Mehrtash Harandi

4 papers Monash University

• Geometry-Aware Collaborative Multi-Solutions Optimizer for Model Fine-Tuning with Parameter Efficiency
• Token-Level Self-Play with Importance-Aware Guidance for Large Language Models
• Unleashing Diffusion Transformers for Visual Correspondence by Modulating Massive Activations
• Unveiling m-Sharpness Through the Structure of Stochastic Gradient Noise