Shweta Mahajan

36 papers A* 11C 1Journal 20Unranked 2

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	Generative Scenario Rollouts for End-to-End Autonomous Driving. CoRR Rajeev Yasarla, Deepti Hegde, Shizhong Han, Hsin-Pai Cheng, Yunxiao Shi, Meysam Sadeghigooghari, Shweta Mahajan, Apratim Bhattacharyya, Litian Liu, Risheek Garrepalli, Thomas Svantesson, Fatih Porikli, Hong Cai
2025	J	`jnl`	Attention Guided Alignment in Efficient Vision-Language Models. CoRR Shweta Mahajan, Hoang Le, Hyojin Park, Farzad Farhadzadeh, Munawar Hayat, Fatih Porikli
2025	A*	`conf`	Distilling Multi-modal Large Language Models for Autonomous Driving. CVPR Deepti Hegde, Rajeev Yasarla, Hong Cai, Shizhong Han, Apratim Bhattacharyya, Shweta Mahajan, Litian Liu, Risheek Garrepalli, Vishal M. Patel, Fatih Porikli
2025	J	`jnl`	Distilling Multi-modal Large Language Models for Autonomous Driving. CoRR Deepti Hegde, Rajeev Yasarla, Hong Cai, Shizhong Han, Apratim Bhattacharyya, Shweta Mahajan, Litian Liu, Risheek Garrepalli, Vishal M. Patel, Fatih Porikli
2025	J	`jnl`	Do-Undo: Generating and Reversing Physical Actions in Vision-Language Models. CoRR Shweta Mahajan, Shreya Kadambi, Hoang Le, Munawar Hayat, Fatih Porikli
2025	J	`jnl`	DuoLoRA : Cycle-consistent and Rank-disentangled Content-Style Personalization. CoRR Aniket Roy, Shubhankar Borse, Shreya Kadambi, Debasmit Das, Shweta Mahajan, Risheek Garrepalli, Hyojin Park, Ankita Nayak, Rama Chellappa, Munawar Hayat, Fatih Porikli
2025	A*	`conf`	HyperNet Fields: Efficiently Training Hypernetworks without Ground Truth by Learning Weight Trajectories. CVPR Eric Hedlin, Munawar Hayat, Fatih Porikli, Kwang Moo Yi, Shweta Mahajan
2025	J	`jnl`	RoCA: Robust Cross-Domain End-to-End Autonomous Driving. CoRR Rajeev Yasarla, Shizhong Han, Hsin-Pai Cheng, Litian Liu, Shweta Mahajan, Apratim Bhattacharyya, Yunxiao Shi, Risheek Garrepalli, Hong Cai, Fatih Porikli
2024	J	`jnl`	DDIL: Improved Diffusion Distillation With Imitation Learning. CoRR Risheek Garrepalli, Shweta Mahajan, Munawar Hayat, Fatih Porikli
2024	J	`jnl`	HyperNet Fields: Efficiently Training Hypernetworks without Ground Truth by Learning Weight Trajectories. CoRR Eric Hedlin, Munawar Hayat, Fatih Porikli, Kwang Moo Yi, Shweta Mahajan
2024	A*	`conf`	Prompting Hard or Hardly Prompting: Prompt Inversion for Text-to-Image Diffusion Models. CVPR Shweta Mahajan, Tanzila Rahman, Kwang Moo Yi, Leonid Sigal
2024	A*	`conf`	Unsupervised Keypoints from Pretrained Diffusion Models. CVPR Eric Hedlin, Gopal Sharma, Shweta Mahajan, Xingzhe He, Hossam Isack, Abhishek Kar, Helge Rhodin, Andrea Tagliasacchi, Kwang Moo Yi
2024	A*	`conf`	ViVid-1-to-3: Novel View Synthesis with Video Diffusion Models. CVPR Jeong-gi Kwak, Erqun Dong, Yuhe Jin, Hanseok Ko, Shweta Mahajan, Kwang Moo Yi
2024	J	`jnl`	Visual Concept-driven Image Generation with Text-to-Image Diffusion Model. CoRR Tanzila Rahman, Shweta Mahajan, Hsin-Ying Lee, Jian Ren, Sergey Tulyakov, Leonid Sigal
2023	A*	`conf`	Make-A-Story: Visual Memory Conditioned Consistent Story Generation. CVPR Tanzila Rahman, Hsin-Ying Lee, Jian Ren, Sergey Tulyakov, Shweta Mahajan, Leonid Sigal
