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。

LIFT Layout-In-Future Video Generation under Large Viewpoint Change via On-Policy Self-Distillation paper:

AK

532,930 subscribers

17,977 次观看 • 22 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

Looking Ahead Modeling Future Evolution in Autoregressive Video Generation paper:

Looking Ahead Modeling Future Evolution in Autoregressive Video Generation paper:

AK

19,481 次观看 • 9 天前

AnyFlow Any-Step Video Diffusion Model with On-Policy Flow Map Distillation

AnyFlow Any-Step Video Diffusion Model with On-Policy Flow Map Distillation

AK

14,152 次观看 • 5 个月前

Video Analysis and Generation via a Semantic Progress Function paper:

Video Analysis and Generation via a Semantic Progress Function paper:

AK

34,542 次观看 • 6 个月前

📢 Lyra: Generative 3D Scene Reconstruction via Video Diffusion Model Self-Distillation Got only one or a few images and wondering if recovering the 3D environment is a reconstruction or generation problem? Why not do it with a generative reconstruction model! We show that a camera-conditioned video diffusion model can be transformed into a generative reconstruction model that directly outputs a high-quality 3D Gaussian Splatting representation through self-distillation, without requiring real-world training data. Check out our results in the video (wait for dynamic scenes in the second half!) : Project Page: Code and Models: Paper:

📢 Lyra: Generative 3D Scene Reconstruction via Video Diffusion Model Self-Distillation Got only one or a few images and wondering if recovering the 3D environment is a reconstruction or generation problem? Why not do it with a generative reconstruction model! We show that a camera-conditioned video diffusion model can be transformed into a generative reconstruction model that directly outputs a high-quality 3D Gaussian Splatting representation through self-distillation, without requiring real-world training data. Check out our results in the video (wait for dynamic scenes in the second half!) : Project Page: Code and Models: Paper:

Sherwin Bahmani

66,946 次观看 • 1 年前

Most multi-view reconstruction models need full supervision. We show they can self-improve without any ground truth labels. Introducing SelfEvo: Self-Improving 4D Perception via Self-Distillation. Up to +36.5% in video depth, +20.1% in camera estimation, zero annotation.

Most multi-view reconstruction models need full supervision. We show they can self-improve without any ground truth labels. Introducing SelfEvo: Self-Improving 4D Perception via Self-Distillation. Up to +36.5% in video depth, +20.1% in camera estimation, zero annotation.

Qianqian Wang

27,348 次观看 • 6 个月前

Tencent ARC Lab releases FlexiAct on Hugging Face Transfers actions from a reference video to an arbitrary target image! Allows for variations in layout, viewpoint, and skeletal structure

Tencent ARC Lab releases FlexiAct on Hugging Face Transfers actions from a reference video to an arbitrary target image! Allows for variations in layout, viewpoint, and skeletal structure

DailyPapers

10,792 次观看 • 1 年前

From Failures to Learnable Worlds Policy-Conditioned Environment Generation for Navigation Agents paper:

From Failures to Learnable Worlds Policy-Conditioned Environment Generation for Navigation Agents paper:

AK

17,068 次观看 • 16 天前

Distillation is the future.

Distillation is the future.

Matt Mireles

24,695 次观看 • 4 个月前

I had an awesome time interviewing idan shenfeld and Jonas Hübotter from MIT and ETH Zurich about self-distillation. this very promising post-training paradigm where the model acts as its own teacher by conditioning on environment feedback or demonstrations. we cover the SDPO algo for reinforcement learning with rich feedback and SDFT for continual learning without forgetting along with many applications. we dig into how it works, why it's simpler and faster than GRPO, and where this is already showing up in production systems. table of content: 0:00 - what is self distillation 2:50 - idan (MIT) and jonas (ETH Zurich) introduction and motivation 18:40 - different perspective of on-policy self-distillation (presentation) 36:00 - metacognition and specificity in self-distillation 37:24 - very long hard task and self-distillation 42:00 - continual learning with self-distillation (presentation) 1:16:50 - what is next in this research direction? 1:20:00 - is there any experience with subjective feedbacks? 1:22:50 - quality vs number of feedbacks? 1:26:40 - what setting would self-distillation struggle vs GRPO? the slides were super crisp really cool of them to share! enjoy my guys 🌹

