Next
Livestream will start soon!
Livestream has already ended.
Presentation has not been recorded yet!
  • title: Cones: Concept Neurons in Diffusion Models for Customized Generation
      0:00 / 0:00
      • Report Issue
      • Settings
      • Playlists
      • Bookmarks
      • Subtitles Off
      • Playback rate
      • Quