Janus-MOPD: Tracing the Student Learning Dynamics in Multi-Teacher On-Policy Distillation
cs.CL
Submitted: 2026-11-11
Updated: 2026-11-11
Terminology
Sources
- MiMo-V2-Flash Technical Report
- DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence
- MOPD: Multi-Teacher On-Policy Distillation for Capability Integration in LLM Post-Training
- Beyond Domain-Routed Supervision: Cross-Teacher Guarding for Multi-Teacher On-Policy Distillation
- No Pain, More Gain: Iterative Merging for Effective Multi-Teacher On-Policy Distillation
- Composing What Each Teacher Learned: Delta Distillation for Multi-Teacher On-Policy Learning
- D cubed-MOPD: Dynamic Domain ScheDuling for Efficient Multi-Teacher Distillation
- MOPD-Router: Rethinking Teacher Routing in Multi-Teacher On-Policy Distillation
- Distill What You Trust: Reliability-Aware Multi-Teacher On-Policy Distillation
- Counteraction-Aware Multi-Teacher On-Policy Distillation for General Capability Recovery with Domain Preservation
- Beyond Teacher Assignment: Domain-Normalized Multi-Teacher On-Policy Distillation
- Every Coin Has Two Sides: On the Dual Nature of Generalization in On-Policy Distillation of Large Language Models
- ReSI: Recursive Safety Improvement toward Resistant and Resilient AI
- Harmony in Diversity: Multi-domain Contrastive Policy Optimization for Large Reasoning Models
- Qwen3 Technical Report
- MARCH: Scaling Recurrent Memory with Content-Routed State Anchors
- Safin-1: Safety from Within through Memory-Native State Evolution
- Safin-1.5: Safety-Native Architecture and Verifiable Reasoning for Recursive Safety Improvement
- GPQA: A Graduate-Level Google-Proof Q&A Benchmark
Related papers
- ALARM: Audio-Language Alignment for Reasoning Models
- ThinkSum: Probabilistic reasoning over sets using large language models
- Coherence boosting: When your pretrained language model is not paying enough attention
- From Facts to Insights: A Persona-Driven Dual Memory Framework and Dataset for Role-Playing Agents
- Improving General Role-Playing Agents via Psychology-Grounded Reasoning and Role-Aware Policy Optimization
- The Art of Asking: Multilingual Prompt Optimization for Synthetic Data