2024 09 Neurips Accept

7 papers accepted by NeurIPS 2024. Congratulations to everyone!

• “Defensive Unlearning with Adversarial Training for Robust Concept Erasure in Diffusion Models”
• “Pre-training Differentially Private Models with Limited Public Data”
• “DOPPLER: Differentially Private Optimizers with Low-pass Filter for Privacy Noise Reduction”
• “Getting More Juice Out of the SFT Data: Reward Learning from Human Demonstration Improves SFT for LLM Alignment”
• “SLTrain: a sparse plus low rank approach for parameter and memory efficient pretraining”
• “Unraveling the Gradient Descent Dynamics of Transformers”
• “RAW: A Robust and Agile Plug-and-Play Watermark Framework for AI-Generated Images with Provable Guarantees”