reward signal

Beyond Multiple Choice: Verifiable OpenQA for Robust Vision-Language RFT CVPR 2026 Decouple to Generalize: Context-First Self-Evolving Learning for Data-Scarce Vision-Language Reasoning CVPR 2026 Disentangling to Re-couple: Resolving the Similarity-Controllability Paradox in Subject-Driven Text-to-Image Generation CVPR 2026 Do Less, Achieve More: Do We Need Every-Step Optimization for RL Fine-tuning of Diffusion Models? CVPR 2026 ERCThinker: Fast-Slow Thinking for Emotion Recognition in Conversation ACL 2026 LeapAlign: Post-training Flow Matching Models at Any Generation Step by Building Two-Step Trajectories CVPR 2026 Learning to Generate and Extract: A Multi-Agent Collaboration Framework for Zero-Shot Document-Level Event Arguments Extraction AAAI 2026 Pre-DPO: Improving Data Utilization in Direct Preference Optimization Using a Guiding Reference Model AAAI 2026 RehearseVLA: Simulated Post-Training for VLAs with Physically-Consistent World Model CVPR 2026 Specificity-aware reinforcement learning for fine-grained open-world classification CVPR 2026 TextPecker: Rewarding Structural Anomaly Quantification for Enhancing Visual Text Rendering CVPR 2026 ConciseRL: Conciseness-Guided Reinforcement Learning for Efficient Reasoning Models EMNLP 2025 Dynamic Scaling of Unit Tests for Code Reward Modeling ACL 2025 Encouraging Good Processes Without the Need for Good Answers: Reinforcement Learning for LLM Agent Planning EMNLP 2025 FOUNDER: Grounding Foundation Models in World Models for Open-Ended Embodied Decision Making ICML 2025 From General Reward to Targeted Reward: Improving Open-ended Long-context Generation Models EMNLP 2025 Ignore the KL Penalty! Boosting Exploration on Critical Tokens to Enhance RL Fine-Tuning NAACL 2025 Improving the Language Understanding Capabilities of Large Language Models Using Reinforcement Learning EMNLP 2025 On-Policy Self-Alignment with Fine-grained Knowledge Feedback for Hallucination Mitigation ACL 2025 Reward-Guided Prompt Evolving in Reinforcement Learning for LLMs ICML 2025 s3: You Don’t Need That Much Data to Train a Search Agent via RL EMNLP 2025 S-EPOA: Overcoming the Indistinguishability of Segments with Skill-Driven Preference-Based Reinforcement Learning IJCAI 2025 Training Language Model to Critique for Better Refinement ACL 2025 Training Medical QA Models Based on Mixed Rewards from Multiple-Choice and Open-Ended Questions EMNLP 2025 C-GAIL: Stabilizing Generative Adversarial Imitation Learning with Control Theory NeurIPS 2024