Thomas Kipf
@tkipf.bsky.social
Research at Google DeepMind. Ex-Physicist. Controllable World Simulators (GNNs, Structured World Models, Neural Assets). TLM Veo Capabilities (Ingredients & more).
📍 San Francisco, CA
📍 San Francisco, CA
Two life updates:
1) About a year ago I decided to join the Veo team to work on capabilities. It’s been a fun ride! Excited for what’s still to come.
2) I've been busy caring for a newborn the past couple of days 🥰 Excited for the incredible world he will grow up in. Veo's impression below:
1) About a year ago I decided to join the Veo team to work on capabilities. It’s been a fun ride! Excited for what’s still to come.
2) I've been busy caring for a newborn the past couple of days 🥰 Excited for the incredible world he will grow up in. Veo's impression below:
May 27, 2025 at 8:04 PM
Two life updates:
1) About a year ago I decided to join the Veo team to work on capabilities. It’s been a fun ride! Excited for what’s still to come.
2) I've been busy caring for a newborn the past couple of days 🥰 Excited for the incredible world he will grow up in. Veo's impression below:
1) About a year ago I decided to join the Veo team to work on capabilities. It’s been a fun ride! Excited for what’s still to come.
2) I've been busy caring for a newborn the past couple of days 🥰 Excited for the incredible world he will grow up in. Veo's impression below:
I gave a talk on Compositional World Models at NeurIPS last week 🌐
The recording is now online: neurips.cc/virtual/2024... (for registered attendees; starts at 6:06:00)
Workshop: compositional-learning.github.io
The recording is now online: neurips.cc/virtual/2024... (for registered attendees; starts at 6:06:00)
Workshop: compositional-learning.github.io
December 19, 2024 at 1:57 AM
I gave a talk on Compositional World Models at NeurIPS last week 🌐
The recording is now online: neurips.cc/virtual/2024... (for registered attendees; starts at 6:06:00)
Workshop: compositional-learning.github.io
The recording is now online: neurips.cc/virtual/2024... (for registered attendees; starts at 6:06:00)
Workshop: compositional-learning.github.io
Check out the paper & website for emergent scene tracking examples:
📜https://arxiv.org/abs/2411.05927
🌐https://moog-paper.github.io
We can visualize token attention to see what part of the scene they take responsibility for – we find that they capture/track the 3D content of the scene.
📜https://arxiv.org/abs/2411.05927
🌐https://moog-paper.github.io
We can visualize token attention to see what part of the scene they take responsibility for – we find that they capture/track the 3D content of the scene.
November 15, 2024 at 6:09 AM
Check out the paper & website for emergent scene tracking examples:
📜https://arxiv.org/abs/2411.05927
🌐https://moog-paper.github.io
We can visualize token attention to see what part of the scene they take responsibility for – we find that they capture/track the 3D content of the scene.
📜https://arxiv.org/abs/2411.05927
🌐https://moog-paper.github.io
We can visualize token attention to see what part of the scene they take responsibility for – we find that they capture/track the 3D content of the scene.
The world doesn’t live on a pixel grid and neither should vision models!
Excited to share Moving off-the-Grid (MooG): a video model w/o grid-based representations. MooG learns detached “off-the-grid tokens” that bind to (and track) scene elements as camera & content move.
🧵
Excited to share Moving off-the-Grid (MooG): a video model w/o grid-based representations. MooG learns detached “off-the-grid tokens” that bind to (and track) scene elements as camera & content move.
🧵
November 15, 2024 at 6:09 AM
The world doesn’t live on a pixel grid and neither should vision models!
Excited to share Moving off-the-Grid (MooG): a video model w/o grid-based representations. MooG learns detached “off-the-grid tokens” that bind to (and track) scene elements as camera & content move.
🧵
Excited to share Moving off-the-Grid (MooG): a video model w/o grid-based representations. MooG learns detached “off-the-grid tokens” that bind to (and track) scene elements as camera & content move.
🧵