UniEvo-VL: An On-policy Self-Distillation Training Recipe for Multimodal Model Self-improvement

arXiv:2609.38721 · cs.AI, cs.CV · Submitted 2026-09-30 · Read on arXiv

cs.AI, cs.CV

Submitted: 2026-09-30

Updated: 2026-09-30

Terminology

• Verification — 38× in this paper · explained in 2 episodes
• Distillation — 24× in this paper · explained in 2 episodes
• Benchmark — 20× in this paper · explained in 2 episodes
• Accuracy — 13× in this paper · explained in 1 episode
• Self-distillation — 13× in this paper · explained in 6 episodes
• Fidelity — 9× in this paper · explained in 2 episodes
• Diffusion Model — 5× in this paper · explained in 8 episodes
• Diffusion Models — 5× in this paper · explained in 6 episodes
• GRPO — 5× in this paper · explained in 6 episodes
• Fine-Tuning — 4× in this paper · explained in 5 episodes
• On-Policy Distillation — 4× in this paper · explained in 3 episodes
• Adaptation — 2× in this paper · explained in 1 episode
• Alignment — 2× in this paper · explained in 1 episode
• Flow Matching — 2× in this paper · explained in 8 episodes
• On-policy Self-Distillation (OPSD) — 2× in this paper · explained in 2 episodes
• alpha — 2× in this paper · explained in 1 episode
• Adam — 1× in this paper · explained in 2 episodes
• Aggregation — 1× in this paper · explained in 1 episode
• Flow Matching Model — 1× in this paper · explained in 2 episodes
• Generative AI — 1× in this paper · explained in 2 episodes
• Grounding — 1× in this paper · explained in 3 episodes
• Latent Representation — 1× in this paper · explained in 2 episodes
• Regularization — 1× in this paper · explained in 3 episodes
• Reinforcement Learning — 1× in this paper · explained in 4 episodes
• Score Function — 1× in this paper · explained in 4 episodes
• Supervised Fine-Tuning (SFT) — 1× in this paper · explained in 8 episodes

Sources

• GPT-4 Technical Report
• Qwen3-VL Technical Report
• Flow-OPD: On-Policy Distillation for Flow Matching Models
• GenEval: An Object-Focused Framework for Evaluating Text-to-Image Alignment
• UniCorn: Towards Self-Improving Unified Multimodal Models through Self-Generated Supervision
• Turning Internal Gap into Self-Improvement: Promoting the Generation-Understanding Unification in MLLMs
• LoRA: Low-Rank Adaptation of Large Language Models
• Reinforcement Learning via Self-Distillation
• D-OPSD: On-Policy Self-Distillation for Continuously Tuning Step-Distilled Diffusion Models
• SRUM: Fine-Grained Self-Rewarding for Unified Multimodal Models
• GenEval 2: Addressing Benchmark Drift in Text-to-Image Evaluation
• DiffusionOPD: A Unified Perspective of On-Policy Distillation in Diffusion Models
• Flow-GRPO: Training Flow Matching Models via Online RL
• Meta-TTRL: A Metacognitive Framework for Self-Improving Test-Time Reinforcement Learning in Unified Multimodal Models
• Gemini: A Family of Highly Capable Multimodal Models
• UniReason 1.0: A Unified Reasoning Framework for World Knowledge Aligned Image Generation and Editing
• Qwen-Image Technical Report
• Self-Distilled Reasoner: On-Policy Self-Distillation for Large Language Models
• DiffusionNFT: Online Diffusion Reinforcement with Forward Process

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
• 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
• VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection