Ratnesh Kumar

Amala Sanjay Deshmukh, Kateryna Chumachenko, Tuomas Rintamaki et al. · nvidia

We introduce Nemotron Nano V2 VL, the latest model of the Nemotron vision-language series designed for strong real-world document understanding, long video comprehension, and reasoning tasks. Nemotron Nano V2 VL delivers significant improvements over our previous model, Llama-3.1-Nemotron-Nano-VL-8B, across all vision and text domains through major enhancements in model architecture, datasets, and training recipes. Nemotron Nano V2 VL builds on Nemotron Nano V2, a hybrid Mamba-Transformer LLM, and innovative token reduction techniques to achieve higher inference throughput in long document and video scenarios. We are releasing model checkpoints in BF16, FP8, and FP4 formats and sharing large parts of our datasets, recipes and training code.

Benjamin Wilson, William Qi, Tanmay Agarwal et al. · gatech

We introduce Argoverse 2 (AV2) - a collection of three datasets for perception and forecasting research in the self-driving domain. The annotated Sensor Dataset contains 1,000 sequences of multimodal data, encompassing high-resolution imagery from seven ring cameras, and two stereo cameras in addition to lidar point clouds, and 6-DOF map-aligned pose. Sequences contain 3D cuboid annotations for 26 object categories, all of which are sufficiently-sampled to support training and evaluation of 3D perception models. The Lidar Dataset contains 20,000 sequences of unlabeled lidar point clouds and map-aligned pose. This dataset is the largest ever collection of lidar sensor data and supports self-supervised learning and the emerging task of point cloud forecasting. Finally, the Motion Forecasting Dataset contains 250,000 scenarios mined for interesting and challenging interactions between the autonomous vehicle and other actors in each local scene. Models are tasked with the prediction of future motion for "scored actors" in each scenario and are provided with track histories that capture object location, heading, velocity, and category. In all three datasets, each scenario contains its own HD Map with 3D lane and crosswalk geometry - sourced from data captured in six distinct cities. We believe these datasets will support new and existing machine learning research problems in ways that existing datasets do not. All datasets are released under the CC BY-NC-SA 4.0 license.

Ramij R. Hossain, Rahmat Adesunkanmi, Ratnesh Kumar

This paper presents a data-learned linear Koopman embedding of nonlinear networked dynamics and uses it to enable real-time model predictive emergency voltage control in a power network. The approach involves a novel data-driven ``basis-dictionary free" lifting of the system dynamics into a higher dimensional linear space over which an MPC (model predictive control) is exercised, making it both scalable and rapid for practical real-time implementation. A Koopman-inspired deep neural network (KDNN) encoder-decoder architecture for the linear embedding of the underlying dynamics under distributed controls is presented, in which the end-to-end components of the KDNN comprising of a triple of transforms is learned from the system trajectory data in one go: A Neural Network (NN)-based lifting to a higher dimension, a linear dynamics within that higher dimension, and an NN-based projection to the original space. This data-learned approach relieves the burden of the ad-hoc selection of the nonlinear basis functions (e.g., polynomial or radial) used in conventional approaches for lifting to higher dimensional linear space. We validate the efficacy and robustness of the approach via application to the standard IEEE 39-bus system.

Zheng Tang, Milind Naphade, Stan Birchfield et al.

In comparison with person re-identification (ReID), which has been widely studied in the research community, vehicle ReID has received less attention. Vehicle ReID is challenging due to 1) high intra-class variability (caused by the dependency of shape and appearance on viewpoint), and 2) small inter-class variability (caused by the similarity in shape and appearance between vehicles produced by different manufacturers). To address these challenges, we propose a Pose-Aware Multi-Task Re-Identification (PAMTRI) framework. This approach includes two innovations compared with previous methods. First, it overcomes viewpoint-dependency by explicitly reasoning about vehicle pose and shape via keypoints, heatmaps and segments from pose estimation. Second, it jointly classifies semantic vehicle attributes (colors and types) while performing ReID, through multi-task learning with the embedded pose representations. Since manually labeling images with detailed pose and attribute information is prohibitive, we create a large-scale highly randomized synthetic dataset with automatically annotated vehicle attributes for training. Extensive experiments validate the effectiveness of each proposed component, showing that PAMTRI achieves significant improvement over state-of-the-art on two mainstream vehicle ReID benchmarks: VeRi and CityFlow-ReID. Code and models are available at https://github.com/NVlabs/PAMTRI.

