Loading video...

Video Failed to Load

Go Home

Introducing MilliVid, our new method for long-context video generation! MilliVid creates videos that are consistent over long time spans, without using retrieval heuristics or 3D maps! (1/n)

vincesitzmann's profile picture

Vincent Sitzmann

19,447 subscribers

55,055 views • 25 days ago •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

📢Introducing 360Anything, our method for lifting any perspective image or video to gravity-aligned 360° panoramas without using any camera or 3D information. This enables consistent novel view synthesis and 3D scene reconstruction. Project page: 🧵
1:05

📢Introducing 360Anything, our method for lifting any perspective image or video to gravity-aligned 360° panoramas without using any camera or 3D information. This enables consistent novel view synthesis and 3D scene reconstruction. Project page: 🧵

Ziyi Wu

60,784 views • 5 months ago

Voyager Long-Range and World-Consistent Video Diffusion for Explorable 3D Scene Generation
0:30

Voyager Long-Range and World-Consistent Video Diffusion for Explorable 3D Scene Generation

AK

15,840 views • 1 year ago

Self-Forcing++ for minute-scale video generation ByteDance's new method generates high-quality videos up to 4 min 15 sec! It scales diffusion models without long-video teachers or retraining, preserving fidelity and consistency.
1:40

Self-Forcing++ for minute-scale video generation ByteDance's new method generates high-quality videos up to 4 min 15 sec! It scales diffusion models without long-video teachers or retraining, preserving fidelity and consistency.

DailyPapers

17,720 views • 9 months ago

Long Context Tuning for Video Generation
1:07

Long Context Tuning for Video Generation

AK

38,271 views • 1 year ago

This is a step forward for long-context video tuning, which has already unlocked impressive multi-shot video generation pipelines from . Generating minutes- or even hour-long videos without drifting or forgetting is not "coming soon" -- it is already here. 3/4
0:50

This is a step forward for long-context video tuning, which has already unlocked impressive multi-shot video generation pipelines from . Generating minutes- or even hour-long videos without drifting or forgetting is not "coming soon" -- it is already here. 3/4

Gordon Wetzstein

27,473 views • 10 months ago

What representation enables open-world robot manipulation from generated videos? Introducing Dream2Flow, our recent work that bridges video generation and robot control with 3D object flow. Stanford University #ICRA2026 1/N
1:08

What representation enables open-world robot manipulation from generated videos? Introducing Dream2Flow, our recent work that bridges video generation and robot control with 3D object flow. Stanford University #ICRA2026 1/N

Wenlong Huang

105,597 views • 3 months ago

BlockVid Block Diffusion for High-Quality and Consistent Minute-Long Video Generation
1:00

BlockVid Block Diffusion for High-Quality and Consistent Minute-Long Video Generation

AK

19,949 views • 7 months ago

🔥1-min Interactive Video Generation with Multimodal Control🔥 Towards *long-context world model*, #LongVie is an end-to-end autoregressive framework for controllable ultra-long video generation - Page: - Paper: . Thanks AK
2:12

🔥1-min Interactive Video Generation with Multimodal Control🔥 Towards *long-context world model*, #LongVie is an end-to-end autoregressive framework for controllable ultra-long video generation - Page: - Paper: . Thanks AK

Ziwei Liu

14,185 views • 11 months ago

Vision-language models perform diverse tasks via in-context learning. Time for robots to do the same! Introducing In-Context Robot Transformer (ICRT): a robot policy that learns new tasks by prompting with robot trajectories, without any fine-tuning. [1/N]
0:25

Vision-language models perform diverse tasks via in-context learning. Time for robots to do the same! Introducing In-Context Robot Transformer (ICRT): a robot policy that learns new tasks by prompting with robot trajectories, without any fine-tuning. [1/N]

Max Fu

40,435 views • 1 year ago

Introducing: the AI Georeferencer 🗺️ Our new QGIS add-on generates control points for raster maps automatically, using AI. Here's me georeferencing two maps in QGIS without ever manually adding a GCP:
5:57

Introducing: the AI Georeferencer 🗺️ Our new QGIS add-on generates control points for raster maps automatically, using AI. Here's me georeferencing two maps in QGIS without ever manually adding a GCP:

Brendan Ashworth

72,983 views • 1 year ago

Introducing “VOODOO 3D: VOlumetric pOrtrait Disentanglement fOr One-shot 3D head reenactment”. We present a real-time 3D aware one-shot head reenactment method that can generate consistent views from any angle MBZUAI ETH Zürich VinAI Pinscreen URL
1:15

Introducing “VOODOO 3D: VOlumetric pOrtrait Disentanglement fOr One-shot 3D head reenactment”. We present a real-time 3D aware one-shot head reenactment method that can generate consistent views from any angle MBZUAI ETH Zürich VinAI Pinscreen URL

Hao Li

16,030 views • 2 years ago

Gaussian Shell Maps are a new neural scene representation that connects fields and 3D Gaussians. This representation unlocks the full potential of 3D Gaussian splatting for generative AI applications, such as 3D avatar generation. 1/2
0:22

Gaussian Shell Maps are a new neural scene representation that connects fields and 3D Gaussians. This representation unlocks the full potential of 3D Gaussian splatting for generative AI applications, such as 3D avatar generation. 1/2

Gordon Wetzstein

52,480 views • 2 years ago

1.Stem cells reside in specialized microenvironments that precisely regulate their behavior. For this reason they are best studied in their in vivo context. A new paper from our lab describes a method for long-term imaging & quantitative analysis of hematopoiesis in vivo in flies
2:08

1.Stem cells reside in specialized microenvironments that precisely regulate their behavior. For this reason they are best studied in their in vivo context. A new paper from our lab describes a method for long-term imaging & quantitative analysis of hematopoiesis in vivo in flies

Tanentzapf Lab

27,031 views • 3 years ago

Stop watching videos, start interacting with worlds. Stoked to share CAT4D, our new method for turning videos into dynamic 3D scenes that you can move through in real-time!
0:36

Stop watching videos, start interacting with worlds. Stoked to share CAT4D, our new method for turning videos into dynamic 3D scenes that you can move through in real-time!

Ben Poole

45,947 views • 1 year ago

Robot AI brains, aka Vision-Language-Action models, cannot adapt to new tasks as easily as LLMs like Gemini, ChatGPT, or Grok. LLMs can adapt quickly with their in-context learning (ICL) capabilities. But can we inject ICL abilities into a pre-trained VLA like pi0? Yes! Introducing RICL (Retraining for In-Context Learning), our Conference on Robot Learning (CoRL) 2025 paper. Our RICL-pi0 model can adapt to unseen objects, novel motions, and new scenes with just ICL and RAG (retrieval-augmented generation). RICL-pi0 also boosts performance on the long-tail of tasks. A quick 1 minute video summary:
1:03

Robot AI brains, aka Vision-Language-Action models, cannot adapt to new tasks as easily as LLMs like Gemini, ChatGPT, or Grok. LLMs can adapt quickly with their in-context learning (ICL) capabilities. But can we inject ICL abilities into a pre-trained VLA like pi0? Yes! Introducing RICL (Retraining for In-Context Learning), our Conference on Robot Learning (CoRL) 2025 paper. Our RICL-pi0 model can adapt to unseen objects, novel motions, and new scenes with just ICL and RAG (retrieval-augmented generation). RICL-pi0 also boosts performance on the long-tail of tasks. A quick 1 minute video summary:

Kaustubh Sridhar

52,158 views • 10 months ago

We are thrilled to announce a major upgrade to our open-source 3D generation model, introducing two groundbreaking new versions: 3D 2.0 MV (Multi-View Generation) and 3D 2.0 Mini! 3D 2.0 MV : 3D 2.0Mini:
0:39

We are thrilled to announce a major upgrade to our open-source 3D generation model, introducing two groundbreaking new versions: 3D 2.0 MV (Multi-View Generation) and 3D 2.0 Mini! 3D 2.0 MV : 3D 2.0Mini:

Tencent HY

134,410 views • 1 year ago

Just for fun, here's what 32 simultaneous long-context generations with Qwen3 Next 80B looks like on an M3 Ultra. Using the new batch generation in mlx-lm. Context size for each is about 5k tokens:
0:41

Just for fun, here's what 32 simultaneous long-context generations with Qwen3 Next 80B looks like on an M3 Ultra. Using the new batch generation in mlx-lm. Context size for each is about 5k tokens:

Awni Hannun

50,272 views • 9 months ago

New #NVIDIA Paper We introduce Motive, a motion-centric, gradient-based data attribution method that traces which training videos help or hurt video generation. By isolating temporal dynamics from static appearance, Motive identifies which training videos shape motion in video generation. 🔗 1/10
1:15

New #NVIDIA Paper We introduce Motive, a motion-centric, gradient-based data attribution method that traces which training videos help or hurt video generation. By isolating temporal dynamics from static appearance, Motive identifies which training videos shape motion in video generation. 🔗 1/10

Xindi Wu ✈️ ICML 2026

111,463 views • 5 months ago

Radial Attention O(nlog n) Sparse Attention with Energy Decay for Long Video Generation
1:03

Radial Attention O(nlog n) Sparse Attention with Energy Decay for Long Video Generation

AK

36,271 views • 1 year ago