recognition. Furthermore, we propose a bidirectional long short-term memory (Bi-LSTM) baseline method, determining the video division points based on the skeleton points extracted by convolutional pose machine (CPM). Experiments demonstrate that the proposed Bi-LSTM outperforms the state-of-the-art methods with an absolute improvement of $8.1\%$ (from $0.8917$ to $0.9639$) of CSR.

Julio C. S. Jacques Junior, Cagri Ozcinar, Marina Marjanovic et al.

Automatic age estimation from facial images represents an important task in computer vision. This paper analyses the effect of gender, age, ethnic, makeup and expression attributes of faces as sources of bias to improve deep apparent age prediction. Following recent works where it is shown that apparent age labels benefit real age estimation, rather than direct real to real age regression, our main contribution is the integration, in an end-to-end architecture, of face attributes for apparent age prediction with an additional loss for real age regression. Experimental results on the APPA-REAL dataset indicate the proposed network successfully take advantage of the adopted attributes to improve both apparent and real age estimation. Our model outperformed a state-of-the-art architecture proposed to separately address apparent and real age regression. Finally, we present preliminary results and discussion of a proof of concept application using the proposed model to regress the apparent age of an individual based on the gender of an external observer.

Fatemeh Noroozi, Marina Marjanovic, Angelina Njegus et al.

Every speech signal carries implicit information about the emotions, which can be extracted by speech processing methods. In this paper, we propose an algorithm for extracting features that are independent from the spoken language and the classification method to have comparatively good recognition performance on different languages independent from the employed classification methods. The proposed algorithm is composed of three stages. In the first stage, we propose a feature ranking method analyzing the state-of-the-art voice quality features. In the second stage, we propose a method for finding the subset of the common features for each language and classifier. In the third stage, we compare our approach with the recognition rate of the state-of-the-art filter methods. We use three databases with different languages, namely, Polish, Serbian and English. Also three different classifiers, namely, nearest neighbour, support vector machine and gradient descent neural network, are employed. It is shown that our method for selecting the most significant language-independent and method-independent features in many cases outperforms state-of-the-art filter methods.

Meysam Madadi, Egils Avots, Sergio Escalera et al.

A new approach for 2D to 3D garment retexturing is proposed based on Gaussian mixture models and thin plate splines (TPS). An automatically segmented garment of an individual is matched to a new source garment and rendered, resulting in augmented images in which the target garment has been retextured by using the texture of the source garment. We divide the problem into garment boundary matching based on Gaussian mixture models and then interpolate inner points using surface topology extracted through geodesic paths, which leads to a more realistic result than standard approaches. We evaluated and compared our system quantitatively by mean square error (MSE) and qualitatively using the mean opinion score (MOS), showing the benefits of the proposed methodology on our gathered dataset.

Hasan Sait Arslan, Mark Fishel, Gholamreza Anbarjafari

In this paper a doubly attentive transformer machine translation model (DATNMT) is presented in which a doubly-attentive transformer decoder normally joins spatial visual features obtained via pretrained convolutional neural networks, conquering any gap between image captioning and translation. In this framework, the transformer decoder figures out how to take care of source-language words and parts of an image freely by methods for two separate attention components in an Enhanced Multi-Head Attention Layer of doubly attentive transformer, as it generates words in the target language. We find that the proposed model can effectively exploit not just the scarce multimodal machine translation data, but also large general-domain text-only machine translation corpora, or image-text image captioning corpora. The experimental results show that the proposed doubly-attentive transformer-decoder performs better than a single-decoder transformer model, and gives the state-of-the-art results in the English-German multimodal machine translation task.

Morteza Daneshmand, Ahmed Helmi, Egils Avots et al.

This paper provides an overview of 3D scanning methodologies and technologies proposed in the existing scientific and industrial literature. Throughout the paper, various types of the related techniques are reviewed, which consist, mainly, of close-range, aerial, structure-from-motion and terrestrial photogrammetry, and mobile, terrestrial and airborne laser scanning, as well as time-of-flight, structured-light and phase-comparison methods, along with comparative and combinational studies, the latter being intended to help make a clearer distinction on the relevance and reliability of the possible choices. Moreover, outlier detection and surface fitting procedures are discussed concisely, which are necessary post-processing stages.

Fatemeh Noroozi, Ciprian Adrian Corneanu, Dorota Kamińska et al.

