Priyadarshini Panda

Memba: Membrane-driven Parameter-Efficient Fine-Tuning for Mamba

QuRL: Low-Precision Reinforcement Learning for Efficient Reasoning

Event2Vec: Processing neuromorphic events directly by representations in vector space

GPTAQ: Efficient Finetuning-Free Quantization for Asymmetric Calibration

OpenWorldSAM: Extending SAM2 for Universal Image Segmentation with Language Prompts

DuoGPT: Training-free Dual Sparsity through Activation-aware Pruning in LLMs

TesseraQ: Ultra Low-Bit LLM Post-Training Quantization with Block Reconstruction