activity
20192026
most citedDiverse Image Captioning with Context-Object Split Latent Spaces

25 citations · 33 across the 18 of their papers we have counts for

collaborators

19 papers

cs.CV2026

Streaming Interventions: Can Video Large Language Models Correct Mistakes as They Occur?

Apratim Bhattacharyya, Shweta Mahajan, Sanjay Haresh +5

Learning everyday skills, like cooking a dish, relies increasingly on instructional media such as online videos. This opens the door to the use of video (and multimodal) large lang…

cs.CV2026

Generative Scenario Rollouts for End-to-End Autonomous Driving

Rajeev Yasarla, Deepti Hegde, Shizhong Han +10

Vision-Language-Action (VLA) models are emerging as highly effective planning models for end-to-end autonomous driving systems. However, current works mostly rely on imitation lear…

cs.CV2025

Do-Undo Bench: Reversibility for Action Understanding in Image Generation

Shweta Mahajan, Shreya Kadambi, Hoang Le +4

We introduce the Do-Undo task and benchmark to address a critical gap in vision-language models: understanding and generating plausible scene transformations driven by real-world a…

cs.CV2025

Attention Guided Alignment in Efficient Vision-Language Models

Shweta Mahajan, Hoang Le, Hyojin Park +3

Large Vision-Language Models (VLMs) rely on effective multimodal alignment between pre-trained vision encoders and Large Language Models (LLMs) to integrate visual and textual info…

cs.CV2025

RoCA: Robust Cross-Domain End-to-End Autonomous Driving

Rajeev Yasarla, Shizhong Han, Hsin-Pai Cheng +7

End-to-end (E2E) autonomous driving has recently emerged as a new paradigm, offering significant potential. However, few studies have looked into the practical challenge of deploym…

cs.GR2025

DuoLoRA : Cycle-consistent and Rank-disentangled Content-Style Personalization

Aniket Roy, Shubhankar Borse, Shreya Kadambi +8

We tackle the challenge of jointly personalizing content and style from a few examples. A promising approach is to train separate Low-Rank Adapters (LoRA) and merge them effectivel…