AIConfPaper
← Search

Abhinav Mehrotra

9 accepted papers

2026

NanoFLUX: Distillation-Driven Compression of Large Text-to-Image Generation Models for Mobile Devices

Ruchika Chavhan, Malcolm Chadwick, Alberto Gil Couto Pimentel Ramos, Luca Morreale, Mehdi Noroozi, Abhinav Mehrotra
ICML 2026poster

While large-scale text-to-image diffusion models continue to improve in visual quality, their increasing scale has widened the gap between state-of-the-art models and on-device solutions. To address this gap, we introduce NanoFLUX, a **2.4B** text-to-image flow-matching model distilled from **17B** …

Cited by 0Source ↗Scholar ↗
2026

RFDM: Residual Flow Diffusion Models for Video Editing

Mohammadreza Salehi, Mehdi Noroozi, Luca Morreale, Ruchika Chavhan, Malcolm Chadwick, Alberto Gil Couto Pimentel Ramos +1
CVPR 2026

Instructional video editing applies edits to an input video using only text prompts, enabling intuitive natural-language control. Despite the rapid progress, most methods still require fixed-length inputs and substantial compute. Meanwhile, autoregressive video generation enables efficient variable-

Cited by 0Source ↗code ↗Scholar ↗
2026

Rethinking Data Curation in LLM Training: Online Reweighting Offers Better Generalization than Offline Methods

Wanru Zhao, Yihong Chen, Wentao Ma, Yuzhi Tang, Shengchao Hu, Shell Xu Hu +3
ICLR 2026poster

Data curation is a critical yet underexplored component in large language model (LLM) training. Existing approaches (such as data selection and data mixing) operate in an offline paradigm, decoupled from the training process. This separation introduces extra engineering overhead and makes curated su…

Cited by 0Source ↗code ↗Scholar ↗
2025

EDiT: Efficient Diffusion Transformers with Linear Compressed Attention

Philipp Becker, Abhinav Mehrotra, Ruchika Chavhan, Malcolm Chadwick, Luca Morreale, Mehdi Noroozi +2
ICCV 2025poster

Diffusion Transformers (DiTs) have emerged as a leading architecture for text-to-image synthesis, producing high-quality and photorealistic images. However, the quadratic scaling properties of the attention in DiTs hinder image generation with higher resolution or devices with limited resources. Thi…

Cited by 0Source ↗PDF ↗Scholar ↗
2025

Upcycling Text-to-Image Diffusion Models for Multi-Task Capabilities

Ruchika Chavhan, Abhinav Mehrotra, Malcolm Chadwick, Alberto Gil Couto Pimentel Ramos, Luca Morreale, Mehdi Noroozi +1
ICML 2025poster

Text-to-image synthesis has witnessed remarkable advancements in recent years. Many attempts have been made to adopt text-to-image models to support multiple tasks. However, existing approaches typically require resource-intensive re-training or additional parameters to accommodate for the new tasks…

Cited by 0Source ↗PDF ↗Scholar ↗
2024

Towards Neural Architecture Search through Hierarchical Generative Modeling

Lichuan Xiang, Łukasz Dudziak, Mohamed S Abdelfattah, Abhinav Mehrotra, Nicholas Donald Lane, Hongkai Wen
ICML 2024poster

Neural Architecture Search (NAS) aims to automate deep neural network design across various applications, while a good search space design is core to NAS performance. A too-narrow search space may fail to cover diverse task requirements, whereas a too-broad one can escalate computational expenses an…

Cited by 0Source ↗PDF ↗Scholar ↗
2022

Conditioning Sequence-to-sequence Networks with Learned Activations

Alberto Gil Couto Pimentel Ramos, Abhinav Mehrotra, Nicholas Donald Lane, Sourav Bhattacharya
ICLR 2022poster

Conditional neural networks play an important role in a number of sequence-to-sequence modeling tasks, including personalized sound enhancement (PSE), speaker dependent automatic speech recognition (ASR), and generative modeling such as text-to-speech synthesis. In conditional neural networks, the o…

Cited by 13Source ↗PDF ↗Scholar ↗
2021

NAS-Bench-ASR: Reproducible Neural Architecture Search for Speech Recognition

Abhinav Mehrotra, Alberto Gil C. P. Ramos, Sourav Bhattacharya, Łukasz Dudziak, Ravichander Vipperla, Thomas Chau +3
ICLR 2021poster

Powered by innovations in novel architecture design, noise tolerance techniques and increasing model capacity, Automatic Speech Recognition (ASR) has made giant strides in reducing word-error-rate over the past decade. ASR models are often trained with tens of thousand hours of high quality speech d…

Cited by 86Source ↗PDF ↗Scholar ↗
2021

Zero-Cost Proxies for Lightweight NAS

Mohamed S Abdelfattah, Abhinav Mehrotra, Łukasz Dudziak, Nicholas Donald Lane
ICLR 2021poster

Neural Architecture Search (NAS) is quickly becoming the standard methodology to design neural network models. However, NAS is typically compute-intensive because multiple models need to be evaluated before choosing the best one. To reduce the computational power and time needed, a proxy task is oft…

Cited by 372Source ↗PDF ↗code ↗Scholar ↗