arXiv subjects

Mohammad Soleymani

Publications and source records attributed to Mohammad Soleymani.

At least 19 recordsLinked to original sources

arXiv2026

Robust Continuous Human Activity Recognition Using Deep Learning and Distributed Radar Sensors

Continuous human activity recognition (HAR) with distributed radar sensor networks is challenging because Doppler signatures depend strongly on aspect angle, the informativeness of individual radar views varies with motion direction, and activity transitions in uninterrupted sequences are often ambiguous. This paper proposes a ConvNeXt-MHSA-BiGRU framework for frame-wise continuous HAR from Doppler-time spectrograms acquired by five spatially distributed radar nodes. A shared ConvNeXt-inspired encoder extracts time-frequency representations from each radar stream, while radar-wise multi-head self attention (MHSA) models inter-node dependencies and adaptively fuses complementary views. RadarDropout and SpecAugment-style time-frequency masking regularize the network against unreliable radar views and local spectrogram perturbations, whereas stacked bidirectional gated recurrent units (BiGRUs) exploit temporal context for frame-wise classification across activity transitions. The framework is evaluated on nine activities performed by 14 participants using leave-one-person-out (L1PO) subject-independent testing with fivefold cross-validation. It achieves a mean L1PO test accuracy of 87.56% across the 14 held-out subjects and improves recognition performance over the published CNN-RNN baseline. The results demonstrate that combining modern spectrogram encoding, adaptive radar view fusion, and bidirectional temporal modeling provides an effective framework for continuous and distributed radar-based HAR.

eess.SP↗

arXiv2026

HairWeaver: Few-Shot Photorealistic Hair Motion Synthesis with Sim-to-Real Guided Video Diffusion

We present HairWeaver, a diffusion-based pipeline that animates a single human image with realistic and expressive hair dynamics. While existing methods successfully control body pose, they lack specific control over hair, and as a result, fail to capture the intricate hair motions, resulting in stiff and unrealistic animations. HairWeaver overcomes this limitation using two specialized modules: a Motion-Context-LoRA to integrate motion conditions and a Style-Alignment-LoRA to preserve the subject's photoreal appearance across different data domains. These lightweight components are designed to guide a video diffusion backbone while maintaining its core generative capabilities. By training on a specialized dataset of dynamic human motion generated from a CG simulator, HairWeaver affords fine control over hair motion and ultimately learns to produce highly realistic hair that responds naturally to movement. Comprehensive evaluations demonstrate that our approach sets a new state of the art, producing lifelike human hair animations with dynamic details.

cs.CV↗

arXiv2026

Do Audio LLMs Listen or Read? Analyzing and Mitigating Paralinguistic Failures with VoxParadox

Audio large language models (Audio LLMs) demonstrate strong performance on speech understanding tasks, yet their ability to understand paralinguistic information remains limited. To systematically quantify this issue, we introduce VoxParadox, an adversarial benchmark with 2,000 verified examples, spanning 10 paralinguistic tasks, created with controlled speech synthesis to intentionally mismatch transcript claims and speaking style, enabling direct measurement of speech paralinguistic understanding. Evaluation of a diverse set of Audio LLMs reveals consistently low accuracy on acoustic ground truth and a strong tendency to follow language-implied (incorrect) answers. To understand the cause of this gap, we perform layer-wise probing and find that (i) paralinguistic cues can degrade in deeper encoder layers and at the encoder--LLM interface, and (ii) even when such cues are available in audio tokens, the language model frequently ignores them. To address these problems, we propose Prompt-Conditioned Layer Mixer (PCLM), which adaptively combines information from multiple audio layers based on the input prompt, and pair it with Direct Preference Optimization (DPO) to explicitly prefer acoustically supported options over language-implied alternatives. These methods substantially improve Audio LLM paralinguistic understanding, improving Audio Flamingo 3 from 17.40% to 65.20% on VoxParadox, and from 37.74% to 54.78% on MMSU paralinguistic subset. Our project page is available at https://voxparadox.github.io/.

cs.SD↗

arXiv2026

The manifold of unitary and symmetric matrices: characterization, Riemannian optimization and application to BD-RIS design

