activity
20242026
collaborators

6 papers

cs.CV2026

Best of Both Worlds: Multimodal Reasoning and Generation via Unified Discrete Flow Matching

Onkar Susladkar, Tushar Prakash, Gayatri Deshmukh +8

We propose UniDFlow, a unified discrete flow-matching framework for multimodal understanding, generation, and editing. It decouples understanding and generation via task-specific l…

cs.CV2025

Dressing the Imagination: A Dataset for AI-Powered Translation of Text into Fashion Outfits and A Novel NeRA Adapter for Enhanced Feature Adaptation

Gayatri Deshmukh, Somsubhra De, Chirag Sehgal +2

Specialized datasets that capture the fashion industry's rich language and styling elements can boost progress in AI-driven fashion design. We present FLORA, (Fashion Language Outf…

cs.CV2025

Historic Scripts to Modern Vision: A Novel Dataset and A VLM Framework for Transliteration of Modi Script to Devanagari

Harshal Kausadikar, Tanvi Kale, Onkar Susladkar +1

In medieval India, the Marathi language was written using the Modi script. The texts written in Modi script include extensive knowledge about medieval sciences, medicines, land rec…

cs.CV2025

MotionAura: Generating High-Quality and Motion Consistent Videos using Discrete Diffusion

Onkar Susladkar, Jishu Sen Gupta, Chirag Sehgal +2

The spatio-temporal complexity of video data presents significant challenges in tasks such as compression, generation, and inpainting. We present four key contributions to address…

cs.CV2025

L2GNet: Optimal Local-to-Global Representation of Anatomical Structures for Generalized Medical Image Segmentation

Vandan Gorade, Sparsh Mittal, Neethi Dasu +3

Continuous Latent Space (CLS) and Discrete Latent Space (DLS) models, like AttnUNet and VQUNet, have excelled in medical image segmentation. In contrast, Synergistic Continuous and…

eess.SP2024

Hybrid Quantum Neural Network based Indoor User Localization using Cloud Quantum Computing

Sparsh Mittal, Yash Chand, Neel Kanth Kundu

This paper proposes a hybrid quantum neural network (HQNN) for indoor user localization using received signal strength indicator (RSSI) values. We use publicly available RSSI datas…