Senthil Purushwalkam

10

Papers

47

Total Citations

Papers (10)

FaithEval: Can Your Language Model Stay Faithful to Context, Even If "The Moon is Made of Marshmallows"

Trust but Verify: Programmatic VLM Evaluation in the Wild

Task-Driven Modular Networks for Zero-Shot Compositional Learning

The Functional Correspondence Problem

Aligning Videos in Space and Time

The Challenges of Continuous Self-Supervised Learning

Audio-Visual Floorplan Reconstruction

Diffusion Model Alignment Using Direct Preference Optimization

Demystifying Contrastive Self-Supervised Learning: Invariances, Augmentations and Dataset Biases

ConRad: Image Constrained Radiance Fields for 3D Generation from a Single Image