dGRPO merges outcome-based policy optimization with dense teacher guidance from on-policy distillation, yielding more stable long-context reasoning on the new LongBlocks synthetic dataset.
Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) , publisher =
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
AdaSplash-2 introduces a histogram-based initialization for the α-entmax normalizer that cuts iterations to 1-2 and, with a sparsity-aware GPU kernel, matches or beats FlashAttention-2 training speed at moderate-to-high sparsity while delivering long-context gains.
citing papers explorer
-
Combining On-Policy Optimization and Distillation for Long-Context Reasoning in Large Language Models
dGRPO merges outcome-based policy optimization with dense teacher guidance from on-policy distillation, yielding more stable long-context reasoning on the new LongBlocks synthetic dataset.
-
AdaSplash-2: Faster Differentiable Sparse Attention
AdaSplash-2 introduces a histogram-based initialization for the α-entmax normalizer that cuts iterations to 1-2 and, with a sparsity-aware GPU kernel, matches or beats FlashAttention-2 training speed at moderate-to-high sparsity while delivering long-context gains.