Picture for Debangshu Banerjee

Debangshu Banerjee

Support is All You Need for Certified VAE Training

Add code
Apr 16, 2025
Viaarxiv icon

CRANE: Reasoning with constrained LLM generation

Add code
Feb 13, 2025
Viaarxiv icon

Towards Reliable Alignment: Uncertainty-aware RLHF

Add code
Oct 31, 2024
Figure 1 for Towards Reliable Alignment: Uncertainty-aware RLHF
Figure 2 for Towards Reliable Alignment: Uncertainty-aware RLHF
Figure 3 for Towards Reliable Alignment: Uncertainty-aware RLHF
Figure 4 for Towards Reliable Alignment: Uncertainty-aware RLHF
Viaarxiv icon

Relational DNN Verification With Cross Executional Bound Refinement

Add code
May 16, 2024
Viaarxiv icon

When are Bandits Robust to Misspecification?

Add code
Oct 13, 2023
Viaarxiv icon

Incremental Randomized Smoothing Certification

Add code
May 31, 2023
Viaarxiv icon

Incremental Verification of Neural Networks

Add code
Apr 04, 2023
Figure 1 for Incremental Verification of Neural Networks
Figure 2 for Incremental Verification of Neural Networks
Figure 3 for Incremental Verification of Neural Networks
Figure 4 for Incremental Verification of Neural Networks
Viaarxiv icon

Interpreting Robustness Proofs of Deep Neural Networks

Add code
Jan 31, 2023
Viaarxiv icon

On the Minimax Regret for Linear Bandits in a wide variety of Action Spaces

Add code
Jan 09, 2023
Viaarxiv icon

Markov Chain Concentration with an Application in Reinforcement Learning

Add code
Jan 07, 2023
Viaarxiv icon