NEC Labs America
06/08/2026
This week, six elite squads of NEC Labs America summer were activated for Intern Operation: Cipher and Seek, a grueling yet fun field exercise engineered by mission commanders Stacey and Wendy. First, each squad had to crack an ancient cipher using nothing but their minds and two decoder boards. The team that broke the code first earned a 30-second tactical advantage heading into the main mission: a high-stakes sweep of the Princeton facility to locate emergency equipment, document critical infrastructure, and identify key personnel. One team took home the prize, but all squads completed the mission and walked away knowing that they are ready.
06/05/2026
What if you could search imagery the same way you search the web?
🛰️ Our new Open-SAT system lets users query high-resolution satellite images in plain English, no predefined categories, no model retraining required. Ask for “solar panels” or “construction sites,” and the system finds them, accurately and fast.
The secret: instead of tuning a similarity threshold, uses an LLM to reason about what surrounds an object of interest in a satellite scene, then refines the search embedding using that context. The result is a classification-style retrieval that is both threshold-free and training-free.
The authors of the paper are Md Adnan Arefeen, 2023 and 2024 NEC Labs America Intern, North South University; Biplob Debnath, NEC Laboratories America, Inc.; Ravi K. Rajendran, NEC Laboratories America, Inc.; Murugan Sankaradas, NEC Laboratories America, Inc.; Srimat T. Chakradhar, NEC Laboratories America, Inc.
Read more: https://nec-labs.com/blog/open-sat-llm-guided-query-embedding-refinement-for-open-vocabulary-object-retrieval-in-satellite-imagery/
06/02/2026
The NEC Laboratories America team has touched down in Denver for this week, running June 3-7. The / Conference on Computer Vision and Pattern Recognition is one of the most prestigious gatherings in AI and computer vision, bringing together researchers, engineers, and innovators from around the world to share the latest advances in computer vision, machine learning, and pattern recognition.
Year after year, it's where the field takes its next step forward. This year, our team is showing up in full force, organizing workshops, presenting posters, and delivering virtual presentations. Here is our agenda.
• AUTOPILOT Workshop (June 3): Ali K. AlShami on the organizing committee for this workshop on safety-critical autonomous driving, bringing together academia and industry to explore robust perception, prediction, decision-making, and motion planning.
• Uncertainty-Aware Knowledge Distillation for Multimodal Large Language Models: Jingchen Sun (Intern), Shaobo Han and Deep Patel will present a poster on Beta-KD. The key question: can uncertainty tell a multimodal LLM when to trust the teacher versus the data? We formulate knowledge distillation as Bayesian inference with uncertainty-aware weighting.
• Object-Aware 4D Human Motion Generation (June 4): Deep Patel presents virtually on generating realistic, object-aware human motion across space and time.
• Anomaly Detection with Foundation Models Workshop (June 4): Abhishek Aich is organizing the ADFM Workshop, focused on anomaly detection, foundation models, trustworthy AI, and computer vision.
• LangDriveCTRL: Natural Language Controllable Driving Scene Editing with Multi-modal Agents (June 4): Yun He (intern) and Zaid Tasneem present LangDriveCTRL, a natural-language-controllable framework for editing real-world driving videos to synthesize diverse traffic scenarios.
• HorizonWeaver: Generalizable Multi-Level Semantic Editing for Driving Scenes (June 5): Mauricio Soroco (intern) and Ziyu Jiang present HorizonWeaver, which tackles three fundamental challenges in driving scene editing.
• HorizonForge: Driving Scene Editing with Any Trajectories and Any Vehicles (June 6): Yifan Wang (intern) and Ziyu Jiang present HorizonForge, a unified framework that reconstructs scenes as editable Gaussian Splats and Meshes, enabling fine-grained 3D manipulation and language-driven vehicle insertion.
Read more on our blog: https://nec-labs.com/blog/nec-labs-
america-attends-cvpr-2026-in-denver-co-june-3-7-2026/
See you in Denver!
Click here to claim your Sponsored Listing.
Category
Telephone
Website
Address
4 Independence Way, Suite 200
Princeton, NJ