Reinforcement Learning from Human Feedback

Aligning Large Language Models via Fully Self-Synthetic Data ACL 2026 Aligning Multi-Character Narrative Image Generation with Multi-Aspect Human Preferences CVPR 2026 ARES: Adaptive Red-Teaming and End-to-End Repair of Policy-Reward System ACL 2026 BeautyGRPO: Aesthetic Alignment for Face Retouching via Dynamic Path Guidance and Fine-Grained Preference Modeling CVPR 2026 Better Literary Translation: A Multi-Aspect Data Generation and LLM Training Approach ACL 2026 Beyond Multiple Choice: Verifiable OpenQA for Robust Vision-Language RFT CVPR 2026 Beyond Pedagogical Principles: Multi-Horizon Preference Optimization for Efficient Socratic Tutoring ACL 2026 Bias Fitting to Mitigate Length Bias of Reward Model in RLHF ACL 2026 C2: Scalable Rubric-Augmented Reward Modeling from Binary Preferences ACL 2026 Circular-DPO: Aligning Multi-Stage 3D Generative Models via Preference Feedback Loop CVPR 2026 CSRP: Chain-of-Thought Reasoning for Chinese Text Correction via Reinforcement Learning with Efficiency-Aware Rewards ACL 2026 Curing Miracle Steps in LLM Mathematical Reasoning with Rubric Rewards ACL 2026 Current Advances in LLM Reasoning ACL 2026 DARM: Distribution-Aware Reward Modeling by Alleviating Biases from Low Preference-Context Dependency Data ACL 2026 DecIF: Improving Instruction-Following through Decomposition ACL 2026 DocSeeker: Structured Visual Reasoning with Evidence Grounding for Long Document Understanding CVPR 2026 Edit-Aware Reward Modeling for Chinese Grammatical Error Correction ACL 2026 EMAD: Evidence-Centric Grounded Multimodal Diagnosis for Alzheimer's Disease CVPR 2026 FinPercep-RM: A Fine-grained Reward Model and Co-evolutionary Curriculum for RL-based Real-world Super-Resolution CVPR 2026 From Individual to Common: An Early Exploration of Consensus in Non-verifiable Data for Balanced Preference Optimization ACL 2026 Influence-based Online Experience Selection for Effective RLHF ACL 2026 IntroSVG: Learning from Rendering Feedback for Text-to-SVG Generation via an Introspective Generator-Critic Framework CVPR 2026 Iterative Dual-Model Alignment for Story Evaluation ACL 2026 Learning What Matters: Dynamic Dimension Selection and Aggregation for Interpretable Vision-Language Reward Modeling ACL 2026 Learning What to Trust: Bayesian Prior-Guided Optimization for Visual Generation CVPR 2026