stochasticity
Stochasticity refers to the inherent randomness in processes or models, which can influence outcomes in machine learning, particularly in reinforcement learning where agents may explore varied actions with uncertainty.
- DP²O-SR: Direct Perceptual Preference Optimization for Real-World Image Super-Resolution
- DiffBreak: Is Diffusion-Based Purification Robust?
- Discrete Spatial Diffusion: Intensity-Preserving Diffusion Modeling
- Distributional Training Data Attribution: What do Influence Functions Sample?
- FSI-Edit: Frequency and Stochasticity Injection for Flexible Diffusion-Based Image Editing
- FlowDAS: A Stochastic Interpolant-based Framework for Data Assimilation
- Hybrid Latent Reasoning via Reinforcement Learning
- Improving Generative Behavior Cloning via Self-Guidance and Adaptive Chunking
- Inference-Time Scaling for Flow Models via Stochastic Generation and Rollover Budget Forcing
- Learning-Augmented Online Bidding in Stochastic Settings
- Off-policy Reinforcement Learning with Model-based Exploration Augmentation
- ReDit: Reward Dithering for Improved LLM Policy Optimization
- Regret Analysis of Average-Reward Unichain MDPs via an Actor-Critic Approach
- Stochastic Forward-Forward Learning through Representational Dimensionality Compression
- To Distill or Decide? Understanding the Algorithmic Trade-off in Partially Observable RL