2025
Towards Physical Understanding in Video Generation: A 3D Point Regularization Approach.
CoRR, February, 2025

Lightweight Predictive 3D Gaussian Splats.
Proceedings of the Thirteenth International Conference on Learning Representations, 2025

2024
SnapGen-V: Generating a Five-Second Video within Five Seconds on a Mobile Device.
CoRR, 2024

SnapGen: Taming High-Resolution Text-to-Image Models for Mobile Devices with Efficient Architectures and Training.
CoRR, 2024

Scalable Ranked Preference Optimization for Text-to-Image Generation.
CoRR, 2024

SF-V: Single Forward Video Generation Model.
Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, 2024

BitsFusion: 1.99 bits Weight Quantization of Diffusion Model.
Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, 2024

AsCAN: Asymmetric Convolution-Attention Networks for Efficient Recognition and Generation.
Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, 2024

Snap Video: Scaled Spatiotemporal Transformers for Text-to-Video Synthesis.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024

TextCraftor: Your Text Encoder can be Image Quality Controller.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024

2023
Efficient Edge Inference by Selective Query.
Proceedings of the Eleventh International Conference on Learning Representations, 2023

Scaffolding a Student to Instill Knowledge.
Proceedings of the Eleventh International Conference on Learning Representations, 2023

2022
Condensing CNNs with Partial Differential Equations.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022

2021
Online Selective Classification with Limited Feedback.
Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Training Recurrent Neural Networks via Forward Propagation Through Time.
Proceedings of the 38th International Conference on Machine Learning, 2021

Time Adaptive Recurrent Neural Network.
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2021

Selective Classification via One-Sided Prediction.
Proceedings of the 24th International Conference on Artificial Intelligence and Statistics, 2021

2020
RNNs Incrementally Evolving on an Equilibrium Manifold: A Panacea for Vanishing and Exploding Gradients?
Proceedings of the 8th International Conference on Learning Representations, 2020

2019
RNNs Evolving on an Equilibrium Manifold: A Panacea for Vanishing and Exploding Gradients?
CoRR, 2019

Equilibrated Recurrent Neural Network: Neuronal Time-Delayed Self-Feedback Improves Accuracy and Stability.
CoRR, 2019

BLAS-on-flash: An Efficient Alternative for Large Scale ML Training and Inference?
Proceedings of the 16th USENIX Symposium on Networked Systems Design and Implementation, 2019

2018
Parabel: Partitioned Label Trees for Extreme Classification with Application to Dynamic Search Advertising.
Proceedings of the 2018 World Wide Web Conference on World Wide Web, 2018

Extreme Multi-label Learning with Label Features for Warm-start Tagging, Ranking & Recommendation.
Proceedings of the Eleventh ACM International Conference on Web Search and Data Mining, 2018