2023	J	`jnl`	Prompting Hard or Hardly Prompting: Prompt Inversion for Text-to-Image Diffusion Models. CoRR Shweta Mahajan, Tanzila Rahman, Kwang Moo Yi, Leonid Sigal
2023	J	`jnl`	Unsupervised Keypoints from Pretrained Diffusion Models. CoRR Eric Hedlin, Gopal Sharma, Shweta Mahajan, Xingzhe He, Hossam Isack, Abhishek Kar, Helge Rhodin, Andrea Tagliasacchi, Kwang Moo Yi
2023	A*	`conf`	Unsupervised Semantic Correspondence Using Stable Diffusion. NeurIPS Eric Hedlin, Gopal Sharma, Shweta Mahajan, Hossam Isack, Abhishek Kar, Andrea Tagliasacchi, Kwang Moo Yi
2023	J	`jnl`	Unsupervised Semantic Correspondence Using Stable Diffusion. CoRR Eric Hedlin, Gopal Sharma, Shweta Mahajan, Hossam Isack, Abhishek Kar, Andrea Tagliasacchi, Kwang Moo Yi
2023	J	`jnl`	ViVid-1-to-3: Novel View Synthesis with Video Diffusion Models. CoRR Jeong-gi Kwak, Erqun Dong, Yuhe Jin, Hanseok Ko, Shweta Mahajan, Kwang Moo Yi
2022	J	`jnl`	Diverse Image Captioning with Grounded Style. CoRR Franz Klein, Shweta Mahajan, Stefan Roth
2022	J	`jnl`	Make-A-Story: Visual Memory Conditioned Consistent Story Generation. CoRR Tanzila Rahman, Hsin-Ying Lee, Jian Ren, Sergey Tulyakov, Shweta Mahajan, Leonid Sigal
2022	—	`—`	Multimodal Representation Learning for Diverse Synthesis with Deep Generative Models. Shweta Mahajan
2022	—	`ch.`	Multimodales Repräsentationslernen für diversifizierte Synthese. Ausgezeichnete Informatikdissertationen Shweta Mahajan
2021	—	`conf`	Diverse Image Captioning with Grounded Style. GCPR Franz Klein, Shweta Mahajan, Stefan Roth
2021	A*	`conf`	PixelPyramids: Exact Inference Models from Lossless Image Pyramids. ICCV Shweta Mahajan, Stefan Roth
2021	J	`jnl`	PixelPyramids: Exact Inference Models from Lossless Image Pyramids. CoRR Shweta Mahajan, Stefan Roth
2020	A*	`conf`	Diverse Image Captioning with Context-Object Split Latent Spaces. NeurIPS Shweta Mahajan, Stefan Roth
2020	J	`jnl`	Diverse Image Captioning with Context-Object Split Latent Spaces. CoRR Shweta Mahajan, Stefan Roth
2020	A*	`conf`	Latent Normalizing Flows for Many-to-Many Cross-Domain Mappings. ICLR Shweta Mahajan, Iryna Gurevych, Stefan Roth
2020	J	`jnl`	Latent Normalizing Flows for Many-to-Many Cross-Domain Mappings. CoRR Shweta Mahajan, Iryna Gurevych, Stefan Roth
2020	A*	`conf`	Normalizing Flows With Multi-Scale Autoregressive Priors. CVPR Apratim Bhattacharyya, Shweta Mahajan, Mario Fritz, Bernt Schiele, Stefan Roth
2020	J	`jnl`	Normalizing Flows with Multi-Scale Autoregressive Priors. CoRR Shweta Mahajan, Apratim Bhattacharyya, Mario Fritz, Bernt Schiele, Stefan Roth
2019	—	`conf`	Joint Wasserstein Autoencoders for Aligning Multimodal Embeddings. ICCV Workshops Shweta Mahajan, Teresa Botschen, Iryna Gurevych, Stefan Roth
2019	J	`jnl`	Joint Wasserstein Autoencoders for Aligning Multimodal Embeddings. CoRR Shweta Mahajan, Teresa Botschen, Iryna Gurevych, Stefan Roth
2019	C	`conf`	b-it-bots: Our Approach for Autonomous Robotics in Industrial Environments. RoboCup Abhishek Padalkar, Mohammad Wasil, Shweta Mahajan, Ramesh Kumar, Dharmin Bakaraniya, Raghuvir Shirodkar, Heruka Andradi, Deepan Padmanabhan, Carlo Wiesse, Ahmed Faisal Abdelrahman, Sushant Chavan, Naresh Gurulingan, Deebul Nair, Santosh Thoduka, Iman Awaad, Sven Schneider, Paul G. Plöger, Gerhard K. Kraetzschmar