arXiv subjects

Abbas Edalat

Publications and source records attributed to Abbas Edalat.

At least 19 recordsLinked to original sources

arXiv2026

MultiHuSE: A Multimodal Dataset for Humour Styles and Emotions

Computational recognition of verbal humour remains a challenging task, requiring an understanding of language, delivery style, emotions, and cultural context. Most existing approaches focus on binary classification and lack datasets that capture psychological dimensions of humour alongside variations in expression. We introduce MultiHuSE, a multimodal dataset comprising 2,407 high-definition videos of 50 demographically diverse actors performing 1,463 text samples across four psychological humour styles (affiliative, aggressive, self-enhancing, and self-deprecating), as well as neutral content. A subset is additionally annotated for underlying emotions. The dataset uniquely captures multiple actor interpretations of the same texts, enabling systematic analysis of expressive diversity. Baseline experiments show that multimodal fusion outperforms unimodal approaches (80.1% vs. 77.4% accuracy) in humour style classification, with particularly strong gains for affiliative humour (66% to 74%). While text provides the strongest individual signal, fusion models deliver meaningful improvements. We hope that MultiHuSE provides empirical support for psychological theories linking humour and emotion, while also opening new avenues for research in human communication, well-being, and AI-driven interaction. The dataset is available for academic use under an End-User Licence Agreement.

cs.CL↗

arXiv2026

Mitigating Strong-Modality Collapse in Multimodal Learning via Inverted Asymmetric Fusion

Fusing multiple modalities is expected to improve model performance. However, on the MultiHuSE dataset, early, late, and symmetric attention fusion often fail to outperform the best unimodal baseline (text). Pathway isolation of a symmetric attention fusion model reveals that the text-pathway accuracy drops from 74.9% to 56.4% after fusion in one such setting, indicating that the dominant modality can be degraded during integration. We term this strong-modality collapse and argue that it helps explain why some multimodal models fail to surpass unimodal baselines. We propose Inverted Asymmetric Fusion (IAF), which avoids forcing mutual attention across modalities. The dominant modality is preserved by passing through fusion unchanged, while weaker modalities attend to it as a contextual anchor. Before fusion, weaker modalities are strengthened using Modality-Aware Knowledge Distillation. We evaluate IAF on three benchmarks with different modality hierarchies: text-dominant datasets (MultiHuSE, UR-FUNNY) and an audio-visual-dominant dataset (MUStARD). Pathway isolation shows that IAF preserves the dominant modality's internal accuracy at its unimodal ceiling across all tested configurations, whereas symmetric fusion degrades it by up to 18.5% on MultiHuSE. IAF improves over the strongest unimodal baseline by up to 8.25%.

cs.LG↗

arXiv2026

Embodied Empathy: A Multimodal AR and LLM-Powered System for Self-Attachment Psychotherapy with Self-Initiated Humour

The growing global demand for mental health support increasingly exceeds the supply of qualified practitioners, creating an urgent need for scalable digital interventions that can deliver meaningful emotional connection. In response, we present a novel multimodal application that operationalises the Self-Initiated Humour Protocol (SIHP) within a Self-Attachment Technique (SAT) framework. Our mobile application integrates customisable 3D childhood avatars, augmented reality, and an LLM-driven virtual therapist capable of automated emotion mirroring. An eight-day user study (N=16) indicates the system's feasibility and improvements in self-reported mood. Results show that personalised avatars and text-to-speech output strengthen emotional bonding and perceived empathy. Although emotion mirroring boosts engagement, its effectiveness depends heavily on classification accuracy and animation intensity. Moreover, findings indicate a shift in user expectations--from reactive chatbots to proactive conversational facilitators. We conclude with design implications for leveraging AI and AR to cultivate embodied empathy in digital mental health tools.

cs.HC↗

arXiv2026

Finite-Precision Algebraic Quantum Field Theory: Quantum Parcels, Locality, Modular Structure and Factors

