ArXiv TLDR

Abhishek Gupta

2 papers · Latest:

Robotics

TMRL: Diffusion Timestep-Modulated Pretraining Enables Exploration for Efficient Policy Finetuning

TMRL introduces diffusion timestep-modulated pretraining to enable efficient exploration and finetuning of robot policies, improving sample efficiency.

2605.12236
Machine Learning

Transferable Physics-Informed Representations via Closed-Form Head Adaptation

Pi-PINN introduces a transferable learning approach for Physics-Informed Neural Networks, enabling faster and more accurate PDE solving via closed-form head adaptation.

2604.21761

📬 Weekly AI Paper Digest

Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.