SSOPD converts intra-group correct-wrong contrast into process supervision by distilling a teacher distribution from the shortest correct completion into prefixes of the longest wrong completion, improving GRPO on AIME and HMMT benchmarks.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.LG 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
SLICE applies gradient surgery via projection and truncated SVD to initialize LoRA adapters, yielding better stability-plasticity trade-offs on continual learning benchmarks including adversarial task sequences.
citing papers explorer
-
Self-Supervised On-Policy Distillation for Reasoning Language Models
SSOPD converts intra-group correct-wrong contrast into process supervision by distilling a teacher distribution from the shortest correct completion into prefixes of the longest wrong completion, improving GRPO on AIME and HMMT benchmarks.
-
Low-Rank Adapters Initialization via Gradient Surgery for Continual Learning
SLICE applies gradient surgery via projection and truncated SVD to initialize LoRA adapters, yielding better stability-plasticity trade-offs on continual learning benchmarks including adversarial task sequences.