RLVR-World: Training World Models with Reinforcement Learning
Paper • 2505.13934 • Published • 16
RLVR-World
-
-
thuml/rt1-frame-tokenizer
Updated • 12 -
thuml/rt1-world-model-single-step-base
0.1B • Updated • 8 -
thuml/rt1-world-model-single-step-rlvr
Updated • 5 -
thuml/rt1-compressive-tokenizer
Updated • 10 -
thuml/rt1-world-model-multi-step-base
0.1B • Updated • 4 -
thuml/rt1-world-model-multi-step-rlvr
Updated • 6 -
thuml/webarena-world-model-cot
Viewer • Updated • 6.41k • 95 -
thuml/webarena-world-model-sft
2B • Updated • 2 -
thuml/webarena-world-model-rlvr
2B • Updated • 1 -
thuml/bytesized32-world-model-cot
Viewer • Updated • 304k • 28 • 3 -
thuml/bytesized32-world-model-sft
2B • Updated • 8 -
thuml/bytesized32-world-model-rlvr-binary-reward
2B • Updated • 3 -
thuml/bytesized32-world-model-rlvr-task-specific-reward
2B • Updated • 3