Author name cluster

Delip Rao

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

3 papers

1 author row

AAAI Conference 2026 Conference Paper

LaTeX2Layout: High-Fidelity, Scalable Document Layout Annotation Pipeline for Layout Detection

Feijiang Han
Zelong Wang
Bowen Wang
Xinxin Liu
Skyler Cheung
Delip Rao
Chris Callison-Burch
Lyle Ungar

General-purpose Vision-Language Models (VLMs) are increasingly integral to modern AI systems for document understanding, yet their ability to perform fine-grained layout analysis remains severely underdeveloped. Overcoming this limitation requires large-scale, high-fidelity training datasets. However, current annotation methods that rely on parsing rendered PDFs are costly, error-prone, and difficult to scale. We propose a different paradigm: extracting ground-truth layout directly from the LaTeX compilation process rather than the final PDF. We present LaTeX2Layout, a generalizable procedural pipeline that recovers pixel-accurate bounding boxes and reading order from compiler traces. This enables the generation of a 140K-page dataset, including 120K programmatically generated synthetic variants that more than double the layout diversity of real-world data. Using this dataset, we fine-tune an efficient 3B-parameter VLM with an easy-to-hard curriculum that accelerates convergence. Our model achieves Kendall's tau=0.95 for reading order and mAP@50=0.91 for element grounding, delivering nearly 200% relative improvement over strong zero-shot baselines such as GPT-4o and Claude-3.7.

PDF Details DOI

AAAI Conference 2020 Conference Paper

Learning Efficient Representations for Fake Speech Detection

Nishant Subramani
Delip Rao

Synthetic speech or “fake speech” which matches personal vocal traits has become better and cheaper due to advances in deep learning-based speech synthesis and voice conversion approaches. This increased accessibility of synthetic speech systems and the growing misuse of them highlights the critical need to build countermeasures. Furthermore, new synthesis models evolve all the time and the efﬁcacy of previously trained detection models on these unseen attack vectors is poor. In this paper, we focus on: 1) How can we build highly accurate, yet parameter and sample-efﬁcient models for fake speech detection? 2) How can we rapidly adapt detection models to new sources of fake speech? We present four parameter-efﬁcient convolutional architectures for fake speech detection with best detection F1 scores of around 97 points on a large dataset of fake and bonaﬁde speech. We show how the fake speech detection task naturally lends itself to a novel multi-task problem further improving F1 scores for a mere 0. 5% increase in model parameters. Our multi-task setting also helps in data-sparse situations, commonplace in adversarial settings. We investigate an alternative approach to the data-sparsity problem using transfer learning and show that it is possible to meet purely supervised detection performance for unseen attack vectors with as little as 6. 25% of the training data. This is the ﬁrst known application of transfer learning in adversarial settings for speech. Finally, we show how well our transfer learning approach adapts in an instanceefﬁcient way to new attack vectors using the Real-Time Voice Cloning toolkit. We exceed the purely supervised detection performance (99. 18 F1) with as little as 6. 25% of the data.

PDF Details

AAAI Conference 2018 Conference Paper

Listening to the World Improves Speech Command Recognition

Brian McMahan
Delip Rao

We study transfer learning in convolutional network architectures applied to the task of recognizing audio, such as environmental sound events and speech commands. Our key ﬁnding is that not only is it possible to transfer representations from an unrelated task like environmental sound classi- ﬁcation to a voice-focused task like speech command recognition, but also that doing so improves accuracies signiﬁcantly. We also investigate the effect of increased model capacity for transfer learning audio, by ﬁrst validating known results from the ﬁeld of Computer Vision of achieving better accuracies with increasingly deeper networks on two audio datasets: UrbanSound8k and Google Speech Commands. Then we propose a simple multiscale input representation using dilated convolutions and show that it is able to aggregate larger contexts and increase classiﬁcation performance. Further, the models trained using a combination of transfer learning and multiscale input representations need only 50% of the training data to achieve similar accuracies as a freshly trained model with 100% of the training data. Finally, we demonstrate a positive interaction effect for the multiscale input and transfer learning, making a case for the joint application of the two techniques.

PDF Details