gaussian noise
Gaussian noise is a statistical noise that follows a normal distribution, often used to model random variations in data and perturb input or output in machine learning for robust training.
- AdaptGrad: Adaptive Sampling to Reduce Noise
- AegisGuard: RL-Guided Adapter Tuning for TEE-Based Efficient & Secure On-Device Inference
- DNAEdit: Direct Noise Alignment for Text-Guided Rectified Flow Editing
- Ditch the Denoiser: Emergence of Noise Robustness in Self-Supervised Learning from Data Curriculum
- Fractional Langevin Dynamics for Combinatorial Optimization via Polynomial-Time Escape
- NoisyGRPO: Incentivizing Multimodal CoT Reasoning via Noise Injection and Bayesian Estimation
- Temperature is All You Need for Generalization in Langevin Dynamics and other Markov Processes
- Walking the Schrödinger Bridge: A Direct Trajectory for Text-to-3D Generation
- What We Miss Matters: Learning from the Overlooked in Point Cloud Transformers
- Zero-shot Denoising via Neural Compression: Theoretical and algorithmic framework