arXiv subjects

Shubham Pachori

Publications and source records attributed to Shubham Pachori.

5 recordsLinked to original sources

arXiv2026

Nemotron 3 Nano Omni: Efficient and Open Multimodal Intelligence

We introduce Nemotron 3 Nano Omni, the latest model in the Nemotron multimodal series and the first to natively support audio inputs alongside text, images, and video. Nemotron 3 Nano Omni delivers consistent accuracy improvements over its predecessor, Nemotron Nano V2 VL, across all modalities, enabled by advances in architecture, training data and recipes. In particular, Nemotron 3 delivers leading results in real-world document understanding, long audio-video comprehension, and agentic computer use. Built on the highly efficient Nemotron 3 Nano 30B-A3B backbone, Nemotron 3 Nano Omni further incorporates innovative multimodal token-reduction techniques to deliver substantially lower inference latency and higher throughput than other models of similar size. We are releasing model checkpoints in BF16, FP8, and FP4 formats, along with portions of the training data and codebase to facilitate further research and development.

cs.LG↗

arXiv2026

DuoGen: Towards General Purpose Interleaved Multimodal Generation

Interleaved multimodal generation enables capabilities beyond unimodal generation models, such as step-by-step instructional guides, visual planning, and generating visual drafts for reasoning. However, the quality of existing interleaved generation models under general instructions remains limited by insufficient training data and base model capacity. We present DuoGen, a general-purpose interleaved generation framework that systematically addresses data curation, architecture design, and evaluation. On the data side, we build a large-scale, high-quality instruction-tuning dataset by combining multimodal conversations rewritten from curated raw websites, and diverse synthetic examples covering everyday scenarios. Architecturally, DuoGen leverages the strong visual understanding of a pretrained multimodal LLM and the visual generation capabilities of a diffusion transformer (DiT) pretrained on video generation, avoiding costly unimodal pretraining and enabling flexible base model selection. A two-stage decoupled strategy first instruction-tunes the MLLM, then aligns DiT with it using curated interleaved image-text sequences. Across public and newly proposed benchmarks, DuoGen outperforms prior open-source models in text quality, image fidelity, and image-context alignment, and also achieves state-of-the-art performance on text-to-image and image editing among unified generation models. Data and code will be released at https://research.nvidia.com/labs/dir/duogen/.

cs.CV↗

arXiv2017

Multi-Scale Saliency Detection using Dictionary Learning

Saliency detection has drawn a lot of attention of researchers in various fields over the past several years. Saliency is the perceptual quality that makes an object, person to draw the attention of humans at the very sight. Salient object detection in an image has been used centrally in many computational photography and computer vision applications like video compression, object recognition and classification, object segmentation, adaptive content delivery, motion detection, content aware resizing, camouflage images and change blindness images to name a few. We propose a method to detect saliency in the objects using multimodal dictionary learning which has been recently used in classification and image fusion. The multimodal dictionary that we are learning is task driven which gives improved performance over its counterpart (the one which is not task specific).

cs.CV↗

arXiv2017

Hashing in the Zero Shot Framework with Domain Adaptation

Techniques to learn hash codes which can store and retrieve large dimensional multimedia data efficiently have attracted broad research interests in the recent years. With rapid explosion of newly emerged concepts and online data, existing supervised hashing algorithms suffer from the problem of scarcity of ground truth annotations due to the high cost of obtaining manual annotations. Therefore, we propose an algorithm to learn a hash function from training images belonging to `seen' classes which can efficiently encode images of `unseen' classes to binary codes. Specifically, we project the image features from visual space and semantic features from semantic space into a common Hamming subspace. Earlier works to generate hash codes have tried to relax the discrete constraints on hash codes and solve the continuous optimization problem. However, it often leads to quantization errors. In this work, we use the max-margin classifier to learn an efficient hash function. To address the concern of domain-shift which may arise due to the introduction of new classes, we also introduce an unsupervised domain adaptation model in the proposed hashing framework. Results on the three datasets show the advantage of using domain adaptation in learning a high-quality hash function and superiority of our method for the task of image retrieval performance as compared to several state-of-the-art hashing methods.

cs.CV↗

arXiv2016

Zero Shot Hashing

This paper provides a framework to hash images containing instances of unknown object classes. In many object recognition problems, we might have access to huge amount of data. It may so happen that even this huge data doesn't cover the objects belonging to classes that we see in our day to day life. Zero shot learning exploits auxiliary information (also called as signatures) in order to predict the labels corresponding to unknown classes. In this work, we attempt to generate the hash codes for images belonging to unseen classes, information of which is available only through the textual corpus. We formulate this as an unsupervised hashing formulation as the exact labels are not available for the instances of unseen classes. We show that the proposed solution is able to generate hash codes which can predict labels corresponding to unseen classes with appreciably good precision.

cs.CV↗