Publications

Reverse Personalization

Safe Vision-Language Models via Unsafe Weights Manipulation

Masked Clustering Prediction for Unsupervised Point Cloud Pre-training

Open-World Deepfake Attribution via Confidence-Aware Asymmetric Learning

Wasserstein-Aligned Hyperbolic Multi-View Clustering

A Unified Masked Jigsaw Puzzle Framework for Vision and Language Models

Consistency-Aware Anchor Pyramid Network for Crowd Localization

H2OT: Hierarchical Hourglass Tokenizer for Efficient Video Pose Transformers

Deep Learning-Based Object Pose Estimation: A Comprehensive Survey

Hallucination Early Detection in Diffusion Models

Uncertainty-guided Open-Set Source-Free Unsupervised Domain Adaptation with Target-private Class Segregation

ConViS-Bench: Estimating Video Similarity Through Semantic Concepts

ImageNet-trained CNNs are not biased towards texture: Revisiting feature reliance through controlled suppression

Increasing the Utility of Synthetic Images through Chamfer Guidance

SceneSplat++: A Large Dataset and Comprehensive Benchmark for Language Gaussian Splatting

Towards a General Attention Framework on Gyrovector Spaces for Matrix Manifolds

When Semantics Mislead Vision: Mitigating Large Multimodal Models Hallucinations in Scene Text Spotting and Understanding