Improving OCR Faithfulness via Gated and Attenuated On-Policy Distillation
cs.AI
Submitted: 2026-09-29
Updated: 2026-09-29
Terminology
Sources
- Reward-Gated On-Policy Distillation
- Qwen2.5-VL Technical Report
- Does On-Policy Distillation Really Distill? From Noisy Teacher to Self-Improvement
- Distill Where You Fail: Recovering Learning Signals of Negative RL-Groups from Adaptive Teacher Guidance
- Infinity-Parser2 Technical Report
- Do VLMs Read or Rewrite? On Transcription Faithfulness in Vision-Language Models
- HunyuanOCR-1.5: Making Lightweight OCR VLMs Faster and Better
- MonkeyOCR: Document Parsing with a Structure-Recognition-Relation Triplet Paradigm
- Teacher-Guided Policy Optimization for On-Policy Reasoning Distillation under Large Policy Divergence
- OvisOCR2 Technical Report
- olmOCR 2: Unit Test Rewards for Document OCR
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- KDRL: Post-Training Reasoning LLMs via Unified Knowledge Distillation and Reinforcement Learning
- PACED: Distillation and On-Policy Self-Distillation at the Frontier of Student Competence
- I-SDPO: Instance-Level Adaptive Self-Distillation Policy Optimization
- PaddleOCR-VL-1.6: Expanding the Frontier of Document Parsing with Under-Optimized Region Refinement and Progressive Post-Training
- Self-Distilled Reasoner: On-Policy Self-Distillation for Large Language Models
- Beyond Hallucinations: Enhancing LVLMs through Hallucination-Aware Direct Preference Optimization
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