Draft-OPD, which uses target-assisted rollout for stable continuations and replays drafting from the verification-exposed error positions, allowing the drafter to learn from target feedback on both accepted and rejected proposals, focusing on the draft-induced errors that limit speculative acceptance.
It is demonstrated that PI-Mem breaks the accuracy--efficiency trade-off in long-context reasoning and provides a scalable approach to complex multi-hop question answering over extremely long documents.
Da-Wei Liu, Haixu Song, Shuang Cheng 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.
