Balasubramanian Raman — accepted AI-conference papers

2026

Holonomy Grid Codes for Generalisation Under Directed Actions

ICML 2026poster

Efficient prediction and planning in structured environments often relies on spectral decompositions of transition operators, yet existing grid-cell and successor-representation theories implicitly assume “flat” action geometry where translations commute and a single Fourier eigenbasis suffices. We …

Cited by 0 Source ↗Scholar ↗

2026

VIBE: Disentangling Social Dynamics via Kinematics-Informed Variational Inference for Behavioral Emotion

Abhishek Pratap Singh, Vaibhav Singh, Deepak Kumar, Balasubramanian Raman

ICML 2026poster

Group Emotion Recognition (GER) is crucial for understanding social dynamics, ranging from interpreting intimate conversations to evaluating crowd behavior in large-scale surveillance scenarios. While current AI models can analyze these scenes, they often act as black boxes that take shortcuts. Inst…

Cited by 0 Source ↗Scholar ↗