Reinforcement Learning

Context-Aware Iteration Policy Network for Efficient Optical Flow Estimation AAAI 2024 Contrastive Policy Gradient: Aligning LLMs on sequence-level scores in a supervised-friendly fashion EMNLP 2024 Controllable Citation Sentence Generation with Language Models ACL 2024 Controlled maximal variability along with reliable performance in recurrent neural networks NeurIPS 2024 Countering Reward Over-Optimization in LLM with Demonstration-Guided Reinforcement Learning ACL 2024 CrystalBox: Future-Based Explanations for Input-Driven Deep RL Systems AAAI 2024 DART-Math: Difficulty-Aware Rejection Tuning for Mathematical Problem-Solving NeurIPS 2024 Deep Reinforcement Learning for Communication Networks AAAI 2024 Deterministic Uncertainty Propagation for Improved Model-Based Offline Reinforcement Learning NeurIPS 2024 DGPO: Discovering Multiple Strategies with Diversity-Guided Policy Optimization AAAI 2024 Dialogue for Prompting: A Policy-Gradient-Based Discrete Prompt Generation for Few-Shot Learning AAAI 2024 DiffChat: Learning to Chat with Text-to-Image Synthesis Models for Interactive Image Creation ACL 2024 Diffusion Actor-Critic with Entropy Regulator NeurIPS 2024 Diffusion-based Reinforcement Learning via Q-weighted Variational Policy Optimization NeurIPS 2024 Diffusion for World Modeling: Visual Details Matter in Atari NeurIPS 2024 Diffusion Model Alignment Using Direct Preference Optimization CVPR 2024 Diffusion Policies Creating a Trust Region for Offline Reinforcement Learning NeurIPS 2024 Disentangling Length from Quality in Direct Preference Optimization ACL 2024 Don’t Forget Your Reward Values: Language Model Alignment via Value-based Calibration EMNLP 2024 DreamSmooth: Improving Model-based Reinforcement Learning via Reward Smoothing ICLR 2024 Dynamic Multi-Reward Weighting for Multi-Style Controllable Generation EMNLP 2024 Dynamic Policy-Driven Adaptive Multi-Instance Learning for Whole Slide Image Classification CVPR 2024 Efficient Recurrent Off-Policy RL Requires a Context-Encoder-Specific Learning Rate NeurIPS 2024 EgoGen: An Egocentric Synthetic Data Generator CVPR 2024 Enhancing Alignment using Curriculum Learning & Ranked Preferences EMNLP 2024