Martin Renqiang Min is the Department Head of the Machine Learning Department at NEC Laboratories America. He holds a Ph.D. in Computer Science from the University of Toronto and completed postdoctoral research at Yale University, where he also taught courses on deep learning. His research has been published in top venues, including Nature, NeurIPS, ICML, ICLR, CVPR, and ACL, and his innovations have been recognized internationally, with features in Science and MIT Technology Review.
At NEC, Dr. Min directs a multidisciplinary research team at the forefront of foundational and applied artificial intelligence. His portfolio spans deep learning, natural language understanding, multimodal learning, visual reasoning, and the application of machine learning to biomedical and healthcare data. He has contributed to the design of scalable learning systems that power real-world applications, bridging cutting-edge theory with industry-scale deployment. He also co-chaired the NeurIPS Workshop on Machine Learning in Computational Biology, advancing the dialogue between AI and life sciences.
Under his leadership, NEC’s machine learning group drives innovation across multiple domains, including AI for precision medicine, next-generation language modeling, and interpretable multimodal systems. He is known for fostering interdisciplinary collaboration—both within NEC and with academic and industry partners—encouraging research that connects scientific breakthroughs with societal impact. His team’s contributions extend to core technologies used across telecommunications, enterprise solutions, and healthcare, positioning NEC at the leading edge of applied AI. Dr. Min is recognized for his ability to identify emerging trends in machine learning and translate them into long-term research roadmaps. His work continues to influence the global AI community, and his leadership ensures NEC remains a hub for transformative research that combines fundamental discovery with practical applications that improve people’s lives.
State-of-the-art video models are accurate but too slow for live deployment. This work transfers their knowledge into causal streaming models that process video frames in real time, achieving 4x lower latency with competitive accuracy across action detection and pedestrian intent tasks.
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.
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.
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.
Recent advances in video diffusion models have enabled the generation of high-quality videos. However, these videos still suffer from unrealistic deformations, semantic violations, and physical inconsistencies that are largely rooted in the absence of 3D physical priors. To address these challenges, we propose an object-aware 4D human motion generation framework grounded in 3D Gaussian representations and motion diffusion priors. With pre-generated 3D humans and objects, our method, Motion Score Distilled Interaction (MSDI), employs the spatial and prompt semantic information in large language models (LLMs) and motion priors through the proposed Motion Diffusion Score Distillation Sampling (MSDS). The combination of MSDS and LLMs enables our spatial-aware motion optimization, which distills score gradients from pre-trained motion diffusion models, to refine human motion while respecting object and semantic constraints. Unlike prior methods requiring joint training on limited interaction datasets, our zero-shot approach avoids retraining and generalizes to out-of-distribution object aware human motions. Experiments demonstrate that our framework produces natural and physically plausible human motions that respect 3D spatial context, offering a scalable solution for realistic 4D generation.
Radiology report generation requires advanced medical image analysis, effective temporal reasoning, and accurate text generation. Although recent innovations, particularly multimodal large language models, have shown improved performance, their supervised fine-tuning (SFT) objective is not explicitly aligned with clinical efficacy. In this work, we introduce EditGRPO, a mixed-policy reinforcement learning algorithm designed specifically to optimize the generation through clinically motivated rewards. EditGRPO integrates on-policy exploration with off-policy guidance by injecting sentence-level detailed corrections during training rollouts. This mixed-policy approach addresses the exploration dilemma and sampling efficiency issues typically encountered in RL. Applied to a Qwen2.5-VL-3B, EditGRPO outperforms both SFT and vanilla GRPO baselines, achieving an average improvement of 3.4% in clinical metrics across four major datasets. Notably, EditGRPO also demonstrates superior out-of-domain generalization, with an average performance gain of5.9% on unseen datasets.
Large Language Models (LLMs) have demonstrated remarkable capabilities in understanding and generating human-like text, yet they largely operate as reactive agents, responding only when directly prompted. This passivity creates an “awareness gap,” limiting their potential as truly collaborative partners in dynamic human discussions. We introduce , a framework designed to bridge this gap by training models to proactively decide not just to say, but critically, to speak. Our primary contribution is a scalable two-stage data generation pipeline that synthesizes a large-scale dataset of realistic multi-turn human discussions. Each discussion is annotated with one of five intervention types (e.g., Factual Correction, Concept Definition) and contains an explicit conversational trigger where an AI intervention adds value. By training models to predict a special silent token when no intervention is needed, they learn to remain quiet until a helpful contribution can be made. We explore two architectural baselines: an integrated end-to-end model and a decoupled classifier-generator system optimized for low-latency inference. We evaluate these models on their ability to accurately time interventions and generate helpful responses, paving the way for more situationally aware and proactive conversational AI.
Cell fate decisions are highly coordinated processes governed bycomplex interactions among numerous regulatory genes, whiledisruptions in these mechanisms can lead to developmental abnormalitiesand disease. Traditional methods often fail to capture suchcombinatorial interactions, limiting their ability to fully model cellfate dynamics. Here, we introduce MetaVelo, a global feature explanationframework for identifying key regulatory gene sets influencingcell fate transitions. MetaVelo models these transitions as ablack-box function and employs a differentiable neural ordinary differentialequation (ODE) surrogate to enable efficient optimization.By reparameterizing the problem as a controllable data generationprocess, MetaVelo overcomes the challenges posed by the nondifferentiablenature of cell fate dynamics. Benchmarking acrossdiverse stand-alone and longitudinal single-cell RNA-seq datasetsand three black-box cell fate models demonstrates its superiorityover 12 baseline methods in predicting developmental trajectoriesand identifying combinatorial regulatory gene sets. MetaVelo furtherdistinguishes independent from synergistic regulatory genes,offering novel insights into the gene interactions governing cellfate. With the growing availability of high-resolution single-celldata, MetaVelo provides a scalable and effective framework fo
Adapting large Video-Language Models (VLMs) for action detection using only a few examples poses challenges like overfitting and the granularity mismatch between scene-level pre-training and required person-centric understanding. We propose an efficient adaptation strategy combining parameter-efficient tuning (LoRA) with a novel learnable internal feature augmentation. Applied within the frozen VLM backbone using FiLM, these augmentations generate diverse feature variations directly relevant to the task. Additionally, we introduce a group-weighted loss function that dynamically modulates the training contribution of each augmented sample based on its prediction divergence relative to the group average. This promotes robust learning by prioritizing informative yet reasonable augmentations. We demonstrate our method’s effectiveness on complex multi-label, multi-person action detection datasets (AVA, MOMA), achieving strong mAP performance and showcasing significant data efficiency for adapting VLMs from limited examples.
Designing protein-binding proteins with high affinity is critical in biomedical research and biotechnology. Despite recent advancements targeting specific proteins, the ability to create high-affinity binders for arbitrary protein targets on demand, without extensive rounds of wet-lab testing,remains a significant challenge. Here, we introduce PPDiff, a diffusion model to jointly design the sequence and structure of binders for arbitrary protein targets in a non-autoregressive manner. PPDiff builds upon our developed Sequence Structure Interleaving Network with Causal attention layers (SSINC), which integrates interleaved self-attention layers to capture global amino acid correlations, k-nearest neighbor (kNN) equivariant graph layers to model local interactions in three-dimensional (3D) space, and causal attention layers to simplify the intricate interdependencies within the protein sequence. To assess PPDiff, we curate PPBench, a general protein complex dataset comprising 706,360 complexes from the Protein Data Bank (PDB). The model is pretrained on PPBench and finetuned on two real-world applications: target-protein mini-binder complex design and antigen-antibody complex design. PPDiff consistently surpasses baseline methods, achieving success rates of 50.00%, 23.16%, and 16.89% for the pretraining task and the two downstream applications, respectively.
