Research
- My PhD is focused on developing algorithms, architectures and abstractions for endowing neural networks with a human-like understanding of the world. To this end, I focus on key tenets of human intelligence, i.e., data-efficiency, compositional generalization, counterfactual thinking, long-context understanding and interpretability.
- Also on Google Scholar
Publications
Neural Slot Interpreters: Grounding Object Semantics in Emergent Slot Representations
Bhishma Dedhia, Niraj K Jha
Preprint, Under Submission
[pdf]
Bhishma Dedhia, Niraj K Jha
Preprint, Under Submission
[pdf]
Whittle Index based Age-of-Information Aware Scheduling for Markovian Channels
B Sombabu, Bhishma Dedhia, Sharayu Moharir
Computer Networks and Communications 2023
[wiserpub] [pdf]
B Sombabu, Bhishma Dedhia, Sharayu Moharir
Computer Networks and Communications 2023
[wiserpub] [pdf]
Saliency-driven rate-distortion optimization for 360-degree image coding
Jui-Chiu Chiang, Cheng-Yu Yang, Bhishma Dedhia, Yi-Fan Char
Multimedia Tools and Applications 2021
[springer]
Jui-Chiu Chiang, Cheng-Yu Yang, Bhishma Dedhia, Yi-Fan Char
Multimedia Tools and Applications 2021
[springer]
Saliency Prediction for Omnidirectional Images Considering Optimization on Sphere Domain
Bhishma Dedhia, Jui-Chiu Chiang, Yi-Fan Char
International Conference on Acoustics, Speech and Signal Processing (ICASSP) 2019
[arXiv] [pdf]
Bhishma Dedhia, Jui-Chiu Chiang, Yi-Fan Char
International Conference on Acoustics, Speech and Signal Processing (ICASSP) 2019
[arXiv] [pdf]
* Equal contribution