Model Predictive Task Sampling for Efficient and Robust Adaptation
cs.LG
Submitted: 2025-01-19
Updated: 2026-10-13
Code: https://github.com/thu-rllab/MPTS
Terminology
Sources
- GPT-4 Technical Report
- Solving Rubik's Cube with a Robot Hand
- RL$^2$: Fast Reinforcement Learning via Slow Reinforcement Learning
- The Llama 3 Herd of Models
- Bad Students Make Great Teachers: Active Learning Accelerates Large-Scale Visual Understanding
- Data curation via joint example selection further accelerates multimodal learning
- Auto-Encoding Variational Bayes
- Variational Continual Learning
- On First-Order Meta-Learning Algorithms
- Neural Processes
- CLIPScore: A Reference-free Evaluation Metric for Image Captioning
- HyperNetworks
- Distributionally Robust Language Modeling
- Can Prompt Difficulty be Online Predicted for Accelerating RL Finetuning of Reasoning Models?
- Convolutional Conditional Neural Processes
- Attentive Neural Processes
- High-Dimensional Statistics
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks