Picture for Gagandeep Singh

Gagandeep Singh

Enhancing Sign Language Detection through Mediapipe and Convolutional Neural Networks (CNN)

Jun 06, 2024
Viaarxiv icon

Quantitative Certification of Bias in Large Language Models

Add code
May 29, 2024
Viaarxiv icon

Relational DNN Verification With Cross Executional Bound Refinement

Add code
May 16, 2024
Viaarxiv icon

Cross-Input Certified Training for Universal Perturbations

May 15, 2024
Viaarxiv icon

Is Watermarking LLM-Generated Code Robust?

Add code
Mar 24, 2024
Viaarxiv icon

Improving LLM Code Generation with Grammar Augmentation

Add code
Mar 03, 2024
Figure 1 for Improving LLM Code Generation with Grammar Augmentation
Figure 2 for Improving LLM Code Generation with Grammar Augmentation
Figure 3 for Improving LLM Code Generation with Grammar Augmentation
Figure 4 for Improving LLM Code Generation with Grammar Augmentation
Viaarxiv icon

QuaCer-C: Quantitative Certification of Knowledge Comprehension in LLMs

Add code
Feb 24, 2024
Figure 1 for QuaCer-C: Quantitative Certification of Knowledge Comprehension in LLMs
Figure 2 for QuaCer-C: Quantitative Certification of Knowledge Comprehension in LLMs
Viaarxiv icon

Reward Poisoning Attack Against Offline Reinforcement Learning

Feb 15, 2024
Viaarxiv icon

RAMP: Boosting Adversarial Robustness Against Multiple $l_p$ Perturbations

Add code
Feb 09, 2024
Viaarxiv icon

Efficient Two-Phase Offline Deep Reinforcement Learning from Preference Feedback

Dec 30, 2023
Figure 1 for Efficient Two-Phase Offline Deep Reinforcement Learning from Preference Feedback
Figure 2 for Efficient Two-Phase Offline Deep Reinforcement Learning from Preference Feedback
Figure 3 for Efficient Two-Phase Offline Deep Reinforcement Learning from Preference Feedback
Figure 4 for Efficient Two-Phase Offline Deep Reinforcement Learning from Preference Feedback
Viaarxiv icon