AR-OPD disentangles privileged supervision via anchored residual guidance to reduce hindsight leakage in on-policy distillation, reporting gains of 2.3 points over full privileged OPD and 7.9 over SFT on reasoning tasks.
arXiv preprint arXiv:2509.23753 (2025)
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
years
2026 5verdicts
UNVERDICTED 5representative citing papers
RASFT is an adaptive SFT method that strengthens or relaxes expert imitation per problem based on on-policy rollout solvability and adds clipped reference-policy ratio to limit drift, reporting better results than standard SFT and RL on math and code benchmarks.
InDex adapts VLA models to high-DoF dexterous manipulation via intent-conditioned fine-tuning and a decoupled diffusion head, outperforming monolithic baselines in simulation tasks with minimal data.
GAC derives adaptive mixing weights for SFT-RL hybrid post-training from online gradient variance and signal disagreement estimates, improving benchmark performance over fixed schedules with under 1% overhead.
EKSFT masks high-entropy or high-KL tokens in low-data SFT to preserve pre-trained distribution and improve downstream RL performance on math reasoning tasks.
citing papers explorer
-
Beyond Absolute Imitation: Anchored Residual Guidance for Privileged On-Policy Distillation
AR-OPD disentangles privileged supervision via anchored residual guidance to reduce hindsight leakage in on-policy distillation, reporting gains of 2.3 points over full privileged OPD and 7.9 over SFT on reasoning tasks.
-
RASFT: Rollout-Adaptive Supervised Fine-Tuning for Reasoning
RASFT is an adaptive SFT method that strengthens or relaxes expert imitation per problem based on on-policy rollout solvability and adds clipped reference-policy ratio to limit drift, reporting better results than standard SFT and RL on math and code benchmarks.
-
Bridging the Morphology Gap: Adapting VLA Models to Dexterous Manipulation via Intent-Conditioned Fine-Tuning
InDex adapts VLA models to high-DoF dexterous manipulation via intent-conditioned fine-tuning and a decoupled diffusion head, outperforming monolithic baselines in simulation tasks with minimal data.
-
GAC: Noise-Aware Adaptive Mixing for Hybrid SFT-RL Post-Training
GAC derives adaptive mixing weights for SFT-RL hybrid post-training from online gradient variance and signal disagreement estimates, improving benchmark performance over fixed schedules with under 1% overhead.
-
Entropy-KL Divergence-based Token Masking: A Novel Approach for Selective Fine-tuning of Large Language Models
EKSFT masks high-entropy or high-KL tokens in low-data SFT to preserve pre-trained distribution and improve downstream RL performance on math reasoning tasks.