arXiv subjects

Babak Khalaj

Publications and source records attributed to Babak Khalaj.

8 recordsLinked to original sources

arXiv2026

KG-FairDiff: Knowledge Graph-Guided Prompt Refinement for Demographically Fair Text-to-Image Generation

Text-to-Image (TTI) systems are now everyday infrastructure for journalism, education, advertising, and public communication, and the demographic and cultural stereotypes they inherit from training data (rendering women, people of colour, older adults, and non-Western cultures as under-represented or caricatured) become a population-level harm at deployment scale. Existing mitigations either require costly retraining, infeasible for the closed-source backbones that dominate consumer products, or rely on fixed demographic templates that ignore cultural context. We present KG-FairDiff, a model-agnostic, inference-time framework that formalises fairness-aware prompt refinement as a constrained optimisation problem and operationalises it as a closed-loop pipeline: a knowledge graph of ~1,200 culture- and bias-related triples retrieves structured context, an LLM rewriter proposes refinements, and a validator accepts only prompts that reduce a divergence-based fairness loss while preserving semantic fidelity to the user's original intent. We prove a finite-termination bound for the refinement loop, contribute a mathematically consistent evaluation suite linking Bias-P/Bias-W to divergence from target distributions and ENS to KL divergence, and audit eight widely-deployed backbone generators. KG-FairDiff substantially reduces gender, race, age, and intersectional disparities while preserving prompt semantics, offering a practical, deployment-ready route to more equitable generative AI.

cs.CV↗

arXiv2026

MALLVI: A Multi-Agent Framework for Integrated Generalized Robotics Manipulation

Task planning for robotic manipulation with large language models (LLMs) is an emerging area. Prior approaches rely on specialized models, fine tuning, or prompt tuning, and often operate in an open loop manner without robust environmental feedback, making them fragile in dynamic settings. MALLVI presents a Multi Agent Large Language and Vision framework that enables closed-loop feedback driven robotic manipulation. Given a natural language instruction and an image of the environment, MALLVI generates executable atomic actions for a robot manipulator. After action execution, a Vision Language Model (VLM) evaluates environmental feedback and decides whether to repeat the process or proceed to the next step. Rather than using a single model, MALLVI coordinates specialized agents, Decomposer, Localizer, Thinker, and Reflector, to manage perception, localization, reasoning, and high level planning. An optional Descriptor agent provides visual memory of the initial state. The Reflector supports targeted error detection and recovery by reactivating only relevant agents, avoiding full replanning. Experiments in simulation and real-world settings show that iterative closed loop multi agent coordination improves generalization and increases success rates in zero shot manipulation tasks. Code available at https://github.com/iman1234ahmadi/MALLVI .

cs.RO↗

arXiv2025

DrugRAG: Enhancing Pharmacy LLM Performance Through A Novel Retrieval-Augmented Generation Pipeline

In our study, we evaluated large language model (LLM) performance on pharmacy licensure-style question-answering tasks and developed an external knowledge integration method to improve accuracy. We benchmarked ten LLMs with varying parameter sizes (8 billion to 70+ billion) using a 141-question pharmacy dataset, measuring baseline accuracy without modification. Baseline performance ranged from 46% to 92%, with GPT-5 (92%) and o3 (89%) achieving the highest scores, while smaller open-source models showed substantially lower performance. We then developed DrugRAG, a three-step retrieval-augmented generation (RAG) pipeline that retrieves structured, evidence-based drug information and augments model prompts with contextual pharmacological evidence, operating externally and requiring no changes to model architecture or parameters. DrugRAG increased accuracy across all five evaluated models, with gains ranging from 7 to 21 percentage points (e.g., Gemma 3 27B: 61.0% to 71%, Llama 3.1 8B: 46% to 67%). McNemar analyses demonstrated statistically significant paired improvements primarily in smaller and mid-sized open-source models. These findings demonstrate that integrating structured external drug knowledge via DrugRAG can improve LLM performance on pharmacy-focused question-answering tasks without modifying the underlying models, providing a practical pipeline for enhancing evidence-based pharmacy-focused AI applications.

cs.CL↗

arXiv2025

SkinMap: Weighted Full-Body Skin Segmentation for Robust Remote Photoplethysmography

Remote photoplethysmography (rPPG) is an innovative method for monitoring heart rate and vital signs by using a simple camera to record a person, as long as any part of their skin is visible. This low-cost, contactless approach helps in remote patient monitoring, emotion analysis, smart vehicle utilization, and more. Over the years, various techniques have been proposed to improve the accuracy of this technology, especially given its sensitivity to lighting and movement. In the unsupervised pipeline, it is necessary to first select skin regions from the video to extract the rPPG signal from the skin color changes. We introduce a novel skin segmentation technique that prioritizes skin regions to enhance the quality of the extracted signal. It can detect areas of skin all over the body, making it more resistant to movement, while removing areas such as the mouth, eyes, and hair that may cause interference. Our model is evaluated on publicly available datasets, and we also present a new dataset, called SYNC-rPPG, to better represent real-world conditions. The results indicate that our model demonstrates a prior ability to capture heartbeats in challenging conditions, such as talking and head rotation, and maintain the mean absolute error (MAE) between predicted and actual heart rates, while other methods fail to do so. In addition, we demonstrate high accuracy in detecting a diverse range of skin tones, making this technique a promising option for real-world applications.

