SIRI - a THU-KEG Collection

THU-KEG 's Collections

SIRI

VerIF

OpenSAE-LLaMA-3.1-8B

Crab

ADELIE

SIRI

updated Sep 30, 2025

Scaling Iterative Reinforcement Learning with Interleaved Compression

SIRI: Scaling Iterative Reinforcement Learning with Interleaved Compression

Paper • 2509.25176 • Published Sep 29, 2025 • 13
THU-KEG/SIRI-7B-high

Text Generation • 8B • Updated Sep 30, 2025 • 6 • 5
THU-KEG/SIRI-7B-low

Text Generation • 8B • Updated Sep 30, 2025 • 19 • 2
THU-KEG/SIRI-1.5B-high

Text Generation • 2B • Updated Sep 30, 2025 • 14 • 3
THU-KEG/SIRI-1.5B-low

Text Generation • 2B • Updated Sep 30, 2025 • 8 • 2