We develop Interval Algebraic Quantum Field Theory (IAQFT), a finite-precision operational formulation of algebraic quantum field theory (AQFT). Physical experiments provide only finitely many observations at finite resolution and therefore determine regions of compatible states rather than uniquely specified point states. IAQFT represents this information by quantum parcels---non-empty convex weak$^*$ open regions of state space---with observational parcels determined by finitely many finite-precision expectation constraints. Exact AQFT states remain indispensable mathematical objects and are recovered under appropriate parcel refinement. We establish reduction to exact states, measurement update and no-signalling, and formulate locality through compatible parcel nets. In finite dimensions an exact Jacobian formula for invertible L\"uders updates gives a volume-contraction criterion. Spacelike vacuum correlations and strict CHSH violations persist throughout sufficiently small observational parcels. Reeh--Schlieder cyclicity becomes finite-precision local reachability, while parcel equivalence of vacuum refinements implies vacuum GNS equivalence and hence does not evade Haag-type obstructions. Tomita--Takesaki modular automorphisms act on parcels, measurement update is modularly covariant, and modular conjugation induces a duality between normal parcels of an algebra and its commutant. State-dependent modular correlations are continuous under predual-norm variation of faithful normal states; shrinking parcels with vanishing KMS defect recover a KMS state. Bisognano--Wichmann yields a parcel formulation of the Unruh effect, recovering the exact KMS relation and Unruh temperature under refinement. Finally, limiting projection faces and their conjugation actions recover the Murray--von Neumann factor classification.

quant-ph↗

arXiv2026

Quantum Ergodicity and Thermalization in Interval Quantum Mechanics

We combine Reimann's spectral typicality theorem -- a modern formulation of quantum ergodicity -- with the framework of Interval Quantum Mechanics (IQM). In IQM, quantum states are represented not by points but by \emph{quantum parcels}: weak open convex sets of density matrices defined by finitely many expectation intervals. Such parcels are the exact mathematical representation of the epistemic knowledge obtained from finite-precision measurements of macroscopic observables. We prove that for a single parcel in which every state has large effective dimension (a condition that ensures thermalization), the expectation interval of any bounded observable becomes concentrated around the microcanonical value for most late times. The asymptotic bound depends only on the minimal effective dimension within the parcel, not on its detailed shape. For a double parcel $(O_1,O_2)$ with both components contained in an energy shell, separated by a conserved quantity $Q^*$ that is supported on the range of the measurement projector, we show that the expectation intervals of both parcels become concentrated near the microcanonical values of bounded observables, the separation is preserved exactly, and the updated double parcel after a fuzzy measurement remains valid.

quant-ph↗

arXiv2026

Finite-Precision Quantum Mechanics: Quantum Parcels, Information and Geometry

Quantum mechanics represents states by exactly specified density operators, whereas experimentally available information is necessarily finite in precision. We develop \emph{Interval Quantum Mechanics (IQM)}, in which finite observational information is represented by a \emph{quantum parcel}, a convex open set of density operators. Experimental parcels are determined by finitely many expectation intervals and form a basis for the state-space topology. A single parcel represents the states compatible with the available information, while a double parcel $(O_1,O_2)$ consists of disjoint possible and excluded regions. Exact point states are recovered as ideal limits of successive parcel refinement. Unitary dynamics lifts to a reversible evolution of parcels. Finite-resolution measurements are represented by fuzzy POVMs and Kraus updates; single parcels are preserved, while double-parcel updates are order-compatible whenever they remain double parcels. We give a useful sufficient condition for such preservation, together with examples showing it is not necessary. Under suitable conditions measurement contracts ambient Hilbert--Schmidt volume and strictly increases the associated geometric information. This contrasts with von Neumann entropy, which can remain unchanged under a selective measurement even though information has been gained. In this formulation, several familiar foundational paradoxes no longer arise in standard form. Wave--particle duality becomes a continuous suppression of interference as which-path resolution increases. Schr\"odinger's cat is described by a finite parcel updated toward the observed outcome sector, rather than an exact superposition undergoing abrupt collapse. Entanglement remains genuinely nonclassical: CHSH violation persists throughout an open parcel around a Bell state.

quant-ph↗

arXiv2026

MoCoTalk: Multi-Conditional Diffusion with Adaptive Router for Controllable Talking Head Generation

