Kanishk Jain

Kanishk Jain

I am an AI researcher at Emory University. My work builds data-driven models for high-dimensional time series, animal behavior, neural dynamics, and test-time compute for language models.

I am currently a postdoctoral researcher in Tankut Can's group, working on controllable test-time compute and open-weights language model evaluation.

Previously, I completed my PhD in Physics at Emory with Gordon Berman, developing recurrent neural-network pipelines for behavior and gait dynamics.

Resume Scholar GitHub LinkedIn Email

Research

I am interested in compact representations of complex temporal structure: how to extract interpretable signals from noisy, high-dimensional measurements, and how those signals can reveal individual differences, physiological state, or controllable model behavior.

Recent work includes prompt re-tokenization for output diversity and scalable test-time compute experiments with open-weights language models.

Selected Publications

  1. Kanishk Jain, Matthew Day, and Tankut Can. Generating output diversity from prompt re-tokenization. Workshop on Scientific Methods for Understanding Deep Learning, ICLR 2026. link
  2. Taniel Winner, Michael Rosenberg, Kanishk Jain, Trisha Kesar, Lina Ting, and Gordon Berman. Discovering individual-specific gait signatures from data-driven models of neuromechanical dynamics. PLOS Computational Biology, 19(10), 2023. doi:10.1371/journal.pcbi.1011556
  3. Kanishk Jain and Gordon Berman. Opening the black box of social behavior. Nature Neuroscience, 22, 1947-1948, 2019. doi:10.1038/s41593-019-0547-4
  4. Promit Moitra, Kanishk Jain, and Sudeshna Sinha. Anticipating persistent infection. EPL, 121(6), 2018. doi:10.1209/0295-5075/121/60001
  5. Kristin Kovach, Megan Davis-Fields, Yasuhiko Irie, Kanishk Jain, et al. Evolutionary adaptations of biofilms infecting cystic fibrosis lungs promote mechanical toughness by adjusting polysaccharide production. npj Biofilms and Microbiomes, 2016. doi:10.1038/s41522-016-0007-9