3 papers
cs.LG2026
Compositional Objectives: Learning Structure in Structure
Pranavchandra Vivekananda, Sumukh Bettadapura, Ajan Subramanian
Intelligence is defined in many ways. One of these definitions defines intelligence as the pursuit of learnable novelty. However, learnable novelty can be meaningless without the a…
cs.CL2026
Riding Brainwaves in LLM Space: Understanding Activation Patterns Using Individual Neural Signatures
Ajan Subramanian, Sumukh Bettadapura, Rohan Sathish
Consumer-grade EEG is entering everyday devices, from earbuds to headbands, raising the question of whether language models can be adapted to individual neural responses. We test t…
cs.CV2026
Real Eyes Realize Faster: Gaze Stability and Pupil Novelty for Efficient Egocentric Learning
Ajan Subramanian, Sumukh Bettadapura, Rohan Sathish
Always-on egocentric cameras are increasingly used as demonstrations for embodied robotics, imitation learning, and assistive AR, but the resulting video streams are dominated by r…