Khalil Meftah 8ff4a96b5e feat(rewards): add temporal SigLIP2 and nanoVLM value functions ...

- add isolated configs, models, processors, and tests
- add shared distributional value utilities
- add VF overfit comparison harness
- add standalone Gemma3 VLM alignment workflow
- keep the committed RECAP baseline unchanged

2026-07-23 21:24:52 +02:00

..

__init__.py

Reward models refactor (#3142)

2026-04-28 17:56:24 +02:00

test_classifier_processor.py

Reward models refactor (#3142)

2026-04-28 17:56:24 +02:00

test_distributional_value_function.py

feat(recap): align value function with pi0.6 Gemma3 VLM

2026-07-23 13:38:07 +02:00

test_modeling_classifier.py

RL stack refactoring (#3075)

2026-05-12 15:49:54 +02:00

test_modeling_robometer.py

feat(rewards): add ROBOMETER reward model (#3627)

2026-05-29 21:45:39 +02:00

test_modeling_topreward.py

feat(rewards): add TOPReward reward model (#3629)

2026-05-27 14:24:31 +02:00

test_nanovlm_value_function.py

feat(rewards): add temporal SigLIP2 and nanoVLM value functions

2026-07-23 21:24:52 +02:00

test_reward_model_base.py

fix(train): migrate legacy RA-BC fields in train config loading (#3480)

2026-04-29 16:17:00 +02:00

test_robometer_processor.py

feat(rewards): add ROBOMETER reward model (#3627)

2026-05-29 21:45:39 +02:00

test_sarm_processor.py

Reward models refactor (#3142)

2026-04-28 17:56:24 +02:00

test_sarm_utils.py

Reward models refactor (#3142)

2026-04-28 17:56:24 +02:00

test_temporal_siglip_value_function.py

feat(rewards): add temporal SigLIP2 and nanoVLM value functions

2026-07-23 21:24:52 +02:00

test_topreward_processor.py

feat(rewards): add TOPReward reward model (#3629)

2026-05-27 14:24:31 +02:00

test_topreward.py

feat(rewards): add TOPReward reward model (#3629)

2026-05-27 14:24:31 +02:00