Automatic emotion recognition has become a trending research topic in the past decade. While works based on facial expressions or speech abound, recognizing affect from body gestures remains a less explored topic. We present a new comprehensive survey hoping to boost research in the field. We first introduce emotional body gestures as a component of what is commonly known as "body language" and comment general aspects as gender differences and culture dependence. We then define a complete framework for automatic emotional body gesture recognition. We introduce person detection and comment static and dynamic body pose estimation methods both in RGB and 3D. We then comment the recent literature related to representation learning and emotion recognition from images of emotionally expressive gestures. We also discuss multi-modal approaches that combine speech or face with body gestures for improved emotion recognition. While pre-processing methodologies (e.g. human detection and pose estimation) are nowadays mature technologies fully developed for robust large scale analysis, we show that for emotion recognition the quantity of labelled data is scarce, there is no agreement on clearly defined output spaces and the representations are shallow and largely based on naive geometrical representations.

Gholamreza Anbarjafari, Rain Eric Haamer, Iiris Lusi et al.

The use of virtual reality (VR) is exponentially increasing and due to that many researchers has started to work on developing new VR based social media. For this purpose it is important to have an avatar of the users which look like them to be easily generated by the devices which are accessible, such as mobile phone. In this paper, we propose a novel method of recreating a 3D human face model captured with a phone camera image or video data. The method focuses more on model shape than texture in order to make the face recognizable. We detect 68 facial feature points and use them to separate a face into four regions. For each area the best fitting models are found and are further morphed combined to find the best fitting models for each area. These are then combined and further morphed in order to restore the original facial proportions. We also present a method of texturing the resulting model, where the aforementioned feature points are used to generate a texture for the resulting model

Kaustubh Kulkarni, Ciprian Adrian Corneanu, Ikechukwu Ofodile et al.

Humans modify their facial expressions in order to communicate their internal states and sometimes to mislead observers regarding their true emotional states. Evidence in experimental psychology shows that discriminative facial responses are short and subtle. This suggests that such behavior would be easier to distinguish when captured in high resolution at an increased frame rate. We are proposing SASE-FE, the first dataset of facial expressions that are either congruent or incongruent with underlying emotion states. We show that overall the problem of recognizing whether facial movements are expressions of authentic emotions or not can be successfully addressed by learning spatio-temporal representations of the data. For this purpose, we propose a method that aggregates features along fiducial trajectories in a deeply learnt space. Performance of the proposed model shows that on average it is easier to distinguish among genuine facial expressions of emotion than among unfelt facial expressions of emotion and that certain emotion pairs such as contempt and disgust are more difficult to distinguish than the rest. Furthermore, the proposed methodology improves state of the art results on CK+ and OULU-CASIA datasets for video emotion recognition, and achieves competitive results when classifying facial action units on BP4D datase.

Pejman Rasti, Hasan Demirel, Gholamreza Anbarjafari

In this paper, we propose a new super resolution technique based on the interpolation followed by registering them using iterative back projection (IBP). Low resolution images are being interpolated and then the interpolated images are being registered in order to generate a sharper high resolution image. The proposed technique has been tested on Lena, Elaine, Pepper, and Baboon. The quantitative peak signal-to-noise ratio (PSNR) and structural similarity index (SSIM) results as well as the visual results show the superiority of the proposed technique over the conventional and state-of-art image super resolution techniques. For Lena's image, the PSNR is 6.52 dB higher than the bicubic interpolation.

Gholamreza Anbarjafari

In this paper an equalization technique for colour images is introduced. The method is based on nth root and nth power equalization approach but with optimization of the mean of the image in different colour channels such as RGB and HSI. The performance of the proposed method has been measured by the means of peak signal to noise ratio. The proposed algorithm has been compared with conventional histogram equalization and the visual and quantitative experimental results are showing that the proposed method over perform the histogram equalization.

Gholamreza Anbarjafari

In this paper, a high performance face recognition system based on local binary pattern (LBP) using the probability distribution functions (PDF) of pixels in different mutually independent color channels which are robust to frontal homogenous illumination and planer rotation is proposed. The illumination of faces is enhanced by using the state-of-the-art technique which is using discrete wavelet transform (DWT) and singular value decomposition (SVD). After equalization, face images are segmented by use of local Successive Mean Quantization Transform (SMQT) followed by skin color based face detection system. Kullback-Leibler Distance (KLD) between the concatenated PDFs of a given face obtained by LBP and the concatenated PDFs of each face in the database is used as a metric in the recognition process. Various decision fusion techniques have been used in order to improve the recognition rate. The proposed system has been tested on the FERET, HP, and Bosphorus face databases. The proposed system is compared with conventional and thestate-of-the-art techniques. The recognition rates obtained using FVF approach for FERET database is 99.78% compared with 79.60% and 68.80% for conventional gray scale LBP and Principle Component Analysis (PCA) based face recognition techniques respectively.