Author

Muhammad Burhan Hafez

3 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Oct 2026

DreamFormer: Dream Imitation with a Transformer World Model for Language-Conditioned Robotic Manipulation

DreamFormer first learns a task-agnostic Transformer world model from unstructured play data, then acquires task-specific behaviors by optimizing an intrinsic reward that aligns agent-generated rollouts with expert demonstrations within the latent imagination of a learned world model.

Mostafa Kotb, C. Weber, Muhammad Burhan Hafez et al. · 0 citations

Preprint Sep 2026

Storing Is Not Remembering: LSTM-UT and Bounded Gated Memory for Looped Transformers

In OpenWebText2 language modelling, LSTM-UT outperforms CoTFormer and, at equal width, reaches slightly lower perplexity than CoTFormer while CoTFormer needs up to 91% more training time per step; against a parameter-matched CoTFormer, LSTM-UT comes within 0.6 perplexity.

Aras Kavuncu, Muhammad Burhan Hafez · 0 citations

Preprint Sep 2026

REDACT: Robust Perceptive Locomotion under Unseen Visual Corruption

Depth-conditioned locomotion policies have demonstrated impressive agile maneuvers, but can be steered to unpredictable actions when observations are outside their training distribution. Occlusion, invalid returns, sensor noise, and visual distractors can shift deployment observations away from nominal simulated depth....

Natapat Kirdwichai, Tobias Driskell-Poole, Andrei Sontea et al. · 0 citations