Reinforcement Learning

Triviality Corrected Endogenous Reward ACL 2026 Understanding the Role of Hallucination in Reinforcement Post-Training of Multimodal Reasoning Models CVPR 2026 Unified Generation and Self-Verification for Vision-Language Models via Advantage Decoupled Preference Optimization CVPR 2026 Unified Thinker: A General Reasoning Core for Image Generation ACL 2026 UniGen-1.5: Enhancing Image Generation and Editing through Reward Unification in RL CVPR 2026 VA-p: Variational Policy Alignment for Pixel-Aware Autoregressive Generation CVPR 2026 VGent: Visual Grounding via Modular Design for Disentangling Reasoning and Prediction CVPR 2026 Video-as-Answer: Predict and Generate Next Video Event with Joint-GRPO CVPR 2026 Visual-Aware CoT: Achieving High-Fidelity Visual Consistency in Unified Models CVPR 2026 VIVA: VLM-Guided Instruction-Based Video Editing with Reward Optimization CVPR 2026 Why Does RL Generalize Better Than SFT? A Data-Centric Perspective on VLM Post-Training CVPR 2026 Would LLMs be Good Historical Linguists and Chinese Dialect Learners? ACL 2026 Writing-RL: Advancing Long-form Writing via Adaptive Curriculum Reinforcement Learning ACL 2026 A0: An Affordance-Aware Hierarchical Model for General Robotic Manipulation ICCV 2025 Accelerating LLM Reasoning via Early Rejection with Partial Reward Modeling EMNLP 2025 ACECODER: Acing Coder RL via Automated Test-Case Synthesis ACL 2025 AceMath: Advancing Frontier Math Reasoning with Post-Training and Reward Modeling ACL 2025 Action-Conditioned Hamiltonian Generative Networks (AC-HGN) for Supervised and Reinforcement Learning L4DC 2025 Aesthetic Post-Training Diffusion Models from Generic Preferences with Step-by-step Preference Optimization CVPR 2025 Agent-Aware Training for Agent-Agnostic Action Advising in Deep Reinforcement Learning AAAI 2025 AgentGym: Evaluating and Training Large Language Model-based Agents across Diverse Environments ACL 2025 Agentic-R1: Distilled Dual-Strategy Reasoning EMNLP 2025 Agentic Reward Modeling: Integrating Human Preferences with Verifiable Correctness Signals for Reliable Reward Systems ACL 2025 AgentMixer: Multi-Agent Correlated Policy Factorization AAAI 2025 AgentRM: Enhancing Agent Generalization with Reward Modeling ACL 2025