Key papers

• TREK: Distill to Explore, Reinforce to Refine (2026)
  Yuanda Xu et al.
  2.00
• Ministral 3 (2026)
  Alexander H. Liu et al.
  1.94
• WebArbiter: A Principle-Guided Reasoning Process Reward Model for Web Agents (2026)
  Yao Zhang et al.
  1.94
• Hybrid Linear Attention Done Right: Efficient Distillation and Effective Architectures for Extremely Long Contexts (2026)
  Yingfa Chen et al.
  1.94
• THINKSAFE: Self-Generated Safety Alignment for Reasoning Models (2026)
  Seanie Lee et al.
  1.94
• Privileged Information Distillation for Language Models (2026)
  Emiliano Penaloza et al.
  1.94
• Zooming without Zooming: Region-to-Image Distillation for Fine-Grained Multimodal Perception (2026)
  Lai Wei et al.
  1.94
• NanoVDR: Distilling a 2B Vision-Language Retriever into a 70M Text-Only Encoder for Visual Document Retrieval (2026)
  Zhuchenyang Liu et al.
  1.94
• ShotStream: Streaming Multi-Shot Video Generation for Interactive Storytelling (2026)
  Yawen Luo et al.
  1.94
• Self-Distillation Zero: Self-Revision Turns Binary Rewards into Dense Supervision (2026)
  Yinghui He et al.
  1.94
• Unmasking On-Policy Distillation: Where It Helps, Where It Hurts, and Why (2026)
  Mohammadreza Armandpour et al.
  1.94
• HINT-SD: Targeted Hindsight Self-Distillation for Long-Horizon Agents (2026)
  Woongyeng Yeo et al.
  1.94
• CollectionLoRA: Collecting 50 Effects in 1 LoRA via Multi-Teacher On-Policy Distillation (2026)
  Fangtai Wu et al.
  1.94
• Not All Disagreement Is Learnable: Token Teachability in On-Policy Distillation (2026)
  Yuanyi Wang et al.
  1.94
• OPRD: On-Policy Representation Distillation (2026)
  Shenzhi Yang et al.
  1.94
• Ling and Ring 2.6 Technical Report: Efficient and Instant Agentic Intelligence at Trillion-Parameter Scale (2026)
  Ang Li et al.
  1.94
• TESSERA v2: Scaling Pixel-wise Earth Foundation Models (2026)
  Zhengpeng Feng et al.
  1.94
• Skill1: Unified Evolution of Skill-Augmented Agents via Reinforcement Learning (2026)
  Yaorui Shi et al.
  1.89
• Trajectory as the Teacher: Few-Step Discrete Flow Matching via Energy-Navigated Distillation (2026)
  Amin Karimi Monsefi et al.
  1.89
• Adapting Multilingual Embedding Models to Turkish via Cross-Lingual Tokenizer Surgery and Offline Distillation (2026)
  M. Ali Bayram et al.
  1.89
• COLLEAGUE.SKILL: Automated AI Skill Generation via Expert Knowledge Distillation (2026)
  Tianyi Zhou et al.
  1.89
• Small Vision-Language Models are Smart Compressors for Long Video Understanding (2026)
  Junjie Fei et al.
  1.83
• TIP: Token Importance in On-Policy Distillation (2026)
  Yuanda Xu et al.
  1.83
• Beyond SFT-to-RL: Pre-alignment via Black-Box On-Policy Distillation for Multimodal RL (2026)
  Sudong Wang et al.
  1.83
• Nemotron-Cascade 2: Post-Training LLMs with Cascade RL and Multi-Domain On-Policy Distillation (2026)
  Zhuolin Yang et al.
  1.78
• Learning to Detect Language Model Training Data via Active Reconstruction (2026)
  Junjie Oscar Yin et al.
  1.72
• Reinforcement Learning via Self-Distillation (2026)
  Jonas Hübotter et al.
  1.67
• OVD: On-policy Verbal Distillation (2026)
  Jing Xiong et al.
  1.67
• Democratizing Text-to-Image Masked Generative Models with Compact Text-Aware One-Dimensional Tokens (2025)
  Dongwon Kim et al.
  1.28
• Learning Few-Step Diffusion Models by Trajectory Distribution Matching (2025)
  Yihong Luo et al.
