5 papers
What Do They See? Interpreting Complex Road Scenarios Through the Eyes of Vision-Language-Action Models for Safe and Trustworthy Autonomous Vehicle Learning
Kalpana Panda, Wesley Maia, Vinti Agarwal +1
End-to-end autonomous driving models are now able to navigate complex road scenarios, mapping raw sensor observations directly to observed paths for open-loop evaluation and often…
When Prompts Ignore Structure: Graph-Based Attribute Reasoning for Calibrated VLMs
Tanay Sodha, Aditya Sharma, Ramya Hebbalaguppe +2
Reliable confidence estimation remains a key limitation of test-time adaptation in vision-language models (VLMs), where prompt tuning improves zero-shot accuracy but often degrades…
G-Loss: Graph-Guided Fine-Tuning of Language Models
Aditya Sharma, Vinti Agarwal, Rajesh Kumar
Traditional loss functions, including cross-entropy, contrastive, triplet, and su pervised contrastive losses, used for fine-tuning pre-trained language models such as BERT, operat…
ModTGCN: Modularity-aware Graph Neural Networks for Text Classification
Rajarshi Misra, Aditya Sharma, Vinti Agarwal +1
Graph-based text classification models typically rely on local neighborhood aggregation and overlook global community structure, despite semantic document graphs exhibiting strong…
Weak Links in LinkedIn: Enhancing Fake Profile Detection in the Age of LLMs
Apoorva Gulati, Rajesh Kumar, Vinti Agarwal +1
Large Language Models (LLMs) have made it easier to create realistic fake profiles on platforms like LinkedIn. This poses a significant risk for text-based fake profile detectors.…