This paper proposes and analyzes Riemannian optimization algorithms on the manifold of unitary and symmetric matrices, denoted ${\cal {U}}_s$, which naturally models the scattering matrices of passive and reciprocal devices such as beyond-diagonal reconfigurable intelligent surfaces (BD-RISs). Despite its relevance, the geometry of ${\cal {U}}_s$ has remained largely unexplored, and existing BD-RIS optimization methods either ignore the symmetry constraint or rely on costly Takagi-based parameterizations. We first provide a rigorous geometric characterization of ${\cal {U}}_s$, deriving its tangent space, a simple retraction, and closed-form expressions for geodesics. Building on these results, we develop two Riemannian manifold optimization (MO) algorithms tailored to ${\cal {U}}_s$: a line-search (LS) based scheme and a phase-optimization (PO) update along geodesics. We then apply the proposed framework to BD-RIS-assisted multiple-input multiple-output (MIMO) links, addressing sum-gain maximization, rate maximization, and minimum mean-square error problems, where they outperform existing approaches. Furthermore, we show that when the number of BD-RIS elements exceeds the total number of antennas, the optimal scattering matrix is low-rank, which motivates and enables efficient low-rank variants of the proposed algorithms.

eess.SP↗

arXiv2026

Optimal symmetric low-rank BD-RIS configuration maximizing the determinant of a MIMO link

Beyond-diagonal reconfigurable intelligent surfaces (BD-RISs) significantly improve wireless performance by allowing tunable interconnections among elements, but their design in multiple-input multiple-output (MIMO) systems has so far relied on complex iterative algorithms or suboptimal approximations. This work introduces a simple yet powerful approach: instead of directly maximizing the achievable rate, we maximize the absolute value of the determinant of the equivalent MIMO channel. We derive a closed-form symmetric unitary scattering matrix whose rank is exactly twice the channel's degrees of freedom ($2r$). Remarkably, this low-rank solution achieves the same determinant value as the optimal unitary BD-RIS. Using log-majorization theory, we prove that the rate loss relative to the optimal unitary BD-RIS vanishes at high signal-to-noise ratio (SNR) or when the number of BD-RIS elements becomes large. Moreover, the proposed solution can be perfectly implemented using a $q$-stem BD-RIS architecture with only $q=2r-1$ stems, requiring a minimum number of reconfigurable circuits. The resulting Max-Det solution is orders of magnitude faster to compute than existing iterative methods while achieving near-optimal rates in practical scenarios. This makes high-performance BD-RIS deployment feasible even with large surfaces and limited computational resources.

eess.SP↗

arXiv2026

MoD-DPO: Towards Mitigating Cross-modal Hallucinations in Omni LLMs using Modality Decoupled Preference Optimization

Omni-modal large language models (omni LLMs) have recently achieved strong performance across audiovisual understanding tasks, yet they remain highly susceptible to cross-modal hallucinations arising from spurious correlations and dominant language priors. In this work, we propose Modality-Decoupled Direct Preference Optimization (MoD-DPO), a simple and effective framework for improving modality grounding in omni LLMs. MoD-DPO introduces modality-aware regularization terms that explicitly enforce invariance to corruptions in irrelevant modalities and sensitivity to perturbations in relevant modalities, thereby reducing unintended cross-modal interactions. To further mitigate over-reliance on textual priors, we incorporate a language-prior debiasing penalty that discourages hallucination-prone text-only responses. Extensive experiments across multiple audiovisual hallucination benchmarks demonstrate that MoD-DPO consistently improves perception accuracy and hallucination resistance, outperforming previous preference optimization baselines under similar training budgets. Our findings underscore the importance of modality-faithful alignment and demonstrate a scalable path toward more reliable and resilient multimodal foundation models.

cs.CV↗

arXiv2026

GDPO-Listener: Expressive Interactive Head Generation via Auto-Regressive Flow Matching and Group reward-Decoupled Policy Optimization

Generating realistic 3D head motion for dyadic interactions is a significant challenge in virtual human synthesis. While recent methods achieve impressive results with speaking heads, they frequently suffer from the `Regression-to-the-Mean' problem in listener motions, collapsing into static faces, and lack the parameter space for complex nonverbal motions. In this paper, we propose GDPO-Listener, a novel framework that achieves highly expressive speaking and listening motion generation. First, we introduce an Auto-Regressive Flow Matching architecture enabling stable supervised learning. Second, to overcome kinematic stillness, we apply the Group reward-Decoupled Policy Optimization (GDPO). By isolating reward normalization across distinct FLAME parameter groups, GDPO explicitly incentivizes high variance expressive generations. Finally, we enable explicit semantic text control for customizable responses. Extensive evaluations across the Seamless Interaction and DualTalk datasets demonstrate superior performance compared to existing baselines on long-term kinematic variance, visual expressivity and semantic controllability.

