ReTaCo: Residual-Target Control for On-Policy Distillation
cs.LG
Submitted: 2026-09-30
Updated: 2026-09-30
Code: https://github.com/project-numina/aimo-progress-prize
Terminology
Sources
- BD-KD: Balancing the Divergences for Online Knowledge Distillation
- Reasoning with Exploration: An Entropy Perspective
- Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge
- Process Reinforcement through Implicit Rewards
- Don't Ignore the Tail: Decoupling top-K Probabilities for Efficient Language Model Distillation
- Measuring Mathematical Problem Solving With the MATH Dataset
- Distilling the Knowledge in a Neural Network
- Entropy-Aware On-Policy Distillation of Language Models
- Let's Verify Step by Step
- Is Your Code Generated by ChatGPT Really Correct? Rigorous Evaluation of Large Language Models for Code Generation
- GPQA: A Graduate-Level Google-Proof Q&A Benchmark
- HybridFlow: A Flexible and Efficient RLHF Framework
- FIRST: Teach A Reliable Large Language Model Through Efficient Trustworthy Distillation
- Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM Reasoning
- MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark
- DAPO: An Open-Source LLM Reinforcement Learning System at Scale
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: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks