works on

From the 2 of 62 linked papers with an AI index.

activity
20242026
most citedA Forward Reachability Perspective on Control Barrier Functions and Discount Factors in Reachability Analysis

3 citations · 3 across the 19 of their papers we have counts for

collaborators
Showing cs.LGShow all

6 papers · 1 filter

cs.LG2026

ODEWorld: A Continuous Predictive Architecture via Physical-Time Flow

Dongxiu Liu, Haoyi Niu, Peng Cheng +5

The paper presents ODEWorld, a continuous-time latent world model that learns a physical-time flow using ODEs to predict future states at arbitrary temporal resolutions, improving…

cs.LG2026

WOMBET: World Model-Based Experience Transfer for Robust and Sample-efficient Reinforcement Learning

Mintae Kim, Koushil Sreenath

Reinforcement learning (RL) in robotics is often limited by the cost and risk of data collection, motivating experience transfer from a source task to a target task. Offline-to-onl…

cs.LG2026

Embedding Hybrid Systems into Continuous Latent Vector Fields

Sangli Teng, Hang Liu, Koushil Sreenath

This work proves that an -dimensional hybrid system can be embedded into an -dimensional Euclidean space equipped with a continuous vector field on its embedded image wheneve…

cs.LG2026

Robust Adversarial Policy Optimization Under Dynamics Uncertainty

Mintae Kim, Koushil Sreenath

Reinforcement learning (RL) policies often fail under dynamics that differ from training, a gap not fully addressed by domain randomization or existing adversarial RL methods. Dist…

cs.LG2025

CHyLL: Learning Continuous Neural Representations of Hybrid Systems

Sangli Teng, Hang Liu, Jingyu Song +1

Learning the flows of hybrid systems that have both continuous and discrete time dynamics is challenging. The existing method learns the dynamics in each discrete mode, which suffe…

cs.LG2024

Safety Filters for Black-Box Dynamical Systems by Learning Discriminating Hyperplanes

Will Lavanakul, Jason J. Choi, Koushil Sreenath +1

Learning-based approaches are emerging as an effective approach for safety filters for black-box dynamical systems. Existing methods have relied on certificate functions like Contr…