Zobrazeno 1 - 10
of 155
pro vyhledávání: '"Pandey, Nilesh"'
Autor:
Bhardwaj, Kartikeya, Pandey, Nilesh Prasad, Priyadarshi, Sweta, Ganapathy, Viswanath, Esteves, Rafael, Kadambi, Shreya, Borse, Shubhankar, Whatmough, Paul, Garrepalli, Risheek, Van Baalen, Mart, Teague, Harris, Nagel, Markus
In this paper, we propose Sparse High Rank Adapters (SHiRA) that directly finetune 1-2% of the base model weights while leaving others unchanged, thus, resulting in a highly sparse adapter. This high sparsity incurs no inference overhead, enables rap
Externí odkaz:
http://arxiv.org/abs/2407.16712
Autor:
Bhardwaj, Kartikeya, Pandey, Nilesh Prasad, Priyadarshi, Sweta, Ganapathy, Viswanath, Esteves, Rafael, Kadambi, Shreya, Borse, Shubhankar, Whatmough, Paul, Garrepalli, Risheek, Van Baalen, Mart, Teague, Harris, Nagel, Markus
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 adding no overhead during inference. However, from a mobile deployment
Externí odkaz:
http://arxiv.org/abs/2406.13175
Autor:
Borse, Shubhankar, Kadambi, Shreya, Pandey, Nilesh Prasad, Bhardwaj, Kartikeya, Ganapathy, Viswanath, Priyadarshi, Sweta, Garrepalli, Risheek, Esteves, Rafael, Hayat, Munawar, Porikli, Fatih
While Low-Rank Adaptation (LoRA) has proven beneficial for efficiently fine-tuning large models, LoRA fine-tuned text-to-image diffusion models lack diversity in the generated images, as the model tends to copy data from the observed training samples
Externí odkaz:
http://arxiv.org/abs/2406.08798
Autor:
Bhardwaj, Kartikeya, Pandey, Nilesh Prasad, Priyadarshi, Sweta, Lee, Kyunggeun, Ma, Jun, Teague, Harris
Large generative models such as large language models (LLMs) and diffusion models have revolutionized the fields of NLP and computer vision respectively. However, their slow inference, high computation and memory requirement makes it challenging to d
Externí odkaz:
http://arxiv.org/abs/2403.18159
Publikováno v:
International Journal of Computer Networks & Communications (IJCNC) Vol.16, No.1, January 2024
Cloud computing has high applicability as an Internet based service that relies on sharing computing resources. Cloud computing provides services that are Infrastructure based, Platform based and Software based. The popularity of this technology is d
Externí odkaz:
http://arxiv.org/abs/2402.02052
Post-training quantization (PTQ) is the go-to compression technique for large generative models, such as stable diffusion or large language models. PTQ methods commonly keep the softmax activation in higher precision as it has been shown to be very s
Externí odkaz:
http://arxiv.org/abs/2309.01729
Autor:
Pandey, Nilesh Prasad, Nagel, Markus, van Baalen, Mart, Huang, Yin, Patel, Chirag, Blankevoort, Tijmen
Neural network quantization is frequently used to optimize model size, latency and power consumption for on-device deployment of neural networks. In many cases, a target bit-width is set for an entire network, meaning every layer get quantized to the
Externí odkaz:
http://arxiv.org/abs/2302.05397
Publikováno v:
Symmetry 16 (2024) 10, 1308
In this work, we study the time-dependent behaviour of quantum correlations of a system of an inverted oscillator governed by out-of-equilibrium dynamics using the well-known Schwinger-Keldysh formalism in presence of quantum mechanical quench. Consi
Externí odkaz:
http://arxiv.org/abs/2210.01134
Publikováno v:
Symmetry 2023, 15(3), 655
In this work, we explore the effects of a quantum quench on the circuit complexity for a quenched quantum field theory having weakly coupled quartic interaction. We use the invariant operator method, under a perturbative framework, for computing the
Externí odkaz:
http://arxiv.org/abs/2209.03372
Autor:
Choudhury, Sayantan, Gharat, Rakshit Mandish, Mandal, Saptarshi, Pandey, Nilesh, Roy, Abhishek, Sarker, Partha
Publikováno v:
Phys. Rev. D 106, 025002 (2022)
In this work, we explore the effects of a quantum quench on the entanglement measures of a two-body coupled oscillator system having quartic interaction. We use the invariant operator method, under a perturbative framework, for computing the ground s
Externí odkaz:
http://arxiv.org/abs/2204.05326