On-Policy Attention Linearization
cs.LG
Submitted: 2026-09-25
Updated: 2026-09-25
Terminology
Sources
- Longformer: The Long-Document Transformer
- Priming: Hybrid State Space Models From Pre-trained Transformers
- Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge
- DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model
- Distilling the Knowledge in a Neural Network
- Training Compute-Optimal Large Language Models
- Sequence-Level Knowledge Distillation
- Morphing into Hybrid Attention Models
- MiMo-V2-Flash Technical Report
- MOPD: Multi-Teacher On-Policy Distillation for Capability Integration in LLM Post-Training
- Nemotron 3 Ultra: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning
- Nemotron 3 Nano: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning
- OpenAI o1 System Card
- Retentive Network: A Successor to Transformer for Large Language Models
- Kimi K3: Open Frontier Intelligence
- Qwen3 Technical Report
- Taylor-Calibrate: Principled Initialization for Hybrid Linear Attention Distillation
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks