VC-OPD: Visual Counterfactual On-Policy Distillation for Grounded Vision-Language Reasoning
cs.AI
Submitted: 2026-10-10
Updated: 2026-10-10
Terminology
Sources
- Proximal Policy Optimization Algorithms
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- Aligning Large Multimodal Models with Factually Augmented RLHF
- RLHF-V: Towards Trustworthy MLLMs via Behavior Alignment from Fine-grained Correctional Human Feedback
- Visual-RFT: Visual Reinforcement Fine-Tuning
- VLM-R1: A Stable and Generalizable R1-style Large Vision-Language Model
- R1-VL: Learning to Reason with Multimodal Large Language Models via Step-wise Group Relative Policy Optimization
- Reason-RFT: Reinforcement Fine-Tuning for Visual Reasoning of Vision Language Models
- Perception-Aware Policy Optimization for Multimodal Reasoning
- Perception Before Reasoning: Two-Stage Reinforcement Learning for Visual Reasoning in Vision-Language Models
- Self-Rewarding Vision-Language Model via Reasoning Decomposition
- Grounded Reinforcement Learning for Visual Reasoning
- On-Policy Distillation of Language Models: Learning from Self-Generated Mistakes
- Learning beyond Teacher: Generalized On-Policy Distillation with Reward Extrapolation
- Scaling Reasoning Efficiently via Relaxed On-Policy Distillation
- Trust Region Policy Optimization
- MM-RLHF: The Next Step Forward in Multimodal LLM Alignment
- Safe RLHF-V: Safe Reinforcement Learning from Multi-modal Human Feedback
- Visual Agentic Reinforcement Fine-Tuning
- Distilling the Knowledge in a Neural Network
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Agents' Last Exam
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems