ML Collective
@ml-collective.bsky.social
We are an independent nonprofit organization that believes collaboration opportunities and research training should be openly accessible and free.
Web: https://mlcollective.org/
Twitter: @ml_collective
Web: https://mlcollective.org/
Twitter: @ml_collective
Stop by in 15 min to hear @ajyl.bsky.social
present his paper at DLCT!
The Geometry of Self-Verification in a Task-Specific Reasoning Model
arxiv.org/abs/2504.14379
Zoom below 👇
present his paper at DLCT!
The Geometry of Self-Verification in a Task-Specific Reasoning Model
arxiv.org/abs/2504.14379
Zoom below 👇
August 8, 2025 at 4:45 PM
Stop by in 15 min to hear @ajyl.bsky.social
present his paper at DLCT!
The Geometry of Self-Verification in a Task-Specific Reasoning Model
arxiv.org/abs/2504.14379
Zoom below 👇
present his paper at DLCT!
The Geometry of Self-Verification in a Task-Specific Reasoning Model
arxiv.org/abs/2504.14379
Zoom below 👇
Starting in 30 min at 10am PT!
@nsaphra.bsky.social presents at DLCT:
Sudden Drops in the Loss: Syntax Acquisition, Phase Transitions, and Simplicity Bias in MLMs
Angelica Chen, Ravid Shwartz-Ziv, Kyunghyun Cho, Matthew L. Leavitt, Naomi Saphra
arxiv.org/abs/2309.07311
Zoom 👇
@nsaphra.bsky.social presents at DLCT:
Sudden Drops in the Loss: Syntax Acquisition, Phase Transitions, and Simplicity Bias in MLMs
Angelica Chen, Ravid Shwartz-Ziv, Kyunghyun Cho, Matthew L. Leavitt, Naomi Saphra
arxiv.org/abs/2309.07311
Zoom 👇
July 25, 2025 at 4:37 PM
Starting in 30 min at 10am PT!
@nsaphra.bsky.social presents at DLCT:
Sudden Drops in the Loss: Syntax Acquisition, Phase Transitions, and Simplicity Bias in MLMs
Angelica Chen, Ravid Shwartz-Ziv, Kyunghyun Cho, Matthew L. Leavitt, Naomi Saphra
arxiv.org/abs/2309.07311
Zoom 👇
@nsaphra.bsky.social presents at DLCT:
Sudden Drops in the Loss: Syntax Acquisition, Phase Transitions, and Simplicity Bias in MLMs
Angelica Chen, Ravid Shwartz-Ziv, Kyunghyun Cho, Matthew L. Leavitt, Naomi Saphra
arxiv.org/abs/2309.07311
Zoom 👇
Starting in 1 hour: Joshua Batson presents Anthropic's "Biology of a Large Language Model" work at the DLCT reading group.
Paper: transformer-circuits.pub/2025/attribu...
Come for the chain of thought, stay for the rabbits and habbits.
Zoom info below 👇
Paper: transformer-circuits.pub/2025/attribu...
Come for the chain of thought, stay for the rabbits and habbits.
Zoom info below 👇
June 6, 2025 at 4:05 PM
Starting in 1 hour: Joshua Batson presents Anthropic's "Biology of a Large Language Model" work at the DLCT reading group.
Paper: transformer-circuits.pub/2025/attribu...
Come for the chain of thought, stay for the rabbits and habbits.
Zoom info below 👇
Paper: transformer-circuits.pub/2025/attribu...
Come for the chain of thought, stay for the rabbits and habbits.
Zoom info below 👇
Next Research Jam is in 14 hours, tomorrow morning at 8am PT. Stop by this virtual lab meeting to hear research ideas and updates on projects in progress!
Zoom info at mlcollective.org/events/resea...
Zoom info at mlcollective.org/events/resea...
May 28, 2025 at 1:05 AM
Next Research Jam is in 14 hours, tomorrow morning at 8am PT. Stop by this virtual lab meeting to hear research ideas and updates on projects in progress!
Zoom info at mlcollective.org/events/resea...
Zoom info at mlcollective.org/events/resea...
This week at Deep Learning: Classics and Trends we're kicking off a new five part mini-series on LLM Interpretability.
Up first: Subhash Kantamneni will show how LLMs represent numbers on a helix and use this representation to add!
Join Friday at 10am PT, zoom/etc here: mlcollective.org/dlct/
Up first: Subhash Kantamneni will show how LLMs represent numbers on a helix and use this representation to add!
Join Friday at 10am PT, zoom/etc here: mlcollective.org/dlct/
May 15, 2025 at 11:51 PM
This week at Deep Learning: Classics and Trends we're kicking off a new five part mini-series on LLM Interpretability.
Up first: Subhash Kantamneni will show how LLMs represent numbers on a helix and use this representation to add!
Join Friday at 10am PT, zoom/etc here: mlcollective.org/dlct/
Up first: Subhash Kantamneni will show how LLMs represent numbers on a helix and use this representation to add!
Join Friday at 10am PT, zoom/etc here: mlcollective.org/dlct/
A momentary IRL convergence at lunch before MLC diffuses once again to the remotest geographies. Lovely to see all you badass researchers ❤️
December 13, 2024 at 9:11 PM
A momentary IRL convergence at lunch before MLC diffuses once again to the remotest geographies. Lovely to see all you badass researchers ❤️
MLC lunch is starting in 45 min at the back of the Expo hall!
December 12, 2024 at 8:33 PM
MLC lunch is starting in 45 min at the back of the Expo hall!
Rajat Modi presenting his work right now on getting Glom to work, poster #6304.
Asynchronous Perception Machine for Efficient Test Time Training
Rajat Modi · Yogesh Rawat
West Ballroom A-D #6304
Asynchronous Perception Machine for Efficient Test Time Training
Rajat Modi · Yogesh Rawat
West Ballroom A-D #6304
December 11, 2024 at 7:40 PM
Rajat Modi presenting his work right now on getting Glom to work, poster #6304.
Asynchronous Perception Machine for Efficient Test Time Training
Rajat Modi · Yogesh Rawat
West Ballroom A-D #6304
Asynchronous Perception Machine for Efficient Test Time Training
Rajat Modi · Yogesh Rawat
West Ballroom A-D #6304