cs.CV↗

arXiv2026

RIS-Aided RSMA Improves the Latency vs. Energy Trade-off in the Finite Block Length MIMO Downlink

We simultaneously minimize the latency and improve energy efficiency (EE) of the multi-user multiple-input multiple-output (MU-MIMO) rate splitting multiple access (RSMA) downlink, aided by a reconfigurable intelligent surface (RIS). Our results show that RSMA improves the EE and may reduce the delay to 13\% of that of spatial division multiple access (SDMA). Moreover, RIS and RSMA support each other synergistically, while an RIS operating without RSMA provides limited benefits in terms of latency and cannot effectively mitigate interference. {Furthermore, increasing the RIS size amplifies the gains of RSMA more significantly than those of SDMA, without altering the fundamental EE-latency trade-offs.} Results also show that latency increases with more stringent reliability requirements, and RSMA yields more significant gains under such conditions, making it eminently suitable for energy-efficient ultra-reliable low-latency communication (URLLC) scenarios.

eess.SP↗

arXiv2026

AVERE: Improving Audiovisual Emotion Reasoning with Preference Optimization

Emotion understanding is essential for building socially intelligent agents. Although recent multimodal large language models have shown strong performance on this task, two key challenges remain - spurious associations between emotions and irrelevant audiovisual cues, and hallucinations of audiovisual cues driven by text priors in the language model backbone. To quantify and understand these issues, we introduce EmoReAlM, a benchmark designed to evaluate MLLMs for cue-emotion associations, hallucinations and modality agreement. We then propose AVEm-DPO, a preference optimization technique that aligns model responses with both audiovisual inputs and emotion-centric queries. Specifically, we construct preferences over responses exhibiting spurious associations or hallucinations, and audiovisual input pairs guided by textual prompts. We also include a regularization term that penalizes reliance on text priors, thereby mitigating modality-specific cue hallucinations. Experimental results on DFEW, RAVDESS and EMER demonstrate that our method significantly improves the performance of the reference baseline models with 6-19% of relative performance gains in zero-shot settings. By providing both a rigorous benchmark and a robust optimization framework, this work enables principled evaluation and improvement of MLLMs for emotion understanding and social AI. Code, models and benchmark will be released at https://avere-iclr.github.io.

cs.LG↗

arXiv2026

Riemannian optimization on the manifold of unitary and symmetric matrices with application to BD-RIS-assisted systems

In this paper, we rigorously characterize for the first time the manifold of unitary and symmetric matrices, deriving its tangent space and its geodesics. The resulting parameterization of the geodesics (through a real and symmetric matrix) allows us to derive a new Riemannian manifold optimization (MO) algorithm whose most remarkable feature is that it does not need to set any adaptation parameter. We apply the proposed MO algorithm to maximize the achievable rate in a multiple-input multiple-output (MIMO) system assisted by a beyond-diagonal reconfigurable intelligent surface (BD-RIS), illustrating the method's performance through simulations. The MO algorithm achieves a significant reduction in computational cost compared to previous alternatives based on Takagi decomposition, while retaining global convergence to a stationary point of the cost function.

eess.SP↗

arXiv2025

Spectral-Energy Efficiency Tradeoff of Nearly-Passive RIS in MIMO URLLC Downlink: Diagonal vs. Beyond Diagonal

This paper investigates the spectral and energy efficiency (EE) tradeoff of nearly-passive (NP), both locally and globally NP (GNP), reconfigurable intelligent surface (RIS), considering diagonal and beyond-diagonal (BD) implementations in multi-user multiple-input multiple-output (MU-MIMO) broadcast channels designed for ultra-reliable low-latency communication (URLLC). We demonstrate that while all RIS architectures enhance the spectral efficiency, GNP BD-RIS achieves the highest gains. However, its EE is highly sensitive to the static circuit power consumption since BD-RIS has many more circuit elements than diagonal architectures. Furthermore, we demonstrate that the benefits of BD-RIS over diagonal RIS diminish as the number of data streams per user increases due to enhanced channel diversity in MIMO systems.