Talking-head generation requires joint modeling of identity, head pose, facial expression, and mouth dynamics. Existing methods typically address only a subset of these factors, and rely on fixed-weight or heuristic fusion when multiple conditions are involved. We present MoCoTalk, a multi-conditional video diffusion framework that unifies four complementary control signals: a reference image, facial keypoints, 3DMM-rendered shading meshes, and the corresponding speech audio. To resolve destructive interference among heterogeneous conditions, we introduce an Adaptive Multi-Condition Router that computes channel-wise, timestep-aware gating over the four condition streams, allowing the fusion strategy to vary with both feature subspace and noise level. To better capture speech-related facial dynamics, we design a Mouth-Augmented Shading Mesh, a 3DMM-based representation that decouples head motion, mouth motion, expression, and lighting. This design provides a temporally consistent geometric prior and allows flexible recombination of these attributes at inference. We further introduce a lip consistency loss to tighten audio-visual alignment. Extensive experiments show that MoCoTalk achieves state-of-the-art performance on the majority of structural, motion, and perceptual metrics, while offering attribute-level controllability that single-condition methods do not provide.

cs.CV↗

arXiv2026

A Domain-Theoretic Foundation for Imprecise Probability and Credal Sets

We develop a domain-theoretic framework for imprecise probability reasoning and inference on general topological spaces with a countably based continuous lattice of open sets. We address two distinct forms of uncertainty: partial or incomplete event descriptions, and sets of probability distributions as represented by credal sets -- as well as their combination. Within this framework, we construct a theory of conditional probability and derive novel inference rules for performing Bayesian updating in the presence of these two complementary types of imprecision. These results are extended to a theory of conditional independence for imprecise probabilistic events. We also formulate logical predicates for conditional probability, Bayesian updating, and conditional independence, and we obtain the relevant soundness and completeness results. A key contribution is the construction of a Scott-continuous mapping from any credal set to the domain of intervals, providing a domain-theoretic realisation of classical results from capacity theory and Choquet integration. Finally, we introduce and study a new family of credal sets generated by iterated function systems with imprecise probability weights, broadening the scope of computationally tractable imprecise probabilistic models. The resulting computable framework unifies logical, topological, and measure-theoretic perspectives on uncertainty, supporting robust probabilistic inference under partial and set-valued information.

cs.LO↗

arXiv2026

Structure Matters: Evaluating Multi-Agents Orchestration in Generative Therapeutic Chatbots

While large language models (LLMs) excel at open-ended dialogue, effective psychotherapy requires structured progression and adherence to clinical protocols, making the design of psychotherapist chatbots challenging. We investigate how different LLM-based designs shape perceived therapeutic dialogue in a chatbot grounded in the Self-Attachment Technique (SAT), a novel self-administered psychotherapy rooted in attachment theory. We compare three architectural variants: (1) a multi-agent system utilizing finite state machine aligned with therapeutic stages and a shared long-term memory, (2) a single-agent using identical knowledge-base and the same prompts, and (3) an unguided LLM. In an eight-day randomized controlled trial (RCT) with N=66 Farsi-speaking participants, balanced across the three chatbots, the multi-agent system is perceived as significantly more natural and human-like than the other variants and achieves higher ratings across most other metrics. These findings demonstrate that for therapeutic AI, architectural orchestration is as critical as prompt engineering in fostering natural, engaging dialogue.

