NExt accelerates RLVR training for LLMs by nonlinearly extrapolating low-rank parameter trajectories extracted from LoRA runs.
Early weight averaging meets high learning rates for llm pre-training
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3verdicts
UNVERDICTED 3representative citing papers
Distribution-wise rewards with subset-replace strategy and post-hoc merging improve FID-50K on SiT (8.30 to 5.77) and EDM2 (3.74 to 3.52) while preserving diversity.
ORBIT preserves foundational language capabilities during generative retrieval fine-tuning by using origin-regulated weight averaging to constrain parameter drift beyond a distance threshold.
citing papers explorer
-
Low-rank Optimization Trajectories Modeling for LLM RLVR Acceleration
NExt accelerates RLVR training for LLMs by nonlinearly extrapolating low-rank parameter trajectories extracted from LoRA runs.
-
Optimizing Visual Generative Models via Distribution-wise Rewards
Distribution-wise rewards with subset-replace strategy and post-hoc merging improve FID-50K on SiT (8.30 to 5.77) and EDM2 (3.74 to 3.52) while preserving diversity.
-
ORBIT: Preserving Foundational Language Capabilities in GenRetrieval via Origin-Regulated Merging
ORBIT preserves foundational language capabilities during generative retrieval fine-tuning by using origin-regulated weight averaging to constrain parameter drift beyond a distance threshold.