TrustJudge: Inconsistencies of LLM-as-a-Judge and How to Alleviate Them Paper • 2509.21117 • Published Sep 25, 2025 • 29
Step-3 is Large yet Affordable: Model-system Co-design for Cost-effective Decoding Paper • 2507.19427 • Published Jul 25, 2025 • 18
Farseer: A Refined Scaling Law in Large Language Models Paper • 2506.10972 • Published Jun 12, 2025 • 1
StepLaw/StepLaw-N_59M-D_7.0B-LR7.812e-03-BS1572864 Text Generation • 0.1B • Updated Apr 15, 2025 • 8
StepLaw/StepLaw-N_59M-D_7.0B-LR7.812e-03-BS131072 Text Generation • 0.1B • Updated Apr 15, 2025 • 7
StepLaw/StepLaw-N_59M-D_7.0B-LR7.812e-03-BS1048576 Text Generation • 0.1B • Updated Apr 15, 2025 • 5
StepLaw/StepLaw-N_59M-D_7.0B-LR7.812e-03-BS65536 Text Generation • 0.1B • Updated Apr 15, 2025 • 4
StepLaw/StepLaw-N_59M-D_7.0B-LR7.812e-03-BS524288 Text Generation • 0.1B • Updated Apr 15, 2025 • 7
StepLaw/StepLaw-N_59M-D_7.0B-LR7.812e-03-BS262144 Text Generation • 0.1B • Updated Apr 15, 2025 • 6
StepLaw/StepLaw-N_59M-D_7.0B-LR5.524e-03-BS1572864 Text Generation • 0.1B • Updated Apr 15, 2025 • 6
StepLaw/StepLaw-N_59M-D_7.0B-LR5.524e-03-BS131072 Text Generation • 0.1B • Updated Apr 15, 2025 • 4
StepLaw/StepLaw-N_59M-D_7.0B-LR5.524e-03-BS1048576 Text Generation • 0.1B • Updated Apr 15, 2025 • 5
StepLaw/StepLaw-N_59M-D_7.0B-LR5.524e-03-BS524288 Text Generation • 0.1B • Updated Apr 15, 2025 • 3
StepLaw/StepLaw-N_59M-D_7.0B-LR5.524e-03-BS262144 Text Generation • 0.1B • Updated Apr 15, 2025 • 3
StepLaw/StepLaw-N_59M-D_7.0B-LR3.906e-03-BS1572864 Text Generation • 0.1B • Updated Apr 15, 2025 • 3
StepLaw/StepLaw-N_59M-D_7.0B-LR3.906e-03-BS131072 Text Generation • 0.1B • Updated Apr 15, 2025 • 3
StepLaw/StepLaw-N_59M-D_7.0B-LR3.906e-03-BS1048576 Text Generation • 0.1B • Updated Apr 15, 2025 • 4
StepLaw/StepLaw-N_59M-D_7.0B-LR3.906e-03-BS65536 Text Generation • 0.1B • Updated Apr 15, 2025 • 7
StepLaw/StepLaw-N_59M-D_7.0B-LR3.906e-03-BS524288 Text Generation • 0.1B • Updated Apr 15, 2025 • 4