2 1 4

Mustafa Shukor

mshukor

mshukor

AI & ML interests

None yet

Recent Activity

authored a paper 1 day ago

Rewarded soups: towards Pareto-optimal alignment by interpolating weights fine-tuned on diverse rewards

authored a paper 1 day ago

Implicit Multimodal Alignment: On the Generalization of Frozen LLMs to Multimodal Inputs

authored a paper 1 day ago

Scaling Laws for Native Multimodal Models Scaling Laws for Native Multimodal Models

View all activity

Organizations

Articles 2

Article

Porting Pi0-FAST to LeRobot from JAX to PyTorch: Challenges, Fixes, and Open Questions

Article

144

models 5

mshukor/act_so100_v2_task3_long

Updated 7 days ago • 4

mshukor/act_so100_v2_task2_long

Updated 7 days ago • 4

mshukor/act_so100_v2_task1_long

Updated 7 days ago • 4

mshukor/act_so100_v2_task1

Updated 9 days ago • 5

mshukor/IMA-DePALM

Updated Oct 4, 2024

datasets

None public yet

Mustafa Shukor

AI & ML interests

Recent Activity

Organizations

Articles 2

Porting Pi0-FAST to LeRobot from JAX to PyTorch: Challenges, Fixes, and Open Questions

π0 and π0-FAST: Vision-Language-Action Models for General Robot Control

Papers 6

spaces 4 Sort: Recently updated

UnIVAL

eP-ALM (Audio-Text)

eP-ALM (Video-Text)

eP-ALM (Image-Text)

models 5 Sort: Recently updated

datasets

spaces 4

models 5