Sakshi Choudhary

According to our database, Sakshi Choudhary authored at least 11 papers between 2023 and 2026.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2026

OASIS: Online Activation Subspace Learning for Memory-Efficient Training.

Sakshi Choudhary, Utkarsh Saxena, Kaushik Roy

CoRR, April, 2026

Learning When to Attend: Conditional Memory Access for Long-Context LLMs.

Sakshi Choudhary, Aditya Chattopadhyay, Luca Zancato, Elvis Nunez, Matthew Trager, Wei Xia, Stefano Soatto

CoRR, March, 2026

Achieving Global Flatness in Decentralized Learning with Heterogeneous Data.

Sakshi Choudhary, Sai Aparna Aketi, Kaushik Roy

Trans. Mach. Learn. Res., 2026

Mode-Dependent Statistical Characteristics of Speckle Patterns From Structured Light Beams.

Harsh Vardhan, Aswathi K. Sivarajan, Sakshi Choudhary, Gangi Reddy Salla, Ravi Kumar

IEEE Access, 2026

2025

TRIM: Token-wise Attention-Derived Saliency for Data-Efficient Instruction Tuning.

Manish Nagaraj, Sakshi Choudhary, Utkarsh Saxena, Deepak Ravikumar, Kaushik Roy

CoRR, October, 2025

SADDLe: Sharpness-Aware Decentralized Deep Learning with Heterogeneous Data.

Sakshi Choudhary, Sai Aparna Aketi, Kaushik Roy

Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, 2025

CODE-CL: Conceptor-Based Gradient Projection for Deep Continual Learning.

Marco Paul E. Apolinario, Sakshi Choudhary, Kaushik Roy

Proceedings of the IEEE/CVF International Conference on Computer Vision, 2025

2024

CoDeC: Communication-Efficient Decentralized Continual Learning.

Sakshi Choudhary, Sai Aparna Aketi, Gobinda Saha, Kaushik Roy

Trans. Mach. Learn. Res., 2024

Averaging Rate Scheduler for Decentralized Learning on Heterogeneous Data.

Sai Aparna Aketi, Sakshi Choudhary, Kaushik Roy

Proceedings of the Second Tiny Papers Track at ICLR 2024, 2024

Eigen Attention: Attention in Low-Rank Space for KV Cache Compression.

Utkarsh Saxena, Gobinda Saha, Sakshi Choudhary, Kaushik Roy

Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2024, 2024

2023

A 65 nm 1.4-6.7 TOPS/W Adaptive-SNR Sparsity-Aware CIM Core with Load Balancing Support for DL workloads.

Mustafa Fayez Ali, Indranil Chakraborty, Sakshi Choudhary, Muya Chang, Dong Eun Kim, Arijit Raychowdhury, Kaushik Roy

Proceedings of the IEEE Custom Integrated Circuits Conference, 2023