Haifeng Chen is the Department Head of the Data Science and System Security Department at NEC Laboratories America. He received his PhD in Computer Engineering from Rutgers University. His research focuses on data mining, system security, and industrial AI. He leads NEC’s work on secure systems, anomaly detection, and AI-driven automation solutions. Based in Princeton, Dr. Chen brings deep expertise in machine learning, anomaly detection, and system health monitoring, with a particular focus on building trustworthy and scalable AI-driven platforms. He has spearheaded numerous high-impact projects, including AI for spacecraft systems, root-cause analysis in cloud environments, and dynamic graph analysis for network security.
His leadership has helped shape the department’s role as a key contributor to NEC’s innovations in fields such as enterprise systems, national defense, and space technology. Dr. Chen holds more than 80 patents and has published over 100 peer-reviewed papers in top-tier venues, earning multiple best paper awards. His contributions extend beyond technical leadership; he serves on program committees for major AI and data science conferences such as SIGKDD and AAAI and has been a panelist for NSF grant reviews. Recognized with NEC’s highest corporate honor, the Contributor of the Year award, Haifeng Chen continues to drive the lab’s efforts in developing real-world, high-impact solutions that merge cutting-edge research with scalable applications across industries.
NEC Laboratories America researchers are heading to Seoul this July for ICML 2026, the Forty-Third International Conference on Machine Learning. One of the most prestigious gatherings in the field, ICML draws academic and industry researchers from around the world to share work spanning machine learning, artificial intelligence, data science, and their many applications.
NEC Laboratories America heads to ACL 2026 in San Diego, California, July 2–7, to present accepted papers spanning knowledge updating and memory control in large language models, task-aware cultural alignment, uncertainty-aware reasoning, and adaptive chain-of-thought optimization, representing some of the most active frontiers in NLP and AI research today.
Procurement teams lose time and money to inaccurate demand forecasts and manual supplier negotiations. A new framework from NEC Corporation and NEC Laboratories America combines automated negotiation with multimodal AI forecasting to optimize both sides of the procurement process.
Procurement is a key function in supply chain management that involves acquiring goods and services to meet organizational needs. Efficient procurement is crucial for minimizing costs, ensuring timely delivery, and maintaining quality standards. This paper explores the integration of automated negotiation and multimodal time-series forecasting to enhance procurement processes. Automated negotiation can streamline interactions with suppliers, while multimodal time-series forecasting can improve demand prediction accuracy by leveraging diverse data sources leading to better negotiation outputs. By combining these approaches, organizations can optimize procurement strategies, reduce costs, and improve overall supply chain efficiency. We present two case studies using simulations based on real-world data for procurement that show the effectiveness of the proposed framework.
Most retrieval-augmented generation systems stop at documents, ignoring the relational databases that power finance, healthcare, and research. Our researchers built a rule-driven framework that learns which source to query for each question, delivering better answers at lower computational cost.
NEC Laboratories America’s AI research played a role in NASA’s Artemis missions, helping analyze complex spacecraft data at scale. Our System Invariant Analysis Technology enables faster insights, improved anomaly detection, and greater confidence in mission readiness for deep space exploration.
Large Language Models (LLMs) have shown remarkable performance on general Question Answering (QA), yet they often struggle in domain-specific scenarios where accurate and up-to-date information is required. Retrieval-Augmented Generation (RAG) addresses this limitation by enriching LLMs with external knowledge, but existing systems primarily rely on unstructured documents, while largely overlooking relational databases, which provide precise, timely, and efficiently queryable factual information, serving as indispensable infrastructure in domains such as finance, healthcare, and scientific research. Motivated by this gap, we conduct a systematic analysis that reveals three central observations: (i) databases and documents offer complementary strengths across queries, (ii) naively combining both sources introduces noise and cost without consistent accuracy gains, and (iii) selecting the most suitable source for each query is crucial to balance effectiveness and efficiency. We further observe that query types show consistent regularities in their alignment with retrieval paths, suggesting that routing decisions can be effectively guided by systematic rules that capture these patterns. Building on these insights, we propose a rule-driven routing framework designed specifically for hybrid-source RAG. A routing agent scores candidate augmentation paths based on explicit rules and selects the most suitable one; a rule-making expert agent refines the rules using QA feedback to produce more comprehensive and reliable decision criteria; and a path-level meta-cache reuses past routing decisions for semantically similar queries to reduce latency and cost. Experiments on three QA datasets demonstrate that our framework consistently outperforms static strategies and learned routing baselines, achieving higher accuracy while maintaining moderate computational cost.
Time series data is ubiquitous across various domains, including manufacturing, finance, and healthcare. High-quality annotations are essential for effectively understanding time series and facilitating downstream tasks. However, obtaining such annotations is challenging, particularly in mission-critical domains. In this paper, we propose TESSA, a multi-agent system designed to automatically generate both general and domain-specific annotations for time series data. TESSA introduces two agents: a general annotation agent and a domain-specific annotation agent. The general agent captures common patterns and knowledge across multiple source domains, leveraging both time-series-wise and text-wise features to generate general annotations. Meanwhile, the domain-specific agent utilizes limited annotations from the target domain to learn domain-specific terminology and generate targeted annotations. Extensive experiments on multiple synthetic and real-world datasets demonstrate that TESSA effectively generates high-quality annotations, outperforming existing methods.
Large Language Models (LLMs) excel at many reasoning tasks but struggle with knowledge-intensive queries due to their inability to dynamically access up-to-date or domain-specific information. Retrieval-Augmented Generation (RAG) has emerged as a promising solution, enabling LLMs to ground their responses in external sources. However, existing RAG methods lack fine-grained control over both the query and source sides, resulting in noisy retrieval, shallow reasoning, and limited adaptability to heterogeneous knowledge sources. In this work, we introduce DeepSieve, a novel RAG method that incorporates information sieving via LLM-as-a-knowledge-router. DeepSieve breaks down complex queries into structured sub-queries and recursively routes each to the most appropriate knowledge source, filtering out irrelevant information through a multi-stage information sieving process. This modular and transparent approach ensures that DeepSieve remains adaptable across diverse information needs. Experiments on three multi-hop QA benchmarks involving heterogeneous sources show that DeepSieve achieves greater reasoning depth, retrieval precision, and interpretability compared to conventional RAG approaches. Our codes are available at https://github.com/MinghoKwok/DeepSieve.
Automatically extracting workflows as procedural graphs from natural language is promising yet underexplored, demanding both structural validity and logical alignment. While recent large language models (LLMs) show potential for procedural graph extraction, they often produce ill-formed structures or misinterpret logical flows. We present text2flow, a multi-agent framework that formulates procedural graph extraction as a multi-round reasoning process with dedicated structural and logical refinement. The framework iterates through three stages: (1) a graph extraction phase with the graph builder agent, (2) a structural feedback phase in which a simulation agent diagnoses and explains structural defects, and (3) a logical feedback phase in which a semantic agent aligns semantics between flow logic and linguistic cues in the source text. Important feedback is prioritized and expressed in naturallanguage, which is injected into subsequent prompts, enabling interpretable and controllable refinement. This modular design allows agents to target distinct error types without supervision or parameter updates. Experiments demonstrate that text2flow achieves substantial improvements in both structural correctness and logical consistency over strong baselines.
