Our Machine Learning team has been at the forefront of machine learning developments, including deep learning, support vector machines, and semantic analysis, for over a decade. We develop innovative technologies integrated into NEC’s products and services. Machine learning is the critical technology for data analytics and artificial intelligence. Recent progress in this field opens opportunities for various new applications.
Deep learning will maintain prominence with more robust model architectures, training methods, and optimization techniques. Enhanced interpretability and explainability will be imperative, especially for AI systems in critical domains like healthcare and finance. Addressing bias and ensuring fairness in AI algorithms will be a top priority, leading to the development of tools and guidelines for ethical AI. Federated learning, quantum computing’s potential impact, and the growth of edge computing will diversify ML applications.
Natural language processing will continue to advance, driving progress in conversational AI, while healthcare, finance, education, and creative industries will witness profound AI integration. As quantum computing matures, it could revolutionize machine learning, while edge computing and federated learning will expand AI’s reach across various domains. Our machine learning research will produce innovation across industries, including more accurate medical diagnoses, safer autonomous systems, and efficient energy use while enabling personalized education and AI-generated creativity.
Read our news and publications from our world-class team of researchers from our Machine Learning department.
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.
Designing drug molecules is no longer just about generation, but control. NEC Laboratories America introduces MolDiffdAE, a diffusion-based framework that enables precise, multi-objective tuning of 3D molecular properties. By learning a semantic space, researchers can efficiently guide design, accelerating drug discovery and exploration of chemical space.
We study the problem of length generalization (LG) in transformers: the ability of a model trained on shorter sequences to maintain performance when evaluated on much longer, previously unseen inputs. Prior work by Huang et al. (2024) established that transformers eventually achieve length generalization once the training sequence length exceeds some finite threshold, but left open the question of how large it must be. In this work, we provide the first quantitative bounds on the required training length for length generalization to occur. Motivated by previous empirical and theoretical work, we analyze LG in several distinct problem settings: error control vs. average error control over an input distribution, infinite-precision softmax attention vs. finite-precision attention (which reduces to an argmax) in the transformer, as well as for one- or two-layer transformers. In all scenarios, we prove that LG occurs when the internal behavior of the transformer on longer sequences can be “simulated” by its behavior on shorter sequences seen during training. Our bounds give qualitative estimates for the required length of training data required for a transformer to generalize, and we verify these insights empirically. These results sharpen our theoretical understanding of the mechanisms underlying extrapolation in transformers, and formalize the intuition that richer training data is required for generalization on more complex tasks.
Eric C. Blow of NEC Laboratories America presents a keynote at COOL Chips 29 in Tokyo, exploring multi-modal photonic computing for real-time, ultra-efficient inference. This work highlights how photonics is reshaping AI performance, enabling faster and more energy-efficient processing across next-generation systems.
AI interpretability has long been the focus, but what if it’s only part of the story? New research introduces model semantics, a framework for understanding what AI systems truly represent and how their internal structures connect to real-world phenomena.
Clinical diagnosis requires sequential evidence acquisition under uncertainty. However, most Large Language Model (LLM) based diagnostic systems assume fully observed patient information and therefore do not explicitly model how clinical evidence should be sequentially acquired over time. Even when diagnosis is formulated as a sequential decision process, it is still challenging to learn effective diagnostic trajectories. This is because the space of possible evidence-acquisition paths is relatively large, while clinical datasets rarely provide explicit supervision information for desirable diagnostic paths. To this end, we formulate sequential diagnosis as a Latent Diagnostic Trajectory Learning (LDTL) framework based on a planning LLM agent and a diagnostic LLM agent. For the diagnostic LLM agent, diagnostic action sequences are treated as latent paths and we introduce a posterior distribution that prioritizes trajectories providing more diagnostic information. The planning LLM agent is then trained to follow this distribution, encouraging coherent diagnostic trajectories that progressively reduce uncertainty. Experiments on the MIMIC-CDM benchmark demonstrate that our proposed LDTL framework outperforms existing baselines in diagnostic accuracy under a sequential clinical diagnosis setting, while requiring fewer diagnostic tests. Furthermore, ablation studies highlight the critical role of trajectory-level posterior alignment in achieving these improvements.
Controlled generation of 3D molecules is highly valuable in drug design, enabling targeted modifications that preserve core structure and binding-relevant geometry while improving developability-related properties. While equivariant diffusion models achieve state-of-the-art de novo 3D molecule generation, reliably controlling multiple molecular properties remains challenging. A key limitation is structural: diffusion models typically lack an explicit latent space for targeted manipulation. We propose a semantics-guided equivariant autoencoding diffusion model that learns a disentangled semantic embedding of 3D molecules via an auxiliary encoder, to achieve fine-grained control over the generative denoising process. This semantic embedding enables efficient retrieval, random generation and controlled generation. By directly manipulating the embedding, we effectively steer the molecular generation toward desired compositions, shapes and physicochemical properties, and further enhance the generation quality with retrieval-augmented generation (RAG) using the embedding as the query. Importantly, the disentangled embedding offers significant advantages for joint manipulation of multiple properties. Experiments demonstrate precise and data-efficient property control while preserving non-targeted properties.
We introduce a framework to analyse interpretability in deep learning, by drawing on a formal notion of model semantics from the philosophy of science. We argue that interpretability is only one aspect of a models semantics and illustrate our framework with examples from biomedicine.
Many pioneers of modern artificial intelligence and machine learning spent part of their careers at NEC research labs in the United States. Researchers such as Yann LeCun, Vladimir Vapnik, Léon Bottou, Corinna Cortes, and others contributed foundational ideas in deep learning, statistical learning theory, speech recognition, and computer vision.
Vision Transformers (ViTs) have achieved state-of-the-art performance in offline video action detection, but their reliance on processing fixed-size clips with full spatio-temporal attention makes them computationally expensive and ill-suited for real-time streaming applications due to massive computational redundancy. This paper introduces a novel framework to adapt these powerful offline models into efficient, online student models through knowledge distillation. We propose two causal, streaming-friendly attention architectures that replace the full self-attention mechanism: (1) a lightweight Temporal Shift Attention that integrates past context with minimal overhead, and (2) a Decomposed Spatial-Temporal Attention that combines intra-frame spatial attention with an LSTM for temporal modeling. Both architectures utilize caching to eliminate redundant operations on a frame-by-frame basis. To maximize knowledge transfer, we introduce an uncertainty-guided distillation process, which formulates the training as a multi-task learning problem. Our resulting models demonstrate significant efficiency gains, achieving up to a4x improvement in latency and throughput compared to the original offline teacher while ensuring state-of-the-art performance for online methods. Our work provides a practical and effective methodology for deploying high-accuracy transformer models in latency-sensitive, real-world video analysis systems.
