LLMs Gaming Verifiers: RLVR can Lead to Reward Hacking Paper β’ 2604.15149 β’ Published Apr 16 β’ 1
Evaluation Cards: An Interpretive Layer for AI Evaluation Reporting Paper β’ 2606.09809 β’ Published 13 days ago β’ 4
The Reward Was in Your Data All Along: Correcting Flow Matching with Discriminator-Guided RL Paper β’ 2606.19162 β’ Published 4 days ago β’ 19
The Reward Was in Your Data All Along: Correcting Flow Matching with Discriminator-Guided RL Paper β’ 2606.19162 β’ Published 4 days ago β’ 19
KletterMix: Climbing Toward High-Quality German Pretraining Data Paper β’ 2606.03773 β’ Published 18 days ago β’ 21
LeWM Collection Official checkpoints and datasets related to LeWM paper. β’ 9 items β’ Updated Mar 27 β’ 46
LIME: Making LLM Data More Efficient with Linguistic Metadata Embeddings Paper β’ 2512.07522 β’ Published Dec 8, 2025
view article Article Weβre open-sourcing our text-to-image model and the process behind it Photoroom β’ Nov 12, 2025 β’ 100