RIM-pytorch

RIM-pytorch (wip)

Explorations into Recurrent Independent Mechanisms, from Goyal et al. of MILA

Jeff Hawkins would be delighted if this were to pan out

Install

$ pip install RIM-pytorch

Citations

@misc{goyal2020recurrentindependentmechanisms,
    title   = {Recurrent Independent Mechanisms},
    author  = {Anirudh Goyal and Alex Lamb and Jordan Hoffmann and Shagun Sodhani and Sergey Levine and Yoshua Bengio and Bernhard Schölkopf},
    year    = {2020},
    eprint  = {1909.10893},
    archivePrefix = {arXiv},
    primaryClass = {cs.LG},
    url     = {https://arxiv.org/abs/1909.10893},
}

@misc{lamb2021transformerscompetitiveensemblesindependent,
    title   = {Transformers with Competitive Ensembles of Independent Mechanisms},
    author  = {Alex Lamb and Di He and Anirudh Goyal and Guolin Ke and Chien-Feng Liao and Mirco Ravanelli and Yoshua Bengio},
    year    = {2021},
    eprint  = {2103.00336},
    archivePrefix = {arXiv},
    primaryClass = {cs.LG},
    url     = {https://arxiv.org/abs/2103.00336},
}

@misc{kimiteam2026attentionresiduals,
    title   = {Attention Residuals},
    author  = {Kimi Team and Guangyu Chen and Yu Zhang and Jianlin Su and Weixin Xu and Siyuan Pan and Yaoyu Wang and Yucheng Wang and Guanduo Chen and Bohong Yin and Yutian Chen and Junjie Yan and Ming Wei and Y. Zhang and Fanqing Meng and Chao Hong and Xiaotong Xie and Shaowei Liu and Enzhe Lu and Yunpeng Tai and Yanru Chen and Xin Men and Haiqing Guo and Y. Charles and Haoyu Lu and Lin Sui and Jinguo Zhu and Zaida Zhou and Weiran He and Weixiao Huang and Xinran Xu and Yuzhi Wang and Guokun Lai and Yulun Du and Yuxin Wu and Zhilin Yang and Xinyu Zhou},
    year    = {2026},
    eprint  = {2603.15031},
    archivePrefix = {arXiv},
    primaryClass = {cs.CL},
    url     = {https://arxiv.org/abs/2603.15031},
}

@misc{wang20261000layernetworksselfsupervised,
    title  = {1000 Layer Networks for Self-Supervised RL: Scaling Depth Can Enable New Goal-Reaching Capabilities},
    author = {Kevin Wang and Ishaan Javali and Michał Bortkiewicz and Tomasz Trzciński and Benjamin Eysenbach},
    year   = {2026},
    eprint = {2503.14858},
    archivePrefix = {arXiv},
    primaryClass = {cs.LG},
    url    = {https://arxiv.org/abs/2503.14858},
}

Metadata

Release files for RIM-pytorch 0.0.25

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for RIM-pytorch 0.0.25
File	Size	Uploaded
rim_pytorch-0.0.25.tar.gz	8.4 kB	Apr 6, 2026	Details

Built distribution (wheel)

Table of built distributions (wheels) for RIM-pytorch 0.0.25
File	Interpreter	ABI	Platform	Reset
rim_pytorch-0.0.25-py3-none-any.whl 8.4 kB Apr 6, 2026	Python 3	none	any	Details

Total release size: 16.8 kB

Release files / rim_pytorch-0.0.25.tar.gz

Download URL	rim_pytorch-0.0.25.tar.gz
Size	8.4 kB
Tags	Source
SHA-256 checksum How to use checksums	`f35758435aa2538b6c9f154f5a0849579c140bc8479a74527a0b265178716b4b`
BLAKE2b-256 checksum How to use checksums	`6bc6a29e5730fb3c3f3bf98b57591c40b0e36a2fb274a0fd83944c0f2e0277a7`
Upload date	Apr 6, 2026
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`uv/0.8.13`

Release files / rim_pytorch-0.0.25-py3-none-any.whl

Download URL	rim_pytorch-0.0.25-py3-none-any.whl
Size	8.4 kB
Tags	Python 3
SHA-256 checksum How to use checksums	`2a4e9ca8276d34ded3c24add8c5c9a1962db78acd54a39318f97b822e89afa5f`
BLAKE2b-256 checksum How to use checksums	`998440c1bb00c1995d722b75541c9c900894112833bb3fbb6a4c004f40fab70a`
Upload date	Apr 6, 2026
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`uv/0.8.13`