8 papers
Edge-Efficient Image Restoration: Transformer Distillation into State-Space Models
Srinivas Soumitri Miriyala, Sowmya Vajrala, Sravanth Kodavanti +2
We propose a modular framework for hybrid image restoration that integrates transformer and state-space model (SSM) blocks with a focus on improving runtime efficiency on edge hard…
TOC-SR: Task-Optimal Compact diffusion for Image Super Resolution
Sowmya Vajrala, Akshay Bankar, Manjunath Arveti +5
Diffusion models have recently demonstrated strong performance for image restoration tasks, including super-resolution. However, their large model size and iterative sampling proce…
Unlocking the Edge deployment and ondevice acceleration of multi-LoRA enabled one-for-all foundational LLM
Sravanth Kodavanti, Sowmya Vajrala, Srinivas Miriyala +13
Deploying large language models (LLMs) on smartphones poses significant engineering challenges due to stringent constraints on memory, latency, and runtime flexibility. In this wor…
Quantization with Unified Adaptive Distillation to enable multi-LoRA based one-for-all Generative Vision Models on edge
Sowmya Vajrala, Aakash Parmar, Prasanna R +4
Generative Artificial Intelligence (GenAI) features such as image editing, object removal, and prompt-guided image transformation are increasingly integrated into mobile applicatio…
EdgeDiT: Hardware-Aware Diffusion Transformers for Efficient On-Device Image Generation
Sravanth Kodavanti, Manjunath Arveti, Sowmya Vajrala +2
Diffusion Transformers (DiT) have established a new state-of-the-art in high-fidelity image synthesis; however, their massive computational complexity and memory requirements hinde…
Towards Efficient Image Deblurring for Edge Deployment
Srinivas Miriyala, Sowmya Vajrala, Sravanth Kodavanti
Image deblurring is a critical stage in mobile image signal processing pipelines, where the ability to restore fine structures and textures must be balanced with real-time constrai…