5 papers
AgentKVShift: Efficient KV Cache Reuse for Agentic Memory Systems
Nilesh Prasad Pandey, Jason Kong, Lanxiang Hu +5
Memory-augmented LLM agents maintain context across hundreds of interactions through agentic memory systems that actively curate retrieved content with LLM-generated metadata such…
A KL Lens on Quantization: Fast, Forward-Only Sensitivity for Mixed-Precision SSM-Transformer Models
Jason Kong, Nilesh Prasad Pandey, Flavio Ponzina +1
Deploying Large Language Models (LLMs) on edge devices faces severe computational and memory constraints, limiting real-time processing and on-device intelligence. Hybrid architect…
QMC: Efficient SLM Edge Inference via Outlier-Aware Quantization and Emergent Memories Co-Design
Nilesh Prasad Pandey, Jangseon Park, Onat Gungor +2
Deploying Small Language Models (SLMs) on edge platforms is critical for real-time, privacy-sensitive generative AI, yet constrained by memory, latency, and energy budgets. Quantiz…
DPQ-HD: Post-Training Compression for Ultra-Low Power Hyperdimensional Computing
Nilesh Prasad Pandey, Shriniwas Kulkarni, David Wang +3
Hyperdimensional Computing (HDC) is emerging as a promising approach for edge AI, offering a balance between accuracy and efficiency. However, current HDC-based applications often…
Sparse High Rank Adapters
Kartikeya Bhardwaj, Nilesh Prasad Pandey, Sweta Priyadarshi +9
Low Rank Adaptation (LoRA) has gained massive attention in the recent generative AI research. One of the main advantages of LoRA is its ability to be fused with pretrained models,…