arXiv subjects

Maziyar Baran Pouyan

Publications and source records attributed to Maziyar Baran Pouyan.

4 recordsLinked to original sources

arXiv2026

ERPBench: A State-Grounded Evaluation Paradigm for Computer-Use Agents in Enterprise Software

Computer-use agents that operate through screenshots and simulated actions are advancing rapidly, yet their evaluation remains anchored to general desktop and web tasks. Enterprise Resource Planning systems run the finance, procurement, inventory, and customer operations of organizations worldwide, and pose distinct challenges for computer-use agents: dense interfaces, coordinated multi-step interactions, and errors that alter persistent business records rather than surfacing on screen. Existing enterprise computer-use benchmarks rely on proprietary platforms or on simulated approximations of such software. We introduce ERPBench, a benchmark that evaluates screenshot-only agents on a live and reproducible system and scores each task against ground-truth values in its database. Beyond the benchmark, we present a production-grade harness that gates agent actions behind human approval for safe deployment. Evaluating six closed and open-source agents, we demonstrate that strong general performance does not transfer to enterprise reliability. Even when an agent reaches the right form and saves it, the stored record is often wrong: some agents save in up to 85% of runs but write the correct value in as few as 3%. We further characterize failure modes specific to enterprise workflows.

cs.AI↗

arXiv2026

Adaptive Data Augmentation with Multi-armed Bandit: Sample-Efficient Embedding Calibration for Implicit Pattern Recognition

Recognizing implicit visual and textual patterns is essential in many real-world applications of modern AI. However, tackling long-tail pattern recognition tasks remains challenging for current pre-trained foundation models such as LLMs and VLMs. While finetuning pre-trained models can improve accuracy in recognizing implicit patterns, it is usually infeasible due to a lack of training data and high computational overhead. In this paper, we propose ADAMAB, an efficient embedding calibration framework for few-shot pattern recognition. To maximally reduce the computational costs, ADAMAB trains embedder-agnostic light-weight calibrators on top of fixed embedding models without accessing their parameters. To mitigate the need for large-scale training data, we introduce an adaptive data augmentation strategy based on the Multi-Armed Bandit (MAB) mechanism. With a modified upper confidence bound algorithm, ADAMAB diminishes the gradient shifting and offers theoretically guaranteed convergence in few-shot training. Our multi-modal experiments justify the superior performance of ADAMAB, with up to 40% accuracy improvement when training with less than 5 initial data samples of each class.

cs.CV↗

arXiv2025

Enhanced Single-Cell RNA-seq Embedding through Gene Expression and Data-Driven Gene-Gene Interaction Integration

Single-cell RNA sequencing (scRNA-seq) provides unprecedented insights into cellular heterogeneity, enabling detailed analysis of complex biological systems at single-cell resolution. However, the high dimensionality and technical noise inherent in scRNA-seq data pose significant analytical challenges. While current embedding methods focus primarily on gene expression levels, they often overlook crucial gene-gene interactions that govern cellular identity and function. To address this limitation, we present a novel embedding approach that integrates both gene expression profiles and data-driven gene-gene interactions. Our method first constructs a Cell-Leaf Graph (CLG) using random forest models to capture regulatory relationships between genes, while simultaneously building a K-Nearest Neighbor Graph (KNNG) to represent expression similarities between cells. These graphs are then combined into an Enriched Cell-Leaf Graph (ECLG), which serves as input for a graph neural network to compute cell embeddings. By incorporating both expression levels and gene-gene interactions, our approach provides a more comprehensive representation of cellular states. Extensive evaluation across multiple datasets demonstrates that our method enhances the detection of rare cell populations and improves downstream analyses such as visualization, clustering, and trajectory inference. This integrated approach represents a significant advance in single-cell data analysis, offering a more complete framework for understanding cellular diversity and dynamics.

q-bio.GN↗

arXiv2025

SafeTy Reasoning Elicitation Alignment for Multi-Turn Dialogues

Malicious attackers can exploit large language models (LLMs) by engaging them in multi-turn dialogues to achieve harmful objectives, posing significant safety risks to society. To address this challenge, we propose a novel defense mechanism: SafeTy Reasoning Elicitation Alignment for Multi-Turn Dialogues (STREAM). STREAM defends LLMs against multi-turn attacks while preserving their functional capabilities. Our approach involves constructing a human-annotated dataset, the Safety Reasoning Multi-turn Dialogues dataset, which is used to fine-tune a plug-and-play safety reasoning moderator. This model is designed to identify malicious intent hidden within multi-turn conversations and alert the target LLM of potential risks. We evaluate STREAM across multiple LLMs against prevalent multi-turn attack strategies. Experimental results demonstrate that our method significantly outperforms existing defense techniques, reducing the Attack Success Rate (ASR) by 51.2%, all while maintaining comparable LLM capability.

cs.CL↗