6 papers
Toward IIT-Inspired Consciousness in LLMs: A Reward-Based Learning Framework
Hamid Reza Akbari, Mohammad Hossein Sameti, Amir M. Mansourian +2
The pursuit of Artificial General Intelligence (AGI) is a central goal in language model development, in which consciousness-like processing could serve as a key facilitator. While…
Enriching Knowledge Distillation with Cross-Modal Teacher Fusion
Amir M. Mansourian, Amir Mohammad Babaei, Shohreh Kasaei
Multi-teacher knowledge distillation (KD), a more effective technique than traditional single-teacher methods, transfers knowledge from expert teachers to a compact student model u…
A Comprehensive Survey on Knowledge Distillation
Amir M. Mansourian, Rozhan Ahmadi, Masoud Ghafouri +8
Deep Neural Networks (DNNs) have achieved notable performance in the fields of computer vision and natural language processing with various applications in both academia and indust…
No Concept Left Behind: Test-Time Optimization for Compositional Text-to-Image Generation
Mohammad Hossein Sameti, Amir M. Mansourian, Arash Marioriyad +3
Despite recent advances in text-to-image (T2I) models, they often fail to faithfully render all elements of complex prompts, frequently omitting or misrepresenting specific objects…
Attention-guided Feature Distillation for Semantic Segmentation
Amir M. Mansourian, Arya Jalali, Rozhan Ahmadi +1
Deep learning models have achieved significant results across various computer vision tasks. However, due to the large number of parameters in these models, deploying them in real-…
Improving Weakly-supervised Video Instance Segmentation by Leveraging Spatio-temporal Consistency
Farnoosh Arefi, Amir M. Mansourian, Shohreh Kasaei
The performance of Video Instance Segmentation (VIS) methods has improved significantly with the advent of transformer networks. However, these networks often face challenges in tr…