Private AI | Nandan Kumar Jha

AERO: Entropy-Guided Attention for Private LLM Inference

Mon, 01 Jun 2026 00:00:00 +0000

The AERO line grew through several peer-reviewed workshop versions before the current under-review manuscript:

Regularizing the Entropy Landscape of Self-Attention: Towards a Soft Inductive Bias in LLMs, OPT Workshop at NeurIPS 2025. Workshop · OpenReview
ReLU’s Revival: On the Entropic Overload in Normalization-Free Large Language Models, ATTRIB Workshop at NeurIPS 2024. Workshop · arXiv · Code
Entropy-Guided Attention for Private LLMs, PPAI Workshop at AAAI 2025. arXiv · Code · Press release

Entropy and Private Language Models

Tue, 01 Apr 2025 14:00:00 +0000

Invited seminar in the CILVR Seminar Series at NYU Center for Data Science, discussing entropy dynamics and efficient private language-model inference.

Entropy-Guided Attention for Private LLMs

Wed, 01 Jan 2025 00:00:00 +0000

Fireside chat on entropy-guided attention mechanisms and efficient private LLM inference.

Private AI | Nandan Kumar Jha

AERO: Entropy-Guided Attention for Private LLM Inference

Related workshop versions

Entropy and Private Language Models

Entropy-Guided Attention for Private LLMs