Wang's picture

2 1

Wang

Qinsi1

[email protected]

AI & ML interests

None yet

Recent Activity

upvoted a paper 7 days ago

Angles Don't Lie: Unlocking Training-Efficient RL Through the Model's Own Signals

commented on a paper 7 days ago

Angles Don't Lie: Unlocking Training-Efficient RL Through the Model's Own Signals

commented on a paper 14 days ago

CoreMatching: A Co-adaptive Sparse Inference Framework with Token and Neuron Pruning for Comprehensive Acceleration of Vision-Language Models

View all activity

Organizations

None yet

Papers 2

arxiv:2502.02723

arxiv:2410.18311

models 15

Qinsi1/DobiSVD_Noremapping-Llama-2-7b-hf-0.8

Qinsi1/DobiSVD_Noremapping-Llama-2-7b-hf-0.6

Qinsi1/DobiSVD_Noremapping-Llama-2-7b-hf-0.4

Qinsi1/DobiSVD-Llama-2-13b-hf-0.8

Updated Mar 21 • 50

Qinsi1/DobiSVD-Llama-2-13b-hf-0.6

Updated Mar 21 • 10

Qinsi1/DobiSVD-Llama-2-13b-hf-0.4

Updated Mar 21 • 36

Qinsi1/DobiSVD-Llama-13b-hf-0.8

Updated Mar 21 • 39

Qinsi1/DobiSVD-Llama-13b-hf-0.6

Updated Mar 21 • 64

Qinsi1/DobiSVD-Llama-13b-hf-0.4

Updated Mar 21 • 8

Qinsi1/DobiSVD-Llama-7b-hf-0.8

Updated Mar 21 • 74

datasets 0

None public yet