Zheng Tang, Shuo Wang, David C. Anastasiu et al.

The ninth AI City Challenge continues to advance real-world applications of computer vision and AI in transportation, industrial automation, and public safety. The 2025 edition featured four tracks and saw a 17% increase in participation, with 245 teams from 15 countries registered on the evaluation server. Public release of challenge datasets led to over 30,000 downloads to date. Track 1 focused on multi-class 3D multi-camera tracking, involving people, humanoids, autonomous mobile robots, and forklifts, using detailed calibration and 3D bounding box annotations. Track 2 tackled video question answering in traffic safety, with multi-camera incident understanding enriched by 3D gaze labels. Track 3 addressed fine-grained spatial reasoning in dynamic warehouse environments, requiring AI systems to interpret RGB-D inputs and answer spatial questions that combine perception, geometry, and language. Both Track 1 and Track 3 datasets were generated in NVIDIA Omniverse. Track 4 emphasized efficient road object detection from fisheye cameras, supporting lightweight, real-time deployment on edge devices. The evaluation framework enforced submission limits and used a partially held-out test set to ensure fair benchmarking. Final rankings were revealed after the competition concluded, fostering reproducibility and mitigating overfitting. Several teams achieved top-tier results, setting new benchmarks in multiple tasks.

Sanghyoup Gu, Ratnesh Kumar

Traditional Visual Simultaneous Localization and Mapping (VSLAM) systems assume a static environment, which makes them ineffective in highly dynamic settings. To overcome this, many approaches integrate semantic information from deep learning models to identify dynamic regions within images. However, these methods face a significant limitation as a supervised model cannot recognize objects not included in the training datasets. This paper introduces a novel feature-based Semantic VSLAM capable of detecting dynamic features in the presence of both known and unknown objects. By employing an unsupervised segmentation network, we achieve unlabeled segmentation, and next utilize an objector detector to identify any of the known classes among those. We then pair this with the computed high-gradient optical-flow information to next identify the static versus dynamic segmentations for both known and unknown object classes. A consistency check module is also introduced for further refinement and final classification into static versus dynamic features. Evaluations using public datasets demonstrate that our method offers superior performance than traditional VSLAM when unknown objects are present in the images while still matching the performance of the leading semantic VSLAM techniques when the images contain only the known objects

Rahmat Adesunkanmi, Balaji Sesha Srikanth Pokuri, Ratnesh Kumar

In many real-world applications where the system dynamics has an underlying interdependency among its variables (such as power grid, economics, neuroscience, omics networks, environmental ecosystems, and others), one is often interested in knowing whether the past values of one time series influences the future of another, known as Granger causality, and the associated underlying dynamics. This paper introduces a Koopman-inspired framework that leverages neural networks for data-driven learning of the Koopman bases, termed NeuroKoopman Dynamic Causal Discovery (NKDCD), for reliably inferring the Granger causality along with the underlying nonlinear dynamics. NKDCD employs an autoencoder architecture that lifts the nonlinear dynamics to a higher dimension using data-learned bases, where the lifted time series can be reliably modeled linearly. The lifting function, the linear Granger causality lag matrices, and the projection function (from lifted space to base space) are all represented as multilayer perceptrons and are all learned simultaneously in one go. NKDCD also utilizes sparsity-inducing penalties on the weights of the lag matrices, encouraging the model to select only the needed causal dependencies within the data. Through extensive testing on practically applicable datasets, it is shown that the NKDCD outperforms the existing nonlinear Granger causality discovery approaches.