cs.HC↗

arXiv2025

A generalisation of Henstock-Kurzweil integral to compact metric spaces

We introduce the notion of a gauge and of a tagged partition (subordinate to a given gauge) by intersections of open and closed sets of a compact metric space extending the corresponding notions in Henstock-Kurzweil integration of real-valued functions with respect to the Lebesgue measure on the unit interval. We show that, for the integration of bounded functions with respect to a normalised Borel measure $\mu$ on a compact metric space, the notion of a gauge and an associated tagged partition, arise naturally from a normalised simple valuation way-below the Borel measure. Then we consider the integration of unbounded functions with respect to a normalised Borel measure on a compact metric space, for which the Lebesgue integral may fail to exist. A pair of a tagged partition and a gauge defines a simple valuation and we introduce a partial order on these pairs, emulating the partial order of simple valuations in the probabilistic power domain. We define the $D_\mu$-integral of a real-valued function with respect to a Borel measure using the limit of the net of the integrals of the simple valuations induced by pairs of tagged partitions and gauges for the function. The $D_\mu$-integral of functions on a compact metric space with respect to a normalised Borel measure satisfies the basic properties of an integral and generalises the Henstock-Kurzweil integral. We show that when the Lebesgue integral of the function exists then the $D_\mu$-integral also exists and they have the same value. We provide a family of real-valued functions on the Cantor space that are $D_\mu$-integrable but not Lebesgue integrable.

math.FA↗

arXiv2025

A domain-theoretic framework for conditional probability and Bayesian updating in programming

We present a domain-theoretic framework for probabilistic programming that provides a constructive definition of conditional probability and addresses computability challenges previously identified in the literature. We introduce a novel approach based on an observable notion of events that enables computability. We examine two methods for computing conditional probabilities -- one using conditional density functions and another using trace sampling with rejection -- and prove they yield consistent results within our framework. We implement these ideas in a simple probabilistic functional language with primitives for sampling and evaluation, providing both operational and denotational semantics and proving their consistency. Our work provides a rigorous foundation for implementing conditional probability in probabilistic programming languages.

cs.LO↗

arXiv2025

Explaining Humour Style Classifications: An XAI Approach to Understanding Computational Humour Analysis

Humour styles can have either a negative or a positive impact on well-being. Given the importance of these styles to mental health, significant research has been conducted on their automatic identification. However, the automated machine learning models used for this purpose are black boxes, making their prediction decisions opaque. Clarity and transparency are vital in the field of mental health. This paper presents an explainable AI (XAI) framework for understanding humour style classification, building upon previous work in computational humour analysis. Using the best-performing single model (ALI+XGBoost) from prior research, we apply comprehensive XAI techniques to analyse how linguistic, emotional, and semantic features contribute to humour style classification decisions. Our analysis reveals distinct patterns in how different humour styles are characterised and misclassified, with particular emphasis on the challenges in distinguishing affiliative humour from other styles. Through detailed examination of feature importance, error patterns, and misclassification cases, we identify key factors influencing model decisions, including emotional ambiguity, context misinterpretation, and target identification. The framework demonstrates significant utility in understanding model behaviour, achieving interpretable insights into the complex interplay of features that define different humour styles. Our findings contribute to both the theoretical understanding of computational humour analysis and practical applications in mental health, content moderation, and digital humanities research.

cs.CL↗

arXiv2024

A Two-Model Approach for Humour Style Recognition

Humour, a fundamental aspect of human communication, manifests itself in various styles that significantly impact social interactions and mental health. Recognising different humour styles poses challenges due to the lack of established datasets and machine learning (ML) models. To address this gap, we present a new text dataset for humour style recognition, comprising 1463 instances across four styles (self-enhancing, self-deprecating, affiliative, and aggressive) and non-humorous text, with lengths ranging from 4 to 229 words. Our research employs various computational methods, including classic machine learning classifiers, text embedding models, and DistilBERT, to establish baseline performance. Additionally, we propose a two-model approach to enhance humour style recognition, particularly in distinguishing between affiliative and aggressive styles. Our method demonstrates an 11.61% improvement in f1-score for affiliative humour classification, with consistent improvements in the 14 models tested. Our findings contribute to the computational analysis of humour in text, offering new tools for studying humour in literature, social media, and other textual sources.

cs.CL↗

arXiv2024

Exploring Description-Augmented Dataless Intent Classification

In this work, we introduce several schemes to leverage description-augmented embedding similarity for dataless intent classification using current state-of-the-art (SOTA) text embedding models. We report results of our methods on four commonly used intent classification datasets and compare against previous works of a similar nature. Our work shows promising results for dataless classification scaling to a large number of unseen intents. We show competitive results and significant improvements (+6.12\% Avg.) over strong zero-shot baselines, all without training on labelled or task-specific data. Furthermore, we provide qualitative error analysis of the shortfalls of this methodology to help guide future research in this area.

