Tobias Weyand

Research Engineer @GoogleDeepMind working on video understanding.

[Tobias Weyand @0xtob]

@AljosaOsep @ylecun According to Schmidhuber, every ML paper is stolen from Schmidhuber.

[Lucas Beyer (bl16) @giffmana]

Can't believe we're getting this before GTA 6

[Tobias Weyand @0xtob]

@giffmana Yeah, agents really take away many headaches from Linux. Another awesome use case I recently discovered is letting them deal with tricky git issues like resolving rebase conflicts.

[Tobias Weyand @0xtob]

@giffmana I recently let Gemini guide me through setting up a raspberry pi as a time machine backup server which was a total breeze! How much longer until we just give LLMs root and let them deal with all our sysadmin stuff?

[Tobias Weyand @0xtob]

@ahmetius @SachitMenon Here's our video about the paper: https://t.co/nwmVaYcLkj

[Tobias Weyand @0xtob]

Attending #ICCV2025? Come chat with us about our Minerva dataset that tests if models can truly reason about videos! 🕵️‍♀️

@ahmetius and @SachitMenon will be presenting the dataset at Poster Session 5 tomorrow (Thurs, Oct 23) morning. Find them at poster #391.

[Tobias Weyand @0xtob]

We're excited to release Minerva 🕵️‍♀️, a benchmark to evaluate if AI can truly reason about videos, from spotting game-changing moments in sports 🏀 to understanding character motivations in short films 🍿. We provide the "why" behind the answers! Pointers below 👇

[Tobias Weyand @0xtob]

Our team is hiring! If you have experience in video understanding and/or generation, join us @GoogleDeepMind and help push the frontiers with Veo and Gemini!

[Mikhail Sirotenko @sirotenko_m]

We're hiring at @GoogleDeepMind! Looking for a talented Research Engineer to help build the future of Video generation and undrestanding (Veo and Gemini).

Apply here: https://t.co/hYCj2jgvgw

[Tobias Weyand @0xtob]

@giffmana Same goes for punting. My daughter actually once responded to a question with "Sorry, I'm just a language model"

[Tobias Weyand @0xtob]

Excited that our Minerva and Neptune datasets are both featured in the Gemini 2.5 tech report! Minerva is among the most challenging video benchmarks with a large gap between SotA (Gemini 2.5 Pro, 67.6%) and humans (92.5%).
https://t.co/mWROj5JXSz

[Antoine Yang @AntoineYang2]

The newly generally available Gemini 2.5 Flash and Pro are even better at video understanding than the versions we shared in the blog a month ago, see more details in the tech report 😀

[Boqing Gong @BoqingGo]

Excited! VideoPrism-Base/Large are publicly available now: https://t.co/g5BNiA5O05

Check it out if you need a versatile video encoder for video-language or video-native tasks. Feedback appreciated!

[Tobias Weyand @0xtob]

Gemini 2.5 Pro sets the state of the art on our newly released Minerva video reasoning benchmark by scoring 63.5%.

📜 Paper: https://t.co/nEWfr1SbqA
📊 Dataset: https://t.co/JengJVEgH6

[JB Alayrac @jalayrac]

A lot of work went to make Gemini 2.5 SOTA at video understanding, check out this 🧵 for more details!

Looking back at where we were a year ago, the progress really feels phenomenal!

So many things to unlock and enable from video 🎥 and we are only getting started!

[Tobias Weyand @0xtob]

Listen to the @agi_breakdown episode on Minerva here:
https://t.co/oabPUYfYvw

[Tobias Weyand @0xtob]

We're excited to release Minerva 🕵️‍♀️, a benchmark to evaluate if AI can truly reason about videos, from spotting game-changing moments in sports 🏀 to understanding character motivations in short films 🍿. We provide the "why" behind the answers! Pointers below 👇

[Tobias Weyand @0xtob]

The newly released Gemini 2.5 Pro (Preview 05/06) sets the state-of-the art on Minerva with 63.5% accuracy. Human accuracy is 92.5%.
https://t.co/qrDY5qqp2P

[Tobias Weyand @0xtob]

Excited to share Long-Video Masked Autoencoder (LVMAE) our team just published at @NeurIPSConf! We boost the context length of video models using an adaptive decoder and a dual-masking strategy and achieve SotA on several video benchmarks.

Paper: https://t.co/XeBME5RvFX

[Google AI @GoogleAI]

Training video understanding models on longer contexts is computationally intensive. To address this, we present a novel approach that reduces the computational load while also improving the quality of the learned representations. More at: https://t.co/56Vj3kOzOl

[Tobias Weyand @0xtob]

Thank you @JeffDean , very much appreciate the boost! This is really a team effort with my amazing colleagues @NagraniArsha, Mingda Zhang, @raminia, Rachel Hornung, @nitesh_ai, @under_fitting, Austin Meyers, @zhouxy2017, @BoqingGo, @CordeliaSchmid, @sirotenko_m, @ZhuZhu66595.

[Jeff Dean @JeffDean]

A nice new benchmark for long video understanding by Tobias Weyand @0xtob and others. This is likely to be one of the new frontiers of capabilities for large-scale multimodal models, and it's great to have a new benchmark to assess others in this area.

[Tobias Weyand @0xtob]

Excited that our work on Long video understanding is being featured by @GoogleAI !

[Google AI @GoogleAI]

Can #AI truly understand long videos? Tobias Weyand & the Google Research team are testing the limits w/ Neptune, an open-source benchmark for long video understanding. Dive into the details & see how AI tackles temporal reasoning, cause & effect, & more →https://t.co/jNkgEYkdFA

[Tobias Weyand @0xtob]

@ikostrikov

[Tobias Weyand @0xtob]

The other day I let my kids talk to Gemini live. Today my 3 year old asked my 6 year old: "Can you tell me a joke?" - 6 year old: "Sorry, I'm just a language model."