Institution profile

Georgia Tech Research Institute

Academic institutionnorthamerica · us
Official website
Research library27linked papers
Opportunities0open roles
Selected work

Representative Papers

CF-JEPA: Improving Robustness of JEPA World Models via Controllability Factorization

Sep 30, 2026

This study addresses the vulnerability of JEPA-based world models to distractor signals in visual control, which often leads to latent space collapse. To this end, we propose CF-JEPA, a framework built upon a JEPA-style latent world model with a pixel-reconstruction-free self-supervised architecture. By introducing a controllability factorization mechanism, CF-JEPA explicitly decomposes the latent space into controllable and uncontrollable subspaces, effectively isolating distracting information while extracting task-relevant features for control. Experimental results demonstrate that CF-JEPA achieves performance comparable to conventional methods under nominal conditions while significantly outperforming them in the presence of distractors. Notably, it is the only approach capable of preventing latent space collapse. Furthermore, its practical utility is validated through simulated robotic tasks.

0 citationsRead paper

Reward as Observation: Learning Reward-Based Policies for Rapid Adaptation

Sep 30, 2026

This study addresses the challenge of zero-shot transfer for deep policies in novel environments with significantly divergent observation spaces. Departing from conventional reliance on observational inputs, this work introduces a pioneering training algorithm for purely reward-action-conditioned policies. By conditioning solely on reward signals and actions, the proposed policy executes decision-making without accessing raw observations, leveraging source-domain experience to guide training in target environments. The effectiveness of this approach is validated across diverse simulated and real-world robotic scenarios, demonstrating successful zero-shot adaptation and performance improvements across heterogeneous observations, such as varying rendering styles. Ultimately, this research establishes a new paradigm for cross-domain transfer in reinforcement learning by eliminating the dependency on consistent observation representations.

0 citationsRead paper
Recent publications

Latest Papers

CF-JEPA: Improving Robustness of JEPA World Models via Controllability Factorization

Sep 30, 2026

This study addresses the vulnerability of JEPA-based world models to distractor signals in visual control, which often leads to latent space collapse. To this end, we propose CF-JEPA, a framework built upon a JEPA-style latent world model with a pixel-reconstruction-free self-supervised architecture. By introducing a controllability factorization mechanism, CF-JEPA explicitly decomposes the latent space into controllable and uncontrollable subspaces, effectively isolating distracting information while extracting task-relevant features for control. Experimental results demonstrate that CF-JEPA achieves performance comparable to conventional methods under nominal conditions while significantly outperforming them in the presence of distractors. Notably, it is the only approach capable of preventing latent space collapse. Furthermore, its practical utility is validated through simulated robotic tasks.

0 citationsRead paper

Reward as Observation: Learning Reward-Based Policies for Rapid Adaptation

Sep 30, 2026

This study addresses the challenge of zero-shot transfer for deep policies in novel environments with significantly divergent observation spaces. Departing from conventional reliance on observational inputs, this work introduces a pioneering training algorithm for purely reward-action-conditioned policies. By conditioning solely on reward signals and actions, the proposed policy executes decision-making without accessing raw observations, leveraging source-domain experience to guide training in target environments. The effectiveness of this approach is validated across diverse simulated and real-world robotic scenarios, demonstrating successful zero-shot adaptation and performance improvements across heterogeneous observations, such as varying rendering styles. Ultimately, this research establishes a new paradigm for cross-domain transfer in reinforcement learning by eliminating the dependency on consistent observation representations.

0 citationsRead paper