Author

Nilesh Prasad Pandey

Observed names: Nilesh Pandey, Pandey, Nilesh Prasad

Institution: University of California San Diego

Observed institutions: University of California San Diego, Qualcomm (United States)

ORCID: 0009-0002-1118-0345

Observed ORCID: 0009-0002-1118-0345

OpenAlex ID: A5091385765

A Practical Mixed Precision Algorithm for Post-Training Quantization

2023 · Pandey, Nilesh Prasad, Nagel, Markus, et al. · arXiv (Cornell University) · 31

PDF

Softmax Bias Correction for Quantized Generative Models

2023 · Nilesh Prasad Pandey, Marios Fournarakis, et al. · IEEE International Conference on Computer Vision Workshops · 16

PDF

FouRA: Fourier Low-Rank Adaptation

2024 · Shubhankar Borse, Shreya Kadambi, et al. · neural information processing systems · 11

PDF

Sparse High Rank Adapters

2024 · Kartikeya Bhardwaj, Nilesh Pandey, et al. · neural information processing systems · 11

PDF

Real-Time, Accurate, and Consistent Video Semantic Segmentation via Unsupervised Adaptation and Cross-Unit Deployment on Mobile Device

2022 · Hyojin Park, Alan Yessenbayev, et al. · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · 8

Oh! We Freeze: Improving Quantized Knowledge Distillation via Signal Propagation Analysis for Large Language Models

2024 · Bhardwaj, Kartikeya, Pandey, Nilesh Prasad, et al. · arXiv (Cornell University) · 5

PDF

AgentKVShift: Efficient KV Cache Reuse for Agentic Memory Systems

2026 · Pandey, Nilesh Prasad, Kong, Jason, et al. · arXiv (Cornell University) · 3

PDF

DPQ-HD: Post-Training Compression for Ultra-Low Power Hyperdimensional Computing

2025 · Nilesh Prasad Pandey, Shriniwas Kulkarni, et al. · ACM Great Lakes Symposium on VLSI (GLSVLSI) · 3

QMC: Efficient SLM Edge Inference via Outlier-Aware Quantization and Emergent Memories Co-Design

2026 · Nilesh Prasad Pandey, Jangseon Park, et al. · International Symposium on Low Power Electronics and Design (ISLPED) · 2

A KL Lens on Quantization: Fast, Forward-Only Sensitivity for Mixed-Precision SSM-Transformer Models

2026 · Kong, Jason, Pandey, Nilesh Prasad, et al. · arXiv (Cornell University) · 2

PDF

NgramRL: Accelerating RL Post-Training for Structured Generation via Rollout-Aware N-gram Speculative Decoding

2026 · Pandey, Nilesh Prasad, Park, Jangseon, et al. · arXiv (Cornell University)

PDF

Superposed Inference for Hyperdimensional Computing

2026 · Zhao, Quanling, Pandey, Nilesh Prasad, et al. · arXiv (Cornell University)

PDF

LIMBO: Lifelong Inference-Time Memory and Budget Optimization for LLM Agents

2026 · Sharma, Siddharth, Pandey, Nilesh Prasad, et al. · arXiv (Cornell University)

PDF

Works count: 13

Citation count: 92

H-index: 5

I10-index: 4