Rahmat Adesunkanmi, Ratnesh Kumar

This paper presents a clustering technique that reduces the susceptibility to data noise by learning and clustering the data-distribution and then assigning the data to the cluster of its distribution. In the process, it reduces the impact of noise on clustering results. This method involves introducing a new distance among distributions, namely the expectation distance (denoted, ED), that goes beyond the state-of-art distribution distance of optimal mass transport (denoted, $W_2$ for $2$-Wasserstein): The latter essentially depends only on the marginal distributions while the former also employs the information about the joint distributions. Using the ED, the paper extends the classical $K$-means and $K$-medoids clustering to those over data-distributions (rather than raw-data) and introduces $K$-medoids using $W_2$. The paper also presents the closed-form expressions of the $W_2$ and ED distance measures. The implementation results of the proposed ED and the $W_2$ distance measures to cluster real-world weather data as well as stock data are also presented, which involves efficiently extracting and using the underlying data distributions -- Gaussians for weather data versus lognormals for stock data. The results show striking performance improvement over classical clustering of raw-data, with higher accuracy realized for ED. Also, not only does the distribution-based clustering offer higher accuracy, but it also lowers the computation time due to reduced time-complexity.

Soumyabrata Talukder, Ratnesh Kumar

Stability certification and identifying a safe and stabilizing initial set are two important concerns in ensuring operational safety, stability, and robustness of dynamical systems. With the advent of machine-learning tools, these issues need to be addressed for the systems with machine-learned components in the feedback loop. To develop a general theory for stability and stabilizability of a neural network (NN)-controlled nonlinear system subject to bounded parametric variation, a Lyapunov-based stability certificate is proposed and is further used to devise a maximal Lipschitz bound for the NN controller, and also a corresponding maximal region-of-attraction (RoA) inside a given safe operating domain. To compute such a robustly stabilizing NN controller that also maximizes the system's long-run utility, a stability-guaranteed training (SGT) algorithm is proposed. The effectiveness of the proposed framework is validated through an illustrative example.

Zheng Tang, Milind Naphade, Ming-Yu Liu et al.

Urban traffic optimization using traffic cameras as sensors is driving the need to advance state-of-the-art multi-target multi-camera (MTMC) tracking. This work introduces CityFlow, a city-scale traffic camera dataset consisting of more than 3 hours of synchronized HD videos from 40 cameras across 10 intersections, with the longest distance between two simultaneous cameras being 2.5 km. To the best of our knowledge, CityFlow is the largest-scale dataset in terms of spatial coverage and the number of cameras/videos in an urban environment. The dataset contains more than 200K annotated bounding boxes covering a wide range of scenes, viewing angles, vehicle models, and urban traffic flow conditions. Camera geometry and calibration information are provided to aid spatio-temporal analysis. In addition, a subset of the benchmark is made available for the task of image-based vehicle re-identification (ReID). We conducted an extensive experimental evaluation of baselines/state-of-the-art approaches in MTMC tracking, multi-target single-camera (MTSC) tracking, object detection, and image-based ReID on this dataset, analyzing the impact of different network architectures, loss functions, spatio-temporal models and their combinations on task effectiveness. An evaluation server is launched with the release of our benchmark at the 2019 AI City Challenge (https://www.aicitychallenge.org/) that allows researchers to compare the performance of their newest techniques. We expect this dataset to catalyze research in this field, propel the state-of-the-art forward, and lead to deployed traffic optimization(s) in the real world.

Ratnesh Kumar, Edwin Weill, Farzin Aghdasi et al.

In this paper we tackle the problem of vehicle re-identification in a camera network utilizing triplet embeddings. Re-identification is the problem of matching appearances of objects across different cameras. With the proliferation of surveillance cameras enabling smart and safer cities, there is an ever-increasing need to re-identify vehicles across cameras. Typical challenges arising in smart city scenarios include variations of viewpoints, illumination and self occlusions. Most successful approaches for re-identification involve (deep) learning an embedding space such that the vehicles of same identities are projected closer to one another, compared to the vehicles representing different identities. Popular loss functions for learning an embedding (space) include contrastive or triplet loss. In this paper we provide an extensive evaluation of these losses applied to vehicle re-identification and demonstrate that using the best practices for learning embeddings outperform most of the previous approaches proposed in the vehicle re-identification literature. Compared to most existing state-of-the-art approaches, our approach is simpler and more straightforward for training utilizing only identity-level annotations, along with one of the smallest published embedding dimensions for efficient inference. Furthermore in this work we introduce a formal evaluation of a triplet sampling variant (batch sample) into the re-identification literature.