eess.SP↗

arXiv2025

Discrete Facial Encoding: : A Framework for Data-driven Facial Display Discovery

Facial expression analysis is central to understanding human behavior, yet existing coding systems such as the Facial Action Coding System (FACS) are constrained by limited coverage and costly manual annotation. In this work, we introduce Discrete Facial Encoding (DFE), an unsupervised, data-driven alternative of compact and interpretable dictionary of facial expressions from 3D mesh sequences learned through a Residual Vector Quantized Variational Autoencoder (RVQ-VAE). Our approach first extracts identity-invariant expression features from images using a 3D Morphable Model (3DMM), effectively disentangling factors such as head pose and facial geometry. We then encode these features using an RVQ-VAE, producing a sequence of discrete tokens from a shared codebook, where each token captures a specific, reusable facial deformation pattern that contributes to the overall expression. Through extensive experiments, we demonstrate that Discrete Facial Encoding captures more precise facial behaviors than FACS and other facial encoding alternatives. We evaluate the utility of our representation across three high-level psychological tasks: stress detection, personality prediction, and depression detection. Using a simple Bag-of-Words model built on top of the learned tokens, our system consistently outperforms both FACS-based pipelines and strong image and video representation learning models such as Masked Autoencoders. Further analysis reveals that our representation covers a wider variety of facial displays, highlighting its potential as a scalable and effective alternative to FACS for psychological and affective computing applications.

cs.CV↗

arXiv2025

Social-MAE: A Transformer-Based Multimodal Autoencoder for Face and Voice

Human social behaviors are inherently multimodal necessitating the development of powerful audiovisual models for their perception. In this paper, we present Social-MAE, our pre-trained audiovisual Masked Autoencoder based on an extended version of Contrastive Audio-Visual Masked Auto-Encoder (CAV-MAE), which is pre-trained on audiovisual social data. Specifically, we modify CAV-MAE to receive a larger number of frames as input and pre-train it on a large dataset of human social interaction (VoxCeleb2) in a self-supervised manner. We demonstrate the effectiveness of this model by finetuning and evaluating the model on different social and affective downstream tasks, namely, emotion recognition, laughter detection and apparent personality estimation. The model achieves state-of-the-art results on multimodal emotion recognition and laughter recognition and competitive results for apparent personality estimation, demonstrating the effectiveness of in-domain self-supervised pre-training. Code and model weight are available here https://github.com/HuBohy/SocialMAE.

cs.CV↗

arXiv2025

STAR-RIS-aided RSMA for the URLLC multi-user MIMO Downlink

Rate splitting multiple access (RSMA) is intrinsically amalgamated with simultaneously transmitting and reflecting (STAR) reconfigurable intelligent surfaces (RIS) to enhance energy efficiency (EE) of the finite block length (FBL) multiple-input multiple-output (MIMO) downlink. An alternating optimization-based algorithm is proposed to jointly optimize the transmit beamforming matrices, STAR-RIS configurations, and rate-splitting parameters. STAR-RIS attains 360-degree full-plane coverage, while RSMA provides a prominent gain by efficiently managing interference. Numerical results reveal a strong synergy between RSMA and STAR-RIS, demonstreating significant EE gains over reflective RIS and spatial division multiple access (SDMA).

eess.SP↗

arXiv2025

Rate Splitting Multiple Access for RIS-aided URLLC MIMO Broadcast Channels

The performance of modern wireless communication systems is typically limited by interference. The impact of interference can be even more severe in ultra-reliable and low-latency communication (URLLC) use cases. A powerful tool for managing interference is rate splitting multiple access (RSMA), which encompasses many multiple-access technologies like non-orthogonal multiple access (NOMA), spatial division multiple access (SDMA), and broadcasting. Another effective technology to enhance the performance of URLLC systems and mitigate interference is constituted by reconfigurable intelligent surfaces (RISs). This paper develops RSMA schemes for multi-user multiple-input multiple-output (MIMO) RIS-aided broadcast channels (BCs) based on finite block length (FBL) coding. We show that RSMA and RISs can substantially improve the spectral efficiency (SE) and energy efficiency (EE) of MIMO RIS-aided URLLC systems. Additionally, the gain of employing RSMA and RISs noticeably increases when the reliability and latency constraints are more stringent. Furthermore, RISs impact RSMA differently, depending on the user load. If the system is underloaded, RISs are able to manage the interference sufficiently well, making the gains of RSMA small. However, when the user load is high, RISs and RSMA become synergetic.

