preference learning

Act-Adaptive Margin: Dynamically Calibrating Reward Models for Subjective Ambiguity ACL 2026 AesX: Enhance Your Images with Stunning Aesthetic Beauty ACL 2026 Align Video Diffusion Model with Online Video-Centric Preference Optimization WACV 2026 Bandit Learning in Housing Markets AAAI 2026 CoAct: Co-Active LLM Preference Learning with Human-AI Synergy ACL 2026 Conformal Feedback Alignment: Quantifying Answer-Level Reliability for Robust LLM Alignment EACL 2026 Cost-Minimized Label-Flipping Poisoning Attack to LLM Alignment AAAI 2026 CTPD: Cross Tokenizer Preference Distillation AAAI 2026 DARM: Distribution-Aware Reward Modeling by Alleviating Biases from Low Preference-Context Dependency Data ACL 2026 Diagnosing and Remedying Representation Deficiencies for Deterministic Reasoning in KGQA ACL 2026 DiMA: Distinguishing Resident and Tourist Preferences via Multi-Modal LLM Alignment for Out-of-Town Cross-Domain Recommendation AAAI 2026 End-to-End Fine-Tuning of 3D Texture Generation using Differentiable Rewards WACV 2026 Energy Matching based Preference Learning for Diffusion Language Models EACL 2026 GlyphPrinter: Region-Grouped Direct Preference Optimization for Glyph-Accurate Visual Text Rendering CVPR 2026 GRAM-R²: Self-Training Generative Foundation Reward Models for Reward Reasoning AAAI 2026 How Hard Is It to Explain Preferences Using Few Boolean Attributes? AAAI 2026 Interactive Multi-Objective Probabilistic Preference Learning with Soft and Hard Bounds UAI 2026 Knowledge-Based Stable Roommates Problems AAAI 2026 Learning Personalized Photographic Style from Pairwise User Preferences CVPR 2026 Long-form RewardBench: Evaluating Reward Models for Long-form Generation AAAI 2026 MedS³: Towards Medical Slow Thinking with Self-Evolved Soft Dual-sided Process Supervision AAAI 2026 Multi-Robot Learning from Human Feedback AAAI 2026 NUS-IDS at AMIYA/VarDial 2026: Improving Arabic Dialectness in LLMs with Reinforcement Learning EACL 2026 Optimizing LVLMs with On-Policy Data for Effective Hallucination Mitigation WACV 2026 ParetoHqD: Fast Offline Multiobjective Alignment of Large Language Models Using Pareto High-Quality Data AAAI 2026