Linqi Han

This repository contains the model-only checkpoint saved at 30,000 training steps. The files at the repository root are the original contents of checkpoint-30000. Full model and processor settings are in config.json, processorconfig.json, and experimentcfg/. The training run did not include an evaluation. Source checkpoint: outputs/moeforcetransformertuningobs2h1020260926223332/vasev6k12s1e6f384xformer/vasev6/moe/checkpoint-30000.

This repository contains the model-only checkpoint saved at 30,000 training steps. The files at the repository root are the original contents of checkpoint-30000. Full model and processor settings are in config.json, processorconfig.json, and experimentcfg/. The training run did not include an evaluation. Source checkpoint: outputs/moeforcetransformertuningobs2h1020260926223332/usbk6s1e4f384xformer/usb/moe/checkpoint-30000.

This repository contains the model-only checkpoint saved at 30,000 training steps. The files at the repository root are the original contents of checkpoint-30000. Full model and processor settings are in config.json, processorconfig.json, and experimentcfg/. The training run did not include an evaluation. Source checkpoint: outputs/moeforcetransformertuningobs2h1020260926223332/whiteboardv9k8s1e6f384xformer/whiteboardv9/moe/checkpoint-30000.

This repository contains the model-only checkpoint saved at 30,000 training steps. The files at the repository root are the original contents of checkpoint-30000. Full model and processor settings are in config.json, processorconfig.json, and experimentcfg/. The training run did not include an evaluation. Source checkpoint: outputs/moeobs2h10fourtasks20260926191812/pair67/usb/moe/checkpoint-30000.

This repository contains the model-only checkpoint saved at 30,000 training steps. The files at the repository root are the original contents of checkpoint-30000. Full model and processor settings are in config.json, processorconfig.json, and experimentcfg/. The training run did not include an evaluation. Source checkpoint: outputs/moeobs2h10fourtasks20260926191812/pair67/vasev6/moe/checkpoint-30000.

This repository contains the model-only checkpoint saved at 30,000 training steps. The files at the repository root are the original contents of checkpoint-30000. Full model and processor settings are in config.json, processorconfig.json, and experimentcfg/. The training run did not include an evaluation. Source checkpoint: outputs/moeobs2h10fourtasks20260926191812/pair45/whiteboardv9/moe/checkpoint-30000.

This repository contains the model-only checkpoint saved at 30,000 training steps. The files at the repository root are the original contents of checkpoint-30000. Full model and processor settings are in config.json, processorconfig.json, and experimentcfg/. The training run did not include an evaluation. Source checkpoint: outputs/moeobs2h10fourtasks20260926191812/pair45/weightsorting/moe/checkpoint-30000.

This repository contains ten independent, model-only checkpoint-30000 directories. Each was trained for 30,000 steps with two image and joint-state observations, action horizon 10, and global batch size 32. The original checkpoint configuration, processor, normalization statistics, tokenizer files and safetensors are retained in each directory. These training runs did not include evaluation; no success rate is claimed. The eight force runs use a four-frame six-axis wrench history, an MLP force encoder, and one force condition token. PickCube V4 MoE uses a six-frame wrench history, a temporal Transformer force encoder, one force token, four experts, and top-1 routing. The two PickCube V4…

Five independently trained, model-only checkpoints at 30,000 steps, all from nvidia/GR00T-N1.7-3B. Every folder named checkpoint-30000 is directly loadable with its own config, processor, and statistics. All use observation history 2, action horizon 10, and global batch size 32. PickCube V4 force and MoE use the invalid-action loss mask and recovery sample weights. The files are the original saved checkpoints, including training configuration. manifest.json lists SHA-256 checksums for every file. Training completion and checkpoint validation do not imply an evaluation score.

This public repository collects one USB-B no-force baseline and eight independent force MoE experiments (Q02–Q09). Each run trains for 30,000 optimizer steps. Only final checkpoints that pass local validation and remote integrity verification are listed as uploaded. The uploader watches the remaining runs and adds them here. Each checkpoint directory includes complete indexed Safetensors weights, model configuration, processor files, normalization statistics, and embodiment information. The MoE checkpoints use a shared frozen-weight shard plus an experiment-specific trainable-weight shard; the index references both files in the same directory. Load each checkpoint with the ForceBenchmark…

This dataset contains 300 simulated expert episodes across six RoboTwin tasks, with 15,455 windows for predicting the motion of object and robot end-effector points. It was prepared for the Trace-MoT experiments. The data is simulation-only. The object queries use simulator segmentation to identify the intended object; this provides oracle target information. - raw/ /episode /episode.hdf5: head, left, and right camera RGB observations, head depth and segmentation, camera calibration, robot end pose, and joint actions. - raw/ /episode /queries.npz and poses.npz: original point queries and simulator pose data used in label generation. - raw/ /episode /instruction.json: task instructions.…