Subhankar Mishra Lab Weekly Talks
RSS FeedOn this site, you can find the files of the talks & presentations by our lab members and interns on various Machine Learning or Computer Science topics.
Feel free to reach out to us on any of our socials below.
Recent Talks
Data Re-uploading For A Universal Quantum Classifier
Haribandhu JenaPublished: at 08:30 AMA single qubit can act as a universal quantum classifier when combined with a classical subroutine, using data re-uploading to overcome its limitations. By repeatedly uploading data and applying single-qubit operations, it can handle multi-dimensional inputs and classify multiple categories. Extending this to multi-qubit systems with entanglement further enhances its efficiency. Benchmarking results confirm its capability to classify complex data effectively.
NeoBERT
Adhilsha AnsadPublished: at 08:00 AMIn this talk, I introduce NeoBERT, a next-generation encoder that redefines bidirectional modeling through state-of-the-art architectural improvements, modern data strategies, and optimized pre-training.
Quantum Implicit Neural Representations
Haribandhu JenaPublished: at 07:00 PMThis short talk discusses QIREN. QIREN is a quantum generalization of Fourier Neural Networks (FNNs) for implicit neural representations, offering a quantum advantage in modeling high-frequency signal components. It outperforms SoTA models in signal representation, image superresolution, and image generation.
Large Concept Models
Adhilsha AnsadPublished: at 07:00 PMThis talk will will explore the training objectives, segmentation techniques, and generation strategies of Large Concept Models (LCMs). LCMs are a novel class of models that leverage sentence-level tokenization to represent concepts, a higher abstraction than current tokens. We will also discuss the quantization of LCMs and their potential applications in various domains.
The Expressive Power of GNNs
Pankaj KumarPublished: at 02:00 PMThis talk delves into the theoretical foundations of Graph Neural Networks (GNNs), focusing on their ability to model complex relationships between node features and graph structures. While GNNs excel in tasks like node classification and link prediction, their expressive power remains challenging to quantify due to the interplay of graph topology and node features. The discussion highlights key challenges, such as trade-offs between expressiveness and computational efficiency, and explores advancements like the connection between GNNs and the Weisfeiler-Lehman graph isomorphism test. The talk also outlines future directions for developing rigorous evaluation methods to better understand and assess GNN expressivity.