Khalil Meftah 2aa7f601cd feat(recap): align value function with pi0.6 Gemma3 VLM ...

- use 448px SigLIP2 inputs with 2x2 pooling
- adopt native Gemma3 projector and attention masking
- support aligned VLM checkpoints
- update preprocessing, targets, and tests

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

..

annotations

fix(annotation): remove dropout when doing annotation

2026-07-11 11:09:24 +02:00

artifacts

feat(encoding parameters): adding support for user provided video encoding parameters (#3455)

2026-05-14 23:46:42 +02:00

async_inference

feat(dependencies): minimal default tag install (#3362)

2026-04-12 20:03:04 +02:00

cameras

test(cameras): skip flaky async_read test (#3106)

2026-03-08 14:02:33 +01:00

configs

feat(recap): add advantage conditioning recipe YAMLs

2026-07-03 16:55:41 +02:00

datasets

fix(save codec options): making sure codec options are always set via set_if (#3910)

2026-07-02 15:29:14 +02:00

envs

feat(envs): add RoboTwin 2.0 benchmark (#3315)

2026-04-20 17:46:39 +02:00

fixtures

fix(depth unit): adding input depth unit storage in the dataset metadata (#3899)

2026-07-02 11:53:13 +02:00

jobs

feat(train): run training remotely on HF Jobs via --job.target (#3856)

2026-06-29 17:59:33 +02:00

mocks

feat(dependencies): minimal default tag install (#3362)

2026-04-12 20:03:04 +02:00

motors

fix(feetech): motor position readings overflow (#3373)

2026-04-13 22:39:58 +02:00

optim

feat(train): FSDP checkpoint saving (#3810)

2026-06-22 13:51:21 +02:00

policies

feat(pi05): implement Classifier-Free Guidance (CFG) inference

2026-07-03 16:58:11 +02:00

processor

feat(pi05): integrate RenderMessagesStep for advantage conditioning

2026-07-03 16:58:11 +02:00

rewards

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

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

rl

RL stack refactoring (#3075)

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

robots

Feat(robot): add MIT control mode to ReBot (#3778)

2026-06-30 17:17:50 +02:00

scripts

feat(recap): add lerobot-compute-returns script to compute MC returns

2026-07-03 16:55:40 +02:00

teleoperators

refactor(robots): homogenize bi-manual setups implementations (#3772)

2026-06-15 16:28:54 +02:00

training

Add inline offline validation with train/eval split (#3824)

2026-06-25 15:31:24 +02:00

transport

feat(dependencies): minimal default tag install (#3362)

2026-04-12 20:03:04 +02:00

utils

fix(depth unit): adding input depth unit storage in the dataset metadata (#3899)

2026-07-02 11:53:13 +02:00

__init__.py

chore(doc): add license header to all files (#818)

2025-03-05 17:56:51 +01:00

conftest.py

perf(tests): cache draccus docstring extraction (#3903)

2026-07-01 17:05:43 +02:00

test_available.py

feat(dependencies): minimal default tag install (#3362)

2026-04-12 20:03:04 +02:00

test_cli_peft.py

feat(rollout): decouple policy deployment from data recording with new lerobot-rollout CLI (#3413)

2026-04-28 00:57:35 +02:00

test_control_robot.py

feat(rollout): decouple policy deployment from data recording with new lerobot-rollout CLI (#3413)

2026-04-28 00:57:35 +02:00

test_robomme_env.py

feat(envs): add RoboMME benchmark (#3311)

2026-04-20 20:21:27 +02:00

test_rollout.py

feat(rollout): add episode success labeling to DAgger strategy

2026-07-03 16:58:08 +02:00

test_yaml_policy_path.py

Fix policy.path in YAML configs (PR #3145 followup) (#3597)

2026-05-26 14:01:19 +02:00

utils.py

feat(dependencies): minimal default tag install (#3362)

2026-04-12 20:03:04 +02:00