cs.CV↗

arXiv2025

MACS: Measurement-Aware Consistency Sampling for Inverse Problems

Diffusion models have emerged as powerful generative priors for solving inverse imaging problems. However, their practical deployment is hindered by the substantial computational cost of slow, multi-step sampling. Although Consistency Models (CMs) address this limitation by enabling high-quality generation in only one or a few steps, their direct application to inverse problems has remained largely unexplored. This paper introduces a modified consistency sampling framework specifically designed for inverse problems. The proposed approach regulates the sampler's stochasticity through a measurement-consistency mechanism that leverages the degradation operator, thereby enforcing fidelity to the observed data while preserving the computational efficiency of consistency-based generation. Comprehensive experiments on the Fashion-MNIST and LSUN Bedroom datasets demonstrate consistent improvements across both perceptual and pixel-level metrics, including the Fr\'echet Inception Distance (FID), Kernel Inception Distance (KID), peak signal-to-noise ratio (PSNR), and structural similarity index measure (SSIM), compared with baseline consistency and diffusion-based sampling methods. The proposed method achieves competitive or superior reconstruction quality with only a small number of sampling steps.

eess.IV↗

arXiv2025

CORE-3D: Context-aware Open-vocabulary Retrieval by Embeddings in 3D

Object retrieval from a scene has become a new trend of research due to its numerous applications. Recent approaches achieve zero-shot, open-vocabulary 3D semantic mapping by assigning embedding vectors to 2D class-agnostic masks generated via vision-language models (VLMs) and projecting these into 3D. However, these methods often produce fragmented masks and inaccurate semantic assignments due to the direct use of raw masks, limiting their effectiveness in complex environments. To address this, we leverage SemanticSAM with progressive granularity refinement to generate more accurate and numerous object-level masks, mitigating the over-segmentation commonly observed in mask generation models such as vanilla SAM, and improving downstream 3D semantic segmentation. To further enhance semantic context, we employ a context-aware CLIP encoding strategy that integrates multiple contextual views of each mask using empirically determined weighting, providing much richer visual context. We evaluate our approach on multiple 3D scene understanding tasks, including 3D semantic segmentation and object retrieval from language queries, across several benchmark datasets. Experimental results demonstrate significant improvements over existing methods, highlighting the effectiveness of our approach.

cs.CV↗

arXiv2020

Multi-antenna Interference Management for Coded Caching

A multi-antenna broadcast channel scenario is considered where a base station delivers contents to cache-enabled user terminals. A joint design of coded caching (CC) and multigroup multicast beamforming is proposed to benefit from spatial multiplexing gain, improved interference management and the global CC gain, simultaneously. The developed general content delivery strategies utilize the multiantenna multicasting opportunities provided by the CC technique while optimally balancing the detrimental impact of both noise and inter-stream interference from coded messages transmitted in parallel. Flexible resource allocation schemes for CC are introduced where the multicast beamformer design and the receiver complexity are controlled by varying the size of the subset of users served during a given time interval, and the overlap among the multicast messages transmitted in parallel, indicated by parameters $α$ and $β$, respectively. Degrees of freedom (DoF) analysis is provided showing that the DoF only depends on $α$ while it is independent of $β$. The proposed schemes are shown to provide the same degrees-of-freedom at high signal-to-noise ratio (SNR) as the state-of-art methods and, in general, to perform significantly better, especially in the finite SNR regime, than several baseline schemes.

cs.IT↗

arXiv2019

D2D Assisted Beamforming for Coded Caching

Device-to-device (D2D) aided beamforming for coded caching is considered in finite signal-to-noise ratio regime. A novel beamforming scheme is proposed where the local cache content exchange among nearby users is exploited. The transmission is split into two phases: local D2D content exchange and downlink transmission. In the D2D phase, users can autonomously share content with the adjacent users. The downlink phase utilizes multicast beamforming to simultaneously serve all users to fulfill the remaining content requests. We first explain the main procedure via two simple examples and then present the general formulation. Furthermore, D2D transmission scenarios and conditions useful for minimizing the overall delivery time are identified. We also investigate the benefits of using D2D transmission for decreasing the transceiver complexity of multicast beamforming. By exploiting the direct D2D exchange of file fragments, the common multicasting rate for delivering the remaining file fragments in the downlink phase is increased providing greatly enhanced overall content delivery performance.

cs.IT↗