Michael C. Mozer @mc_mozer

Research Scientist, Google Brain now DeepMind where cognitive science and machine learning meet cs.colorado.edu/~mozer San Francisco, CA Joined January 2022

Tweets

14
Followers

682
Following

64
Likes

11

Effie Li @_EffieLi_

6 days ago

🌟To appear in the MechInterp Workshop @ #NeurIPS2025 🌟 Paper: arxiv.org/abs/2509.04466 How do language models (LMs) form representation of new tasks, during in-context learning? We study different types of task representations, and find that they evolve in distinct ways. 🧵1/7

1 15 104 16K 53

Download Image

Shoaib Ahmed Siddiqui @ShoaibASiddiqui

4 months ago

@adrian_weller @DavidSKrueger @gkdziugaite @mc_mozer @Eleni30fillou [📜9/9] Check out our paper for more details. Paper: arxiv.org/abs/2505.22310 Code: github.com/shoaibahmed/vi…

0 1 6 333 0

Shoaib Ahmed Siddiqui @ShoaibASiddiqui

4 months ago

[📜1/9] Does machine unlearning truly erase data influence? Our new paper reveals a critical insight: 'forgotten' information often isn't gone—it's merely dormant, and easily recovered by fine-tuning on just the retain set.

2 11 51 6K 24

Download Image

Archit Karandikar @KarchitK

10 months ago

We are announcing the launch of Airial Travel’s open-to-all beta version for desktop today. Airial is your personal travel agent with AI superpowers which makes planning and booking trips as easy as dreaming them up. airial.travel Me and Sanjeev co-founded Airial…

9 12 45 6K 7

Download Video

Anand Gopalakrishnan @agopal42

11 months ago

Excited to present "Recurrent Complex-Weighted Autoencoders for Unsupervised Object Discovery" at #NeurIPS2024! TL;DR: Our model, SynCx, greatly simplifies the inductive biases and training procedures of current state-of-the-art synchrony models. Thread 👇 1/x.

2 41 164 19K 86

Download Image

Michael Lepori @Michael_Lepori

12 months ago

The ability to properly contextualize is a core competency of LLMs, yet even the best models sometimes struggle. In a new preprint, we use #MechanisticInterpretability techniques to propose an explanation for contextualization errors: the LLM Race Conditions Hypothesis. [1/9]

5 14 101 15K 56

Download Image

Mengye Ren @mengyer

2 years ago

🔍 New LLM Research 🔍 Conventional wisdom says that deep neural networks suffer from catastrophic forgetting as we train them on a sequence of data points with distribution shifts. But conventions are meant to be challenged! In our recent paper led by @YanlaiYang, we discovered…

3 40 218 28K 124

Download Image

Gamaleldin Elsayed @gamaleldinfe

2 years ago

Nature Comms paper: Subtle adversarial image manipulations influence both human and machine perception! We show that adversarial attacks against computer vision models also transfer (weakly) to humans, even when the attack magnitude is small. nature.com/articles/s4146…

12 89 386 84K 143

Download Gif

Dumitru Erhan @doomie

3 years ago

1/ Today we are excited to introduce Phenaki: phenaki.github.io, short-link-to-paper, a model for generating videos from text, with prompts that can change over time, and that is able to generate videos that can be as long as multiple minutes!

36 395 2K 0 413

Download Gif

Sundar Pichai @sundarpichai

3 years ago

Two important breakthroughs from @GoogleAI this week - Imagen Video, a new text-conditioned video diffusion model that generates 1280x768 24fps HD video. And Phenaki, a model which generates long coherent videos for a sequence of text prompts. imagen.research.google/video/

56 283 2K 0 136

Download Video

Thomas Kipf @tkipf

3 years ago

We are excited to make the jump to complex real-world data with this class of models — and about the potential that slot-based models have for reducing the need for detailed human supervision when learning about the physical world. 6/7

1 1 6 0 0

Download Image

Thomas Kipf @tkipf

3 years ago

Excited to share our work on self-supervised video object representation learning: We introduce SAVi++, a slot-based video model that — for the first time — scales to Waymo Open driving scenes w/o direct supervision. 🖥️ slot-attention-video.github.io/savi++ 📜 arxiv.org/abs/2206.07764 1/7

3 33 174 0 37

Download Video

Michael C. Mozer @mc_mozer

4 years ago

Overcoming temptation: Incentive design for intertemporal choice arxiv.org/abs/2203.05782 We use AI models to help individuals adhere to long-term goals (e.g., retirement savings, weight loss) and avoid giving in to temptation.