works on

From the 1 of 6 linked papers with an AI index.

activity
20242026
collaborators

6 papers

cs.LG2026

Augmentations for Robust and Efficient Imitation Learning in Streamed Video Games

Somjit Nath, Abdelhak Lemkhenter, Pallavi Choudhury +4

The paper introduces spatiotemporal data augmentations that mimic streaming artifacts (pixelation, blur, ghosting, etc.) to improve the robustness and efficiency of imitation‑learn…

cs.LG2026

When Does Predictive Inverse Dynamics Outperform Behavior Cloning?

Lukas Schäfer, Pallavi Choudhury, Abdelhak Lemkhenter +10

Behavior cloning (BC) is a practical offline imitation learning method, but it often fails when expert demonstrations are limited. Recent works have introduced a class of architect…

cs.LG2026

Structured Representation Learning with Locally Linear Embeddings and Adaptive Feature Fusion

Somjit Nath, Jackson J Cone, Derek Nowrouzezahrai +1

Neuroscientific research has revealed that the brain encodes complex behaviors by leveraging structured, low-dimensional manifolds and dynamically fusing multiple sources of inform…

cs.GR2026

The Invisible Hand of Physics: When Video Diffusion Models Know More Than They Show

Parsa Esmati, Somjit Nath, Katja Hofmann +3

Modern video diffusion models generate increasingly realistic and temporally coherent videos, motivating their use as candidate world simulators. Yet it remains unclear whether the…

cs.AI2025

Behaviour Discovery and Attribution for Explainable Reinforcement Learning

Rishav Rishav, Somjit Nath, Vincent Michalski +1

Building trust in reinforcement learning (RL) agents requires understanding why they make certain decisions, especially in high-stakes applications like robotics, healthcare, and f…

cs.LG2024

Unsupervised Event Outlier Detection in Continuous Time

Somjit Nath, Yik Chau Lui, Siqi Liu

Event sequence data record the occurrences of events in continuous time. Event sequence forecasting based on temporal point processes (TPPs) has been extensively studied, but outli…