Jyothir S V — accepted AI-conference papers

2025

Hierarchical World Models as Visual Whole-Body Humanoid Controllers

Nicklas Hansen, Jyothir S V, Vlad Sobal, Yann LeCun, Xiaolong Wang, Hao Su

ICLR 2025poster

Whole-body control for humanoids is challenging due to the high-dimensional nature of the problem, coupled with the inherent instability of a bipedal morphology. Learning from visual observations further exacerbates this difficulty. In this work, we explore highly data-driven approaches to visual wh…

Cited by 5 Source ↗PDF ↗Scholar ↗

2025

Recite, Reconstruct, Recollect: Memorization in LMs as a Multifaceted Phenomenon

USVSN Sai Prashanth, Alvin Deng, Kyle O'Brien, Jyothir S V, Mohammad Aflah Khan, Jaydeep Borkar +6

ICLR 2025poster

Memorization in language models is typically treated as a homogenous phenomenon, neglecting the specifics of the memorized data. We instead model memorization as the effect of a set of complex factors that describe each sample and relate it to the model and corpus. To build intuition around these fa…

Cited by 3 Source ↗PDF ↗code ↗Scholar ↗