  1.28
• SANA-Sprint: One-Step Diffusion with Continuous-Time Consistency Distillation (2025)
  Junsong Chen et al.
  1.28
• Distillation and Refinement of Reasoning in Small Language Models for Document Re-ranking (2025)
  Chris Samarinas et al.
  1.28
• Skywork R1V: Pioneering Multimodal Reasoning with Chain-of-Thought (2025)
  Yi Peng et al.
  1.28
• Pixel-SAIL: Single Transformer For Pixel-Grounded Understanding (2025)
  Tao Zhang et al.
  1.28
• SFT or RL? An Early Investigation into Training R1-Like Reasoning Large Vision-Language Models (2025)
  Hardy Chen et al.
  1.28
• Simple Semi-supervised Knowledge Distillation from Vision-Language Models via texttt{D}ual-texttt{H}ead texttt{O}ptimization (2025)
  Seongjae Kang et al.
  1.28
• How Should We Enhance the Safety of Large Reasoning Models: An Empirical Study (2025)
  Zhexin Zhang et al.
  1.28
• AceReason-Nemotron: Advancing Math and Code Reasoning through Reinforcement Learning (2025)
  Yang Chen et al.
  1.28
• Cascading Adversarial Bias from Injection to Distillation in Language Models (2025)
  Harsh Chaudhari et al.
  1.28
• Harnessing Negative Signals: Reinforcement Distillation from Teacher Data for LLM Reasoning (2025)
  Shuyao Xu et al.
  1.28
• When Big Models Train Small Ones: Label-Free Model Parity Alignment for Efficient Visual Question Answering using Small VLMs (2025)
  Abhirama Subramanyam Penamakuri et al.
  1.28
• Interactive Recommendation Agent with Active User Commands (2025)
  Jiakai Tang et al.
  1.28
• When Does Reasoning Matter? A Controlled Study of Reasoning's Contribution to Model Performance (2025)
  Nicolas Boizard et al.
  1.28
• Thinking-Free Policy Initialization Makes Distilled Reasoning Models More Effective and Efficient Reasoners (2025)
  Xin Xu et al.
  1.28
• Fantastic (small) Retrievers and How to Train Them: mxbai-edge-colbert-v0 Tech Report (2025)
  Rikiya Takehi et al.
  1.28
• EvoSyn: Generalizable Evolutionary Data Synthesis for Verifiable Learning (2025)
  He Du et al.
  1.28
• Distilled Decoding 2: One-step Sampling of Image Auto-regressive Models with Conditional Score Distillation (2025)
  Enshu Liu et al.
  1.28
• Flow Map Distillation Without Data (2025)
  Shangyuan Tong et al.
  1.28
• Image-Free Timestep Distillation via Continuous-Time Consistency with Trajectory-Sampled Pairs (2025)
  Bao Tang et al.
  1.28
• MemLoRA: Distilling Expert Adapters for On-Device Memory Systems (2025)
  Massimo Bini et al.
  1.28
• InfiniteVL: Synergizing Linear and Sparse Attention for Highly-Efficient, Unlimited-Input Vision-Language Models (2025)
  Hongyuan Tao et al.
  1.28
• ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillation (2023)
  Zhengyi Wang et al.
  —
• On-Policy Distillation of Language Models: Learning from Self-Generated Mistakes (2023)
  Rishabh Agarwal et al.
  —
• SAM-CLIP: Merging Vision Foundation Models towards Semantic and Spatial Understanding (2023)
  Haoxiang Wang et al.
  —
• Localized Symbolic Knowledge Distillation for Visual Commonsense Models (2023)
  Jae Sung Park et al.
  —
• PALP: Prompt Aligned Personalization of Text-to-Image Models (2024)
  Moab Arar et al.
  —
• Vision Superalignment: Weak-to-Strong Generalization for Vision Foundation Models (2024)
  Jianyuan Guo et al.
  —
• Trajectory Consistency Distillation (2024)
  Jianbin Zheng et al.
  —
• Self-play with Execution Feedback: Improving Instruction-following Capabilities of Large Language Models (2024)
  Guanting Dong et al.
  —
• Heavy Labels Out! Dataset Distillation with Label Space Lightening (2024)
  Ruonan Yu et al.
  —