3 papers indexed here
We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.
Not the right person? Other researchers publish under this name.
Evaluations across scientific, multimodal, agentic, and general-purpose benchmarks show that Intern-S2-Preview-397B achieves competitive or leading results in multiple settings.
This work introduces an evolutionary, task-agnostic, strategy-guided, executably-checkable data synthesis framework that, from minimal seed supervision, jointly synthesizes problems, diverse candidate solutions, and verification artifacts, and iteratively discovers strategies via a consistency-based evaluator that enforces agreement be-tween human-annotated and strategy-induced checks.
This work presents Memory Decoder at Scale, scaling memory models up to 6.9B parameters and pretraining them on 300B tokens, demonstrating that independently scaling pretrained memory offers a more parameter efficient path to improving language model performance.