Shanghai AI Laboratory and Shanghai Jiao Tong University's LUMIA Lab released NCP-ArchPreview, an approximately 8.94-billion-parameter model that reaches the final Stage 1 pretraining loss of Allen In…
A new arXiv paper (2609.11061v1) proposes belief-shift branching, a fork-placement method for tree-structured reinforcement learning with verifiable rewards that forks a chain just before the step whe…
AMD released Instella-MoE-16B-A3B, a fully open Mixture-of-Experts language model with 16B total parameters and 2.8B active per token, trained from scratch on Instinct MI300X and MI325X GPUs. The mode…
A new study from a BlueDot Project cohort introduces value dynamics, a framework for measuring, forecasting, and steering how AI values change in self-training loops. Using tools from population genet…
Researchers introduced Self-Review Reinforcement Learning (SRRL), a training framework that embeds a self-review step into each RL episode to help large language models learn from sparse feedback. SRR…