2025 Poster "convergence acceleration" Papers
2 papers found
ReDit: Reward Dithering for Improved LLM Policy Optimization
Chenxing Wei, Jiarui Yu, Ying He et al.
NEURIPS 2025posterarXiv:2506.18631
6
citations
SUMO: Subspace-Aware Moment-Orthogonalization for Accelerating Memory-Efficient LLM Training
Yehonathan Refael, Guy Smorodinsky, Tom Tirer et al.
NEURIPS 2025posterarXiv:2505.24749
6
citations