I had an awesome time interviewing idan shenfeld and Jonas Hübotter from MIT and ETH Zurich about self-distillation. this very promising post-training paradigm where the model acts as its own teacher by conditioning on environment feedback or demonstrations. we cover the SDPO algo for reinforcement learning with rich feedback and SDFT for continual learning without forgetting along with many applications. we dig into how it works, why it's simpler and faster than GRPO, and where this is already showing up in production systems. table of content: 0:00 - what is self distillation 2:50 - idan (MIT) and jonas (ETH Zurich) introduction and motivation 18:40 - different perspective of on-policy self-distillation (presentation) 36:00 - metacognition and specificity in self-distillation 37:24 - very long hard task and self-distillation 42:00 - continual learning with self-distillation (presentation) 1:16:50 - what is next in this research direction? 1:20:00 - is there any experience with subjective feedbacks? 1:22:50 - quality vs number of feedbacks? 1:26:40 - what setting would self-distillation struggle vs GRPO? the slides were super crisp really cool of them to share! enjoy my guys 🌹

Yacine Mahdid

13,119 次观看 • 6 个月前

Claude distillation has been a big topic this week while I am (coincidentally) writing Chapter 8 on model distillation. In that context, I shared some utilities to generate distillation data from all sorts of open-weight models via OpenRouter and Ollama:

Claude distillation has been a big topic this week while I am (coincidentally) writing Chapter 8 on model distillation. In that context, I shared some utilities to generate distillation data from all sorts of open-weight models via OpenRouter and Ollama:

Sebastian Raschka

63,156 次观看 • 8 个月前

New lecture for the book! Nominally about synthetic data, but mostly is a walk through of the distillation literature from the Hinton 2015 paper to multi-teach on-policy distillation of today! At 7.4 hours of video in my post-training brain dump and counting :) It was fun to stare at the math long enough and talk through the 3-4 core changes that needed to be made to the original formulation to have on-policy distillation be ready for the mainstream like it is today (and in RL frameworks). Otherwise, I include a bit of a history lesson for how synthetic data generally slowly took over all post-training data research (it wasn't always the case)! Then I do some 101 review on constitutional AI, rubrics, and other popular methods. 00:00 The emergence of synthetic data 10:50 Background on teacher-student knowledge-distillation 24:47: On-policy distillation (OPD, MOPD, and OPSD) 37:11 Constitutional AI & AI Feedback 45:50 Rubrics as rewards & conclusions Ofc, watch on YouTube etc.

New lecture for the book! Nominally about synthetic data, but mostly is a walk through of the distillation literature from the Hinton 2015 paper to multi-teach on-policy distillation of today! At 7.4 hours of video in my post-training brain dump and counting :) It was fun to stare at the math long enough and talk through the 3-4 core changes that needed to be made to the original formulation to have on-policy distillation be ready for the mainstream like it is today (and in RL frameworks). Otherwise, I include a bit of a history lesson for how synthetic data generally slowly took over all post-training data research (it wasn't always the case)! Then I do some 101 review on constitutional AI, rubrics, and other popular methods. 00:00 The emergence of synthetic data 10:50 Background on teacher-student knowledge-distillation 24:47: On-policy distillation (OPD, MOPD, and OPSD) 37:11 Constitutional AI & AI Feedback 45:50 Rubrics as rewards & conclusions Ofc, watch on YouTube etc.

Nathan Lambert

93,485 次观看 • 4 个月前

Modality Forcing - turns FLUX.2.klein into 3D-aware models. - joint RGB-D, I2D, and D2I synthesis in one model - pixel-space depth tokenization - preserves T2I quality via self-distillation

Modality Forcing - turns FLUX.2.klein into 3D-aware models. - joint RGB-D, I2D, and D2I synthesis in one model - pixel-space depth tokenization - preserves T2I quality via self-distillation

Wildminder

13,347 次观看 • 4 个月前

The best leaders always come back to lift up the next generation 👏 (via Purdue Football)

The best leaders always come back to lift up the next generation 👏 (via Purdue Football)

NFL

581,382 次观看 • 2 个月前

Helios Real Real-Time Long Video Generation Model paper:

Helios Real Real-Time Long Video Generation Model paper:

AK

25,951 次观看 • 8 个月前

Mode Seeking meets Mean Seeking for Fast Long Video Generation paper:

Mode Seeking meets Mean Seeking for Fast Long Video Generation paper:

AK

20,433 次观看 • 8 个月前