RLVR-World: Training World Models with Reinforcement Learning
Paper • 2505.13934 • Published • 16
RLVR-World
-
-
thuml/rt1-frame-tokenizer
0.1B • Updated • 33 -
thuml/rt1-world-model-single-step-base
0.1B • Updated • 14 -
thuml/rt1-world-model-single-step-rlvr
0.1B • Updated • 12 -
thuml/rt1-compressive-tokenizer
0.1B • Updated • 36 -
thuml/rt1-world-model-multi-step-base
0.1B • Updated • 26 -
thuml/rt1-world-model-multi-step-rlvr
0.1B • Updated • 25 -
thuml/webarena-world-model-cot
Viewer • Updated • 6.41k • 126 -
thuml/webarena-world-model-sft
2B • Updated • 6 -
thuml/webarena-world-model-rlvr
2B • Updated • 19 • 1 -
thuml/bytesized32-world-model-cot
Viewer • Updated • 304k • 340 • 3 -
thuml/bytesized32-world-model-sft
2B • Updated • 12 -
thuml/bytesized32-world-model-rlvr-binary-reward
2B • Updated • 8 -
thuml/bytesized32-world-model-rlvr-task-specific-reward
2B • Updated • 11