We have 3 of 6 papers
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.
Mixed SFT, a single supervised fine-tuning stage that jointly trains on no-CoT and long-CoT data, achieves a clearly higher post-RLVR performance ceiling than next-chunk reasoning RL while requiring over 60 times less training compute.
Evaluations across scientific, multimodal, agentic, and general-purpose benchmarks show that Intern-S2-Preview-397B achieves competitive or leading results in multiple settings.
SciExplore is introduced, a benchmark designed to evaluate scientific information-seeking and reasoning capabilities of LLMs and agents, revealing substantial performance gaps with performance degrading sharply as task complexity increases and extremely low accuracy on the most challenging structured synthesis tasks.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
