NP
Nilesh Prasad Pandey
cs.LGcs.AIcs.CVcs.CL
On Valency
published · living versionsW_f3e535hw·v1 · currentpublished
NgramRL: Accelerating RL Post-Training for Structured Generation via Rollout-Aware N-gram Speculative Decoding
with Jangseon Park, Jason Kong, Onat Gungor, Tajana Rosing
1 version
Preprints & journals
11 papers in the corpus · 2023–2026Superposed Inference for Hyperdimensional Computing2609.32320v1 · Quanling Zhao, Nilesh Prasad Pandey, Ye Tian et al.2026 · 0 citationsarXiv
LIMBO: Lifelong Inference-Time Memory and Budget Optimization for LLM Agents2609.14138v1 · Siddharth Sharma, Nilesh Prasad Pandey, Onat Gungor et al.2026 · 0 citationsarXiv
AgentKVShift: Efficient KV Cache Reuse for Agentic Memory Systems2607.21604v1 · Nilesh Prasad Pandey, Jason Kong, Lanxiang Hu et al.2026 · 0 citationsarXiv
A KL Lens on Quantization: Fast, Forward-Only Sensitivity for Mixed-Precision SSM-Transformer Models2604.13440v1 · Jason Kong, Nilesh Prasad Pandey, Flavio Ponzina et al.2026 · 0 citationsarXiv
QMC: Efficient SLM Edge Inference via Outlier-Aware Quantization and Emergent Memories Co-Design2601.14549v1 · Nilesh Prasad Pandey, Jangseon Park, Onat Gungor et al.2026 · 0 citationsarXiv
DPQ-HD: Post-Training Compression for Ultra-Low Power Hyperdimensional Computing2505.05413v1 · Nilesh Prasad Pandey, Shriniwas Kulkarni, David Wang et al.2025 · 2 citationsarXiv
Sparse High Rank Adapters2406.13175v2 · Kartikeya Bhardwaj, Nilesh Prasad Pandey, Sweta Priyadarshi et al.2024 · 3 citationsarXiv
FouRA: Fourier Low Rank Adaptation2406.08798v1 · Shubhankar Borse, Shreya Kadambi, Nilesh Prasad Pandey et al.2024 · 2 citationsarXiv
Oh! We Freeze: Improving Quantized Knowledge Distillation via Signal Propagation Analysis for Large Language Models2403.18159v2 · Kartikeya Bhardwaj, Nilesh Prasad Pandey, Sweta Priyadarshi et al.2024 · 1 citationarXiv
Softmax Bias Correction for Quantized Generative Models2309.01729v1 · Nilesh Prasad Pandey, Marios Fournarakis, Chirag Patel et al.2023 · 13 citationsarXiv
A Practical Mixed Precision Algorithm for Post-Training Quantization2302.05397v1 · Nilesh Prasad Pandey, Markus Nagel, Mart van Baalen et al.2023 · 9 citationsarXiv
Career total: 12 works. 11 are in this corpus.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.