2025 04 Icml Accept

5 papers accepted by ICML 2025. Congratulations to everyone!

• “RoSTE: An Efficient Quantization-Aware Supervised Fine-Tuning Approach for Large Language Models” see here
• “Inference-Time Alignment of Diffusion Models with Direct Noise Optimization” see here
• “Towards LLM Unlearning Resilient to Relearning Attacks: A Sharpness-Aware Minimization Perspective and Beyond” see here
• “On the Vulnerability of Applying Retrieval-Augmented Generation within Knowledge-Intensive Application Domains” see here
• “BRiTE: Bootstrapping Reinforced Thinking Process to Enhance Language Model Reasoning” see here