4 papers
EgoVLM: Policy Optimization for Egocentric Video Understanding
Ashwin Vinod, Shrey Pandit, Aditya Vavre +1
Emerging embodied AI applications, such as wearable cameras and autonomous agents, have underscored the need for robust reasoning from first person video streams. We introduce EgoV…
Teaching with Lies: Curriculum DPO on Synthetic Negatives for Hallucination Detection
Shrey Pandit, Ashwin Vinod, Liu Leqi +1
Aligning large language models (LLMs) to accurately detect hallucinations remains a significant challenge due to the sophisticated nature of hallucinated text. Recognizing that hal…
Scalable Robust Bayesian Co-Clustering with Compositional ELBOs
Ashwin Vinod, Chandrajit Bajaj
Co-clustering exploits the duality of instances and features to simultaneously uncover meaningful groups in both dimensions, often outperforming traditional clustering in high-dime…
Curvature Informed Furthest Point Sampling
Shubham Bhardwaj, Ashwin Vinod, Soumojit Bhattacharya +3
Point cloud representation has gained traction due to its efficient memory usage and simplicity in acquisition, manipulation, and storage. However, as point cloud sizes increase, e…