Institution profile

Accenture

Industry researchnorthamerica · us
Official website
Research library87linked papers
Opportunities0open roles
Selected work

Representative Papers

Vikhr: Constructing a State-of-the-art Bilingual Open-Source Instruction-Following Large Language Model for Russian

May 22, 2024MRL

To address the poor generation quality and low computational efficiency of existing large language models for Russian, this paper introduces Vikhr—the first high-performance, bilingual, open-source instruction-following model natively optimized for Russian. Methodologically, Vikhr employs full-parameter continual pretraining followed by supervised instruction fine-tuning, deliberately avoiding parameter-efficient adaptations such as LoRA to achieve vocabulary-level native Russian support. Built upon the Mistral architecture, it features a custom Russian–English tokenizer, alongside substantial expansion of high-quality Russian instruction data and pretraining corpora, enhanced by multi-stage data cleaning and synthetic data generation. Experiments demonstrate that Vikhr establishes new state-of-the-art results among open-source models on multiple Russian-language benchmarks, with several metrics surpassing those of proprietary commercial models. All model weights, datasets, and training code are publicly released.

4 citationsRead paper

Do Generative AI Tools Ensure Green Code? An Investigative Study

Apr 16, 20242024 IEEE/ACM International Workshop on Responsible AI Engineering (RAIE)

It remains unclear whether generative AI programming tools inherently produce “green code” aligned with sustainability principles. Method: This study introduces the first Green Code Assessment Framework for Sustainable Software Engineering, integrating static code analysis, multi-tool comparative experiments (ChatGPT, Bard, GitHub Copilot), and compliance checking against established green coding guidelines—including energy-efficient algorithms and resource optimization. Contribution/Results: Empirical evaluation reveals that all three tools systematically violate core green coding principles across most scenarios; their generated code exhibits significantly higher energy consumption and lower resource efficiency than human-written sustainable implementations. The work exposes a critical sustainability gap in current AI programming assistants and delivers a reproducible methodology, empirical benchmarks, and actionable insights—thereby establishing foundational theoretical and technical support for advancing green AI-assisted software development and tool optimization.

2 citationsRead paper

Towards a Knowledge Base of Common Sustainability Weaknesses in Green Software Development

Sep 11, 2023International Conference on Automated Software Engineering

The absence of a standardized, sustainability-focused defect knowledge base for green software development hinders the advancement of automated sustainability analysis tools. Method: We propose the first systematic classification framework for sustainability weaknesses, derived through empirical analysis and pattern mining across ecological dimensions—including energy efficiency and resource waste—to semantically re-annotate and attribute code defects. Our approach explicitly decouples sustainability weaknesses from conventional software defect taxonomies (e.g., CWE), rigorously validating their non-transferability. Contribution/Results: We introduce the first standalone, ecology-aware sustainability weakness taxonomy, supported by formal modeling and empirical validation. The resulting knowledge base enables scalable, reusable foundations for static sustainability analysis, eco-conscious code optimization, and actionable sustainability recommendations in green software engineering.

2 citationsRead paper

From Understanding to Engagement: Personalized pharmacy Video Clips via Vision Language Models (VLMs)

Jan 08, 2026arXiv.org

This work addresses the inefficiency and inconsistency of manual annotation in traditional pharmaceutical video processing, which struggles to leverage multimodal information—particularly in large-scale, long-form videos such as clinical trial interviews. The authors propose an end-to-end framework for automatically generating highlight clips by integrating vision-language models (VLMs) and audio-language models (ALMs), enhanced with role-based prompting to enable personalized editing tailored to marketing, training, and regulatory scenarios. Key innovations include a reproducible Cut & Merge algorithm ensuring audiovisual synchronization and smooth transitions, a role-prompt-driven personalization mechanism, and a highly efficient, low-cost pipeline. Evaluated on the Video MME benchmark and a dataset of 16,159 pharmaceutical videos, the system achieves a 3–4× speedup and 4× cost reduction compared to baselines, while outperforming advanced models like Gemini 2.5 Pro in both coherence (0.348) and informativeness (0.721).

1 citationsRead paper

Scaling Vision Language Models for Pharmaceutical Long Form Video Reasoning on Industrial GenAI Platform

Jan 08, 2026arXiv.org

This work addresses the challenge of efficiently processing long videos in pharmaceutical industrial settings, where GPU resources, latency, and cost are tightly constrained. The authors propose the first industrial-scale multimodal generative AI framework tailored for the pharmaceutical domain, integrating scaled dot-product attention (SDPA), a novel multimodal fusion strategy, and keyframe extraction to achieve 3–8× inference acceleration on commodity GPUs. Systematic evaluation on a large-scale dataset—comprising over 200,000 PDFs, 25,000 long videos, and 888 multilingual audio samples—demonstrates that the multimodal approach significantly outperforms unimodal baselines on 8 out of 12 tasks, with particularly strong gains in video-length-dependent scenarios. The study further identifies four critical bottlenecks: multimodal fusion design, temporal reasoning limits, attention mechanism trade-offs, and video segmentation strategies.

1 citationsRead paper
Recent publications

Latest Papers