Alert button
Picture for Hong-Min Chu

Hong-Min Chu

Alert button

NEFTune: Noisy Embeddings Improve Instruction Finetuning

Oct 10, 2023
Neel Jain, Ping-yeh Chiang, Yuxin Wen, John Kirchenbauer, Hong-Min Chu, Gowthami Somepalli, Brian R. Bartoldson, Bhavya Kailkhura, Avi Schwarzschild, Aniruddha Saha, Micah Goldblum, Jonas Geiping, Tom Goldstein

Figure 1 for NEFTune: Noisy Embeddings Improve Instruction Finetuning
Figure 2 for NEFTune: Noisy Embeddings Improve Instruction Finetuning
Figure 3 for NEFTune: Noisy Embeddings Improve Instruction Finetuning
Figure 4 for NEFTune: Noisy Embeddings Improve Instruction Finetuning
Viaarxiv icon

Universal Guidance for Diffusion Models

Feb 14, 2023
Arpit Bansal, Hong-Min Chu, Avi Schwarzschild, Soumyadip Sengupta, Micah Goldblum, Jonas Geiping, Tom Goldstein

Figure 1 for Universal Guidance for Diffusion Models
Figure 2 for Universal Guidance for Diffusion Models
Figure 3 for Universal Guidance for Diffusion Models
Figure 4 for Universal Guidance for Diffusion Models
Viaarxiv icon

Cold Diffusion: Inverting Arbitrary Image Transforms Without Noise

Aug 19, 2022
Arpit Bansal, Eitan Borgnia, Hong-Min Chu, Jie S. Li, Hamid Kazemi, Furong Huang, Micah Goldblum, Jonas Geiping, Tom Goldstein

Figure 1 for Cold Diffusion: Inverting Arbitrary Image Transforms Without Noise
Figure 2 for Cold Diffusion: Inverting Arbitrary Image Transforms Without Noise
Figure 3 for Cold Diffusion: Inverting Arbitrary Image Transforms Without Noise
Figure 4 for Cold Diffusion: Inverting Arbitrary Image Transforms Without Noise
Viaarxiv icon

Active Learning at the ImageNet Scale

Nov 25, 2021
Zeyad Ali Sami Emam, Hong-Min Chu, Ping-Yeh Chiang, Wojciech Czaja, Richard Leapman, Micah Goldblum, Tom Goldstein

Figure 1 for Active Learning at the ImageNet Scale
Figure 2 for Active Learning at the ImageNet Scale
Figure 3 for Active Learning at the ImageNet Scale
Figure 4 for Active Learning at the ImageNet Scale
Viaarxiv icon

Deep Learning with a Rethinking Structure for Multi-label Classification

Feb 05, 2018
Yao-Yuan Yang, Yi-An Lin, Hong-Min Chu, Hsuan-Tien Lin

Figure 1 for Deep Learning with a Rethinking Structure for Multi-label Classification
Figure 2 for Deep Learning with a Rethinking Structure for Multi-label Classification
Figure 3 for Deep Learning with a Rethinking Structure for Multi-label Classification
Figure 4 for Deep Learning with a Rethinking Structure for Multi-label Classification
Viaarxiv icon

Dynamic Principal Projection for Cost-Sensitive Online Multi-Label Classification

Nov 14, 2017
Hong-Min Chu, Kuan-Hao Huang, Hsuan-Tien Lin

Figure 1 for Dynamic Principal Projection for Cost-Sensitive Online Multi-Label Classification
Figure 2 for Dynamic Principal Projection for Cost-Sensitive Online Multi-Label Classification
Figure 3 for Dynamic Principal Projection for Cost-Sensitive Online Multi-Label Classification
Figure 4 for Dynamic Principal Projection for Cost-Sensitive Online Multi-Label Classification
Viaarxiv icon

Can Active Learning Experience Be Transferred?

Aug 02, 2016
Hong-Min Chu, Hsuan-Tien Lin

Figure 1 for Can Active Learning Experience Be Transferred?
Figure 2 for Can Active Learning Experience Be Transferred?
Figure 3 for Can Active Learning Experience Be Transferred?
Figure 4 for Can Active Learning Experience Be Transferred?
Viaarxiv icon