cs.CL↗

arXiv2024

A Cartesian Closed Category for Random Variables

We present a novel, yet rather simple construction within the traditional framework of Scott domains to provide semantics to probabilistic programming, thus obtaining a solution to a long-standing open problem in this area. Unlike current main approaches that employ some probability measures or continuous valuations on non-standard or rather complex structures, we use the Scott domain of random variables from a standard sample space -- the unit interval or the Cantor space -- to any given Scott domain. The map taking any such random variable to its corresponding probability distribution provides an effectively given, Scott continuous surjection onto the probabilistic power domain of the underlying Scott domain, establishing a new basic result in classical domain theory. We obtain a Cartesian closed category by enriching the category of Scott domains to capture the equivalence of random variables on these domains. The construction of the domain of random variables on this enriched category forms a strong commutative monad, which is suitable for defining the semantics of probabilistic programming.

cs.PL↗

arXiv2024

Systematic Literature Review: Computational Approaches for Humour Style Classification

Understanding various humour styles is essential for comprehending the multifaceted nature of humour and its impact on fields such as psychology and artificial intelligence. This understanding has revealed that humour, depending on the style employed, can either have therapeutic or detrimental effects on an individual's health and relationships. Although studies dedicated exclusively to computational-based humour style analysis remain somewhat rare, an expansive body of research thrives within related task, particularly binary humour and sarcasm recognition. In this systematic literature review (SLR), we survey the landscape of computational techniques applied to these related tasks and also uncover their fundamental relevance to humour style analysis. Through this study, we unveil common approaches, illuminate various datasets and evaluation metrics, and effectively navigate the complex terrain of humour research. Our efforts determine potential research gaps and outlined promising directions. Furthermore, the SLR identifies a range of features and computational models that can seamlessly transition from related tasks like binary humour and sarcasm detection to invigorate humour style classification. These features encompass incongruity, sentiment and polarity analysis, ambiguity detection, acoustic nuances, visual cues, contextual insights, and more. The computational models that emerge contain traditional machine learning paradigms, neural network architectures, transformer-based models, and specialised models attuned to the nuances of humour. Finally, the SLR provides access to existing datasets related to humour and sarcasm, facilitating the work of future researchers.

cs.CL↗

arXiv2023

A Multilingual Virtual Guide for Self-Attachment Technique

In this work, we propose a computational framework that leverages existing out-of-language data to create a conversational agent for the delivery of Self-Attachment Technique (SAT) in Mandarin. Our framework does not require large-scale human translations, yet it achieves a comparable performance whilst also maintaining safety and reliability. We propose two different methods of augmenting available response data through empathetic rewriting. We evaluate our chatbot against a previous, English-only SAT chatbot through non-clinical human trials (N=42), each lasting five days, and quantitatively show that we are able to attain a comparable level of performance to the English SAT chatbot. We provide qualitative analysis on the limitations of our study and suggestions with the aim of guiding future improvements.

cs.CL↗

arXiv2023

Pure Bayesian Nash equilibrium for Bayesian games with multidimensional vector Types and linear payoffs

We study $n$-agent Bayesian Games with $m$-dimensional vector types and linear payoffs, also called Linear Multidimensional Bayesian Games. This class of games is equivalent with $n$-agent, $m$-game Uniform Multigames. We distinguish between games that have a discrete type space and those with a continuous type space. More specifically, we are interested in the existence of pure Bayesian Nash Equilibrium for such games and efficient algorithms to find them. For continuous priors we suggest a methodology to perform Nash Equilibrium search in simple cases. For discrete priors we present algorithms that can handle two actions and two players games efficiently. We introduce the core concept of threshold strategy and, under some mild conditions, we show that these games have at least one pure Bayesian Nash Equilibrium. We illustrate our results with several examples like Double Game Prisoner Dilemna (DGPD), Chicken Game and Sustainable Adoption Decision Problem (SADP).

cs.GT↗