Decomposes VLM distillation loss into orthogonal language and visual components and introduces Visual Gradient Steering to prioritize visual grounding over standard monolithic optimization.
Supervised reinforcement learning: From expert trajectories to step-wise reasoning.CoRR, abs/2510.25992
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
years
2026 4roles
background 2polarities
background 2representative citing papers
AIPO adds active multi-agent consultation (Verify, Knowledge, Reasoning agents) plus custom importance sampling to RLVR training so LLMs expand their reasoning boundary and then operate without the agents.
Survey mapping RL techniques onto LLM training and highlighting gaps in value-based, off-policy, and bootstrapping methods.
Novice programmers completed more tasks with lower workload using GitHub Copilot versus a human partner, but reported significantly more positive and arousing emotions with the human teammate.
citing papers explorer
-
Decomposed On-Policy Distillation for Vision-Language Reasoning: Steering Gradients for Visual Grounding
Decomposes VLM distillation loss into orthogonal language and visual components and introduces Visual Gradient Steering to prioritize visual grounding over standard monolithic optimization.
-
AIPO: Learning to Reason from Active Interaction
AIPO adds active multi-agent consultation (Verify, Knowledge, Reasoning agents) plus custom importance sampling to RLVR training so LLMs expand their reasoning boundary and then operate without the agents.
-
Modularized Reinforcement Learning on LLMs: From MDP Creation to Exploration and Learning
Survey mapping RL techniques onto LLM training and highlighting gaps in value-based, off-policy, and bootstrapping methods.
-
OGER: A Robust Offline-Guided Exploration Reward for Hybrid Reinforcement Learning
Novice programmers completed more tasks with lower workload using GitHub Copilot versus a human partner, but reported significantly more positive and arousing emotions with the human teammate.