Rajdeep Haldar

According to our database, Rajdeep Haldar authored at least 6 papers between 2024 and 2026.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of five.

2026

f-GRPO and Beyond: Divergence-Based Reinforcement Learning Algorithms for General LLM Alignment.

Rajdeep Haldar, Lantao Mei, Guang Lin, Yue Xing, Qifan Song

CoRR, February, 2026

Adversarial Vulnerability from On-Manifold Inseparability and Poor Off-Manifold Convergence.

Rajdeep Haldar, Yue Xing, Qifan Song, Guang Lin

Trans. Mach. Learn. Res., 2026

2025

LLM Safety Alignment is Divergence Estimation in Disguise.

Rajdeep Haldar, Ziyi Wang, Qifan Song, Guang Lin, Yue Xing

CoRR, February, 2025

On Neural Network Approximation of Ideal Adversarial Attack and Convergence of Adversarial Training.

Rajdeep Haldar, Qifan Song

SIAM J. Math. Data Sci., 2025

2024

Adversarial Vulnerability as a Consequence of On-Manifold Inseparibility.

Rajdeep Haldar, Yue Xing, Qifan Song, Guang Lin

CoRR, 2024

Effect of Ambient-Intrinsic Dimension Gap on Adversarial Vulnerability.

Rajdeep Haldar, Yue Xing, Qifan Song

Proceedings of the International Conference on Artificial Intelligence and Statistics, 2024