Deep RL

VideoSSR: Video Self-Supervised Reinforcement Learning CVPR 2026 VIRAL: Visual Sim-to-Real at Scale for Humanoid Loco-Manipulation CVPR 2026 V-Pruner: A Fast and Globally-informed Token Pruning Framework for Vision Transformer AAAI 2026 VQAThinker: Exploring Generalizable and Explainable Video Quality Assessment via Reinforcement Learning AAAI 2026 Where and What Matters: Sensitivity-Aware Task Vectors for Many-Shot Multimodal In-Context Learning AAAI 2026 WIST: Web-Grounded Iterative Self-Play Tree for Domain-Targeted Reasoning Improvement ACL 2026 $Door(s)$: Junction State Estimation for Efficient Exploration in Reinforcement Learning CoRL 2025 A Case for Validation Buffer in Pessimistic Actor-Critic IJCAI 2025 Accelerating Proximal Policy Optimization Learning Using Task Prediction for Solving Environments with Delayed Rewards L4DC 2025 Accelerating Task Generalisation with Multi-Level Skill Hierarchies ICLR 2025 ACECODER: Acing Coder RL via Automated Test-Case Synthesis ACL 2025 Action-Dependent Optimality-Preserving Reward Shaping ICML 2025 Action Flow Matching for Lifelong Learning RSS 2025 ActionStudio: A Lightweight Framework for Data and Training of Large Action Models EMNLP 2025 Activation by Interval-wise Dropout: A Simple Way to Prevent Neural Networks from Plasticity Loss ICML 2025 Active Geospatial Search for Efficient Tenant Eviction Outreach AAAI 2025 Active Reward Modeling: Adaptive Preference Labeling for Large Language Model Alignment ICML 2025 Actor-Critic learning for mean-field control in continuous time JMLR 2025 Actor-Critics Can Achieve Optimal Sample Efficiency ICML 2025 Adapting LLM Agents with Universal Communication Feedback NAACL 2025 Adaptive Q-Network: On-the-fly Target Selection for Deep Reinforcement Learning ICLR 2025 AdaptiveAE: An Adaptive Exposure Strategy for HDR Capturing in Dynamic Scenes ICCV 2025 ADDQ: Adaptive distributional double Q-learning ICML 2025 Adversarial Inception Backdoor Attacks against Reinforcement Learning ICML 2025 Adversarial Preference Learning for Robust LLM Alignment ACL 2025