Nandan Kumar Jha

nandan523's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes

commented a paper 2 days ago

Entropy-Guided Attention for Private LLMs

Paper • 2501.03489 • Published 6 days ago • 12 •

5

authored a paper 3 days ago

Entropy-Guided Attention for Private LLMs

Paper • 2501.03489 • Published 6 days ago • 12

commented a paper 3 days ago

Entropy-Guided Attention for Private LLMs

Paper • 2501.03489 • Published 6 days ago • 12 •

5

authored a paper 3 months ago

AERO: Softmax-Only LLMs for Efficient Private Inference

Paper • 2410.13060 • Published Oct 16, 2024 • 4

commented 2 papers 3 months ago

AERO: Softmax-Only LLMs for Efficient Private Inference

Paper • 2410.13060 • Published Oct 16, 2024 • 4 •

2

ReLU's Revival: On the Entropic Overload in Normalization-Free Large Language Models

Paper • 2410.09637 • Published Oct 12, 2024 • 3 •

2

authored 13 papers 3 months ago

DeepReShape: Redesigning Neural Networks for Efficient Private Inference

Paper • 2304.10593 • Published Apr 20, 2023

ReLU's Revival: On the Entropic Overload in Normalization-Free Large Language Models

Paper • 2410.09637 • Published Oct 12, 2024 • 3

Circa: Stochastic ReLUs for Private Deep Learning

Paper • 2106.08475 • Published Jun 15, 2021

Sisyphus: A Cautionary Tale of Using Low-Degree Polynomial Activations in Privacy-Preserving Deep Learning

Paper • 2107.12342 • Published Jul 26, 2021

CryptoNite: Revealing the Pitfalls of End-to-End Private Inference at Scale

Paper • 2111.02583 • Published Nov 4, 2021

Modeling Data Reuse in Deep Neural Networks by Taking Data-Types into Cognizance

Paper • 2008.02565 • Published Aug 6, 2020

DeepPeep: Exploiting Design Ramifications to Decipher the Architecture of Compact DNNs

Paper • 2007.15248 • Published Jul 30, 2020

DeepReDuce: ReLU Reduction for Fast Private Inference

Paper • 2103.01396 • Published Mar 2, 2021

On the Demystification of Knowledge Distillation: A Residual Network Perspective

Paper • 2006.16589 • Published Jun 30, 2020

DRACO: Co-Optimizing Hardware Utilization, and Performance of DNNs on Systolic Accelerator

Paper • 2006.15103 • Published Jun 26, 2020

ULSAM: Ultra-Lightweight Subspace Attention Module for Compact Convolutional Neural Networks

Paper • 2006.15102 • Published Jun 26, 2020

E2GC: Energy-efficient Group Convolution in Deep Neural Networks

Paper • 2006.15100 • Published Jun 26, 2020

The Ramifications of Making Deep Neural Networks Compact

Paper • 2006.15098 • Published Jun 26, 2020