idm
IDM-VTONai-light-dance_drums_ft_pretrain_wav2vec2-base-new_onset-idmt-mdb-2ui-tars-1.5-7b-idm-full-sft-i1-GGUFai-light-dance_drums_ft_pretrain_wav2vec2-base-new_onset-idmt-2IDM-VTON-F16ai-light-dance_drums_ft_pretrain_wav2vec2-base-new_onset-idmt-mdb-enst-2nsuruguay05-Llama-3.2-1B-IdM2024-GGUFui-tars-1.5-7b-idm-full-sft-8-frames-videos-GGUF
Datasets
All datasets matching “idm”idmIDMR-train
📑 IDMR Dataset (Training Set)
This repository provides the IDMR training dataset, accompanying the paper:
IDMR: Towards Instance-Driven Precise Visual Correspondence in Multimodal Retrieval
📄 arXiv 2504.00954 | 💻 GitHub
📘 Overview
The IDMR dataset is designed for Instance-Driven Multimodal Retrieval, supporting large-scale training across diverse multimodal sources.
This dataset enables research on:
Cross-dataset multimodal retrieval
Instance-driven alignment… See the full description on the dataset page: https://huggingface.co/datasets/lbw18601752667/IDMR-train.idm_ft_newThis dataset was created using LeRobot.
Dataset Structure
meta/info.json:
{
"codebase_version": "v3.0",
"robot_type": "so_follower",
"total_episodes": 501,
"total_frames": 154063,
"total_tasks": 1,
"chunks_size": 1000,
"data_files_size_in_mb": 100,
"video_files_size_in_mb": 200,
"fps": 30,
"splits": {
"train": "0:501"
},
"data_path": "data/chunk-{chunk_index:03d}/file-{file_index:03d}.parquet",
"video_path":… See the full description on the dataset page: https://huggingface.co/datasets/FrozenAngel/idm_ft_new.libero-singleview-idm
LIBERO 单视角离线 IDM：Codex 技术交接与运行手册
本文档是项目迁移到另一台机器后，供 Codex 或工程人员直接接手使用的
主运行手册。除非明确需要改变实验设计，否则应以本文、cfg/ 和
scripts/ 中的配置为准。
0. 接手结论与执行原则
项目目标是把离线 LIBERO 单视角视频转换为机器人动作：
agentview 离线视频
→ 每 16 帧生成 20×20 个均匀点轨迹
→ 单视角 Motion Tokenizer
→ 对应 LIBERO 系列的 IDM
→ 16 步 × 7 维动作
接手此项目的 Codex 应遵守以下原则：
先进入项目根目录，再执行任何脚本；所有默认路径均相对于项目根目录。
先运行资产校验。校验通过时，不要重新下载或重新生成 LIBERO 和轨迹数据。
先进行单卡或 DDP 冒烟测试，再启动完整训练。
Motion Tokenizer 只训练一个共享模型；五个 LIBERO 系列分别训练自己的 IDM。
不训练 Forward… See the full description on the dataset page: https://huggingface.co/datasets/yimmmmmy/libero-singleview-idm.idm-eval
IDM Eval Set
A validation set for evaluating Inverse Dynamics Models on macOS screen recordings. Each sample is a 5-second clip of real productivity desktop usage (browser, IDE, terminal, docs, dashboards) paired with a ground-truth action log captured at the OS level.
The task: given a short screen recording, predict the sequence of user input actions (keypresses, mouse clicks, scrolls, cursor moves) that produced the observed screen changes.
Code
Training… See the full description on the dataset page: https://huggingface.co/datasets/p-doom/idm-eval.IDMGSPTODO