This work introduces Safin-1.5, a model built on a safety architecture and trained through recursive safety improvement, with an inference-time harness that extends its capabilities to formal reasoning, and demonstrates that Safin-1.5 achieves safety and reasoning performance, outperforming frontier models.
Jing-Nan Zheng, Cheng Jin, Ming Zhang et al.· 1 citation
BiPA is introduced, which replays an optimizer's acceptance rule on candidates identical to its seed to measure what selection alone reports, and records each episode as a bipartite graph of turns and the text they read to trace extra input tokens to the behavior behind them.
Jia-Wei Zhou, Bo Peng, Yuxuan Huang et al.· 0 citations
Recursive self-improvement, the participation of AI systems in improving their own capabilities, is beginning to move from theoretical prospect to practice, posing both challenges and opportunities for safety alignment. Models evolve through frequent updates, and their safety alignment requires continual adaptation to...
Jing-Nan Zheng, Dong-Cheng Zhang, Yi Zhang et al.· 2 citations
Downstream RLHF experiments additionally show that using DRM as the training-time reward leads to improved policy performance, directly validating the practical benefit of diffusion-based reward modeling for RLHF training.
Xiang-Yang Wang, Bing-Xiang He, Ze-Yuan Liu et al.· arXiv.org· 0 citations
JustQuant is proposed, a simple yet effective framework that moves the complexity of low-bit quantization from deployment-time operators into the training process and introduces Theseus QAD, a quantization-aware distillation method that progressively applies multi-level supervision, analogous to the gradual replacement...
Kai-Cheng Yang, Kai-Sen Yang, Chun-Yu Liu et al.· 0 citations
OpenMLE is introduced, an open full-stack system for RSI research in MLE, spanning verifiable task environments with execution feedback, operator learning, and long-horizon search (OpenMLE-Evo) and enabling reproducible research on executable AI4AI toward RSI.
Junlin Yang, Che Jiang, Yu Fu et al.· arXiv.org· 7 citations
The routed-state interface unifies contextual memory and persistent capability adaptation within the model's native computation, reframing memory from a passive record of prior context into an active substrate for maintaining and evolving model behavior.
Ming Zhang, Kai-Sen Yang, Shu Yu et al.· 0 citations
Memory-Anchor Routing across Context History (MARCH), a network architecture that effectively scales state-space models beyond a fixed-size dimension, while maintaining computational efficiency over long-sequences, is introduced.
Ming Zhang, Kai-Sen Yang, Shu Yu et al.· 1 citation
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.