eess.SP↗

arXiv2025

A Framework for Fractional Matrix Programming Problems with Applications in FBL MU-MIMO

An efficient framework is conceived for fractional matrix programming (FMP) optimization problems (OPs) namely for minimization and maximization. In each generic OP, either the objective or the constraints are functions of multiple arbitrary continuous-domain fractional functions (FFs). This ensures the framework's versatility, enabling it to solve a broader range of OPs than classical FMP solvers, like Dinkelbach-based algorithms. Specifically, the generalized Dinkelbach algorithm can only solve multiple-ratio FMP problems. By contrast, our framework solves OPs associated with a sum or product of multiple FFs as the objective or constraint functions. Additionally, our framework provides a single-loop solution, while most FMP solvers require twin-loop algorithms. Many popular performance metrics of wireless communications are FFs. For instance, latency has a fractional structure, and minimizing the sum delay leads to an FMP problem. Moreover, the mean square error (MSE) and energy efficiency (EE) metrics have fractional structures. Thus, optimizing EE-related metrics such as the sum or geometric mean of EEs and enhancing the metrics related to spectral-versus-energy-efficiency tradeoff yield FMP problems. Furthermore, both the signal-to-interference-plus-noise ratio and the channel dispersion are FFs. In this paper, we also develop resource allocation schemes for multi-user multiple-input multiple-output (MU-MIMO) systems, using finite block length (FBL) coding, demonstrating attractive practical applications of FMP by optimizing the aforementioned metrics.

eess.SP↗

arXiv2025

MagicPose4D: Crafting Articulated Models with Appearance and Motion Control

With the success of 2D and 3D visual generative models, there is growing interest in generating 4D content. Existing methods primarily rely on text prompts to produce 4D content, but they often fall short of accurately defining complex or rare motions. To address this limitation, we propose MagicPose4D, a novel framework for refined control over both appearance and motion in 4D generation. Unlike current 4D generation methods, MagicPose4D accepts monocular videos or mesh sequences as motion prompts, enabling precise and customizable motion control. MagicPose4D comprises two key modules: (i) Dual-Phase 4D Reconstruction Module, which operates in two phases. The first phase focuses on capturing the model's shape using accurate 2D supervision and less accurate but geometrically informative 3D pseudo-supervision without imposing skeleton constraints. The second phase extracts the 3D motion (skeleton poses) using more accurate pseudo-3D supervision, obtained in the first phase and introduces kinematic chain-based skeleton constraints to ensure physical plausibility. Additionally, we propose a Global-local Chamfer loss that aligns the overall distribution of predicted mesh vertices with the supervision while maintaining part-level alignment without extra annotations. (ii) Cross-category Motion Transfer Module, which leverages the extracted motion from the 4D reconstruction module and uses a kinematic-chain-based skeleton to achieve cross-category motion transfer. It ensures smooth transitions between frames through dynamic rigidity, facilitating robust generalization without additional training. Through extensive experiments, we demonstrate that MagicPose4D significantly improves the accuracy and consistency of 4D content generation, outperforming existing methods in various benchmarks.

cs.CV↗

arXiv2025

Energy Efficiency Optimization of Finite Block Length STAR-RIS-aided MU-MIMO Broadcast Channels

Energy-efficient designs are proposed for multi-user (MU) multiple-input multiple-output (MIMO) broadcast channels (BC), assisted by simultaneously transmitting and reflecting (STAR) reconfigurable intelligent surfaces (RIS) operating at finite block length (FBL). In particular, we maximize the sum energy efficiency (EE), showing that STAR-RIS can substantially enhance it. Our findings demonstrate that the gains of employing STAR-RIS increase when the codeword length and the maximum tolerable bit error rate decrease, meaning that a STAR-RIS is more energy efficient in a system with more stringent latency and reliability requirements.

eess.SP↗