正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

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)

Vincent Sitzmann

19,456 subscribers

55,220 次观看 • 28 天前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 条评论

暂无评论

原始帖子的评论将显示在这里

相关视频

📢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: 🧵

📢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

62,310 次观看 • 5 个月前

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

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

AK

15,840 次观看 • 1 年前

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.

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 次观看 • 9 个月前

Long Context Tuning for Video Generation

Long Context Tuning for Video Generation

AK

38,271 次观看 • 1 年前

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

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 次观看 • 10 个月前

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

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 次观看 • 3 个月前

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

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

AK

19,949 次观看 • 7 个月前

🔥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

🔥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 次观看 • 11 个月前

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]

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

40,446 次观看 • 1 年前

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:

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 次观看 • 1 年前

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

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 次观看 • 2 年前

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 次观看 • 2 年前

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

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 次观看 • 3 年前

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!

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 次观看 • 1 年前

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:

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 次观看 • 10 个月前

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:

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 次观看 • 1 年前

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:

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 次观看 • 9 个月前

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

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 次观看 • 5 个月前

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

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

AK

36,271 次观看 • 1 年前