Alert button
Picture for Hongyang Zhang

Hongyang Zhang

Alert button

AnyTool: Self-Reflective, Hierarchical Agents for Large-Scale API Calls

Add code
Bookmark button
Alert button
Feb 06, 2024
Yu Du, Fangyun Wei, Hongyang Zhang

Viaarxiv icon

EAGLE: Speculative Sampling Requires Rethinking Feature Uncertainty

Add code
Bookmark button
Alert button
Feb 04, 2024
Yuhui Li, Fangyun Wei, Chao Zhang, Hongyang Zhang

Viaarxiv icon

DiPmark: A Stealthy, Efficient and Resilient Watermark for Large Language Models

Add code
Bookmark button
Alert button
Oct 11, 2023
Yihan Wu, Zhengmian Hu, Hongyang Zhang, Heng Huang

Viaarxiv icon

RAIN: Your Language Models Can Align Themselves without Finetuning

Add code
Bookmark button
Alert button
Sep 13, 2023
Yuhui Li, Fangyun Wei, Jinjing Zhao, Chao Zhang, Hongyang Zhang

Figure 1 for RAIN: Your Language Models Can Align Themselves without Finetuning
Figure 2 for RAIN: Your Language Models Can Align Themselves without Finetuning
Figure 3 for RAIN: Your Language Models Can Align Themselves without Finetuning
Figure 4 for RAIN: Your Language Models Can Align Themselves without Finetuning
Viaarxiv icon

Gradient-Based Word Substitution for Obstinate Adversarial Examples Generation in Language Models

Add code
Bookmark button
Alert button
Aug 18, 2023
Yimu Wang, Peng Shi, Hongyang Zhang

Figure 1 for Gradient-Based Word Substitution for Obstinate Adversarial Examples Generation in Language Models
Figure 2 for Gradient-Based Word Substitution for Obstinate Adversarial Examples Generation in Language Models
Figure 3 for Gradient-Based Word Substitution for Obstinate Adversarial Examples Generation in Language Models
Figure 4 for Gradient-Based Word Substitution for Obstinate Adversarial Examples Generation in Language Models
Viaarxiv icon

zkDL: Efficient Zero-Knowledge Proofs of Deep Learning Training

Add code
Bookmark button
Alert button
Jul 30, 2023
Haochen Sun, Hongyang Zhang

Figure 1 for zkDL: Efficient Zero-Knowledge Proofs of Deep Learning Training
Figure 2 for zkDL: Efficient Zero-Knowledge Proofs of Deep Learning Training
Figure 3 for zkDL: Efficient Zero-Knowledge Proofs of Deep Learning Training
Figure 4 for zkDL: Efficient Zero-Knowledge Proofs of Deep Learning Training
Viaarxiv icon

Investigating the Existence of "Secret Language'' in Language Models

Add code
Bookmark button
Alert button
Jul 24, 2023
Yimu Wang, Peng Shi, Hongyang Zhang

Figure 1 for Investigating the Existence of "Secret Language'' in Language Models
Figure 2 for Investigating the Existence of "Secret Language'' in Language Models
Figure 3 for Investigating the Existence of "Secret Language'' in Language Models
Figure 4 for Investigating the Existence of "Secret Language'' in Language Models
Viaarxiv icon

Cooperation or Competition: Avoiding Player Domination for Multi-Target Robustness via Adaptive Budgets

Add code
Bookmark button
Alert button
Jun 27, 2023
Yimu Wang, Dinghuai Zhang, Yihan Wu, Heng Huang, Hongyang Zhang

Figure 1 for Cooperation or Competition: Avoiding Player Domination for Multi-Target Robustness via Adaptive Budgets
Figure 2 for Cooperation or Competition: Avoiding Player Domination for Multi-Target Robustness via Adaptive Budgets
Figure 3 for Cooperation or Competition: Avoiding Player Domination for Multi-Target Robustness via Adaptive Budgets
Figure 4 for Cooperation or Competition: Avoiding Player Domination for Multi-Target Robustness via Adaptive Budgets
Viaarxiv icon

Understanding the Impact of Adversarial Robustness on Accuracy Disparity

Add code
Bookmark button
Alert button
Nov 28, 2022
Yuzheng Hu, Fan Wu, Hongyang Zhang, Han Zhao

Figure 1 for Understanding the Impact of Adversarial Robustness on Accuracy Disparity
Figure 2 for Understanding the Impact of Adversarial Robustness on Accuracy Disparity
Figure 3 for Understanding the Impact of Adversarial Robustness on Accuracy Disparity
Figure 4 for Understanding the Impact of Adversarial Robustness on Accuracy Disparity
Viaarxiv icon