About me

I am a Ph.D. student in the computer science department at Indiana University. I am broadly interested in cognitive mechanisms that enable intelligent systems to develop general-purpose capabilities.

Outside work, I like to bike with friends, find new coffee shops to work at, and dream of building generalist models that are better understood by us.

Interests-

• Machine Learning
• Computational Cognitive Neuroscience

Publications-

• Sahaj Singh Maini, and Zoran Tiganj. “Reinforcement Learning with Adaptive Temporal Discounting.” Reinforcement Learning Conference 2025. pdf
• Deven Mistry, Anooshka Bajaj, Yash Aggarwal, Sahaj Singh Maini, Zoran Tiganj. 2024. “Emergence of episodic memory in LLMs: Characterizing changes in temporal structure of attention scores during training.” pdf (accepted to NAACL 2025)
• Billy Dickson*, Sahaj Singh Maini*, Robert Nosofsky, and Zoran Tiganj. 2024. “Comparing Perceptual Judgments in Large Multimodal Models and Humans.” PsyArXiv. July 4. doi:10.31234/osf.io/pcmrj. pdf (accepted to Behavior Research Methods)
• Saber Sheybani, Sahaj Singh Maini, Aravind Dendukuri, Zoran Tiganj, and Linda B. Smith. 2024. “Modelvsbaby: A Developmentally Motivated Benchmark of Out-of-distribution Object Recognition.” PsyArXiv. May 21. doi:10.31234/osf.io/83gae. pdf (Presented at ICDL 2024 as a poster)
• Sahaj Singh Maini, James Mochizuki-Freeman, Chirag Shankar Indi, Brandon G. Jacques, Per B. Sederberg, Marc W. Howard, and Zoran Tiganj. “Representing Latent Dimensions Using Compressed Number Lines.” 2023 International Joint Conference on Neural Networks (IJCNN). IEEE, 2023. pdf
• James Mochizuki-Freeman, Sahaj Singh Maini, and Zoran Tiganj. “Characterizing neural activity in cognitively inspired RL agents during an evidence accumulation task.” 2023 International Joint Conference on Neural Networks (IJCNN). IEEE, 2023. pdf
• Sahaj Singh Maini, James Mochizuki-Freeman, Chirag Shankar Indi, Brandon G Jacques, Per B Sederberg, Marc Howard, & Zoran Tiganj (2022). Constructing compressed number lines of latent variables using a cognitive model of memory and deep neural networks. In NeurIPS 2022 Memory in Artificial and Real Intelligence workshop. pdf
• James Mochizuki-Freeman, Sahaj Singh Maini, & Zoran Tiganj (2022). Evidence accumulation in deep RL agents powered by a cognitive model. In NeurIPS 2022 Memory in Artificial and Real Intelligence workshop. pdf
• Sahaj Singh Maini, Louis Francis Labuzienski, Saurabh Gulati, and Zoran Tiganj. “Comparing Impact of Time Lag and Item Lag in Relative Judgment of Recency.” Proceedings of the Annual Meeting of the Cognitive Science Society. Vol. 44. No. 44. 2022. pdf
• Selahattin Akkas, Sahaj Singh Maini, and Judy Qiu. “A Fast Video Image Detection using TensorFlow Mobile Networks for Racing Cars.” 2019 IEEE International Conference on Big Data (Big Data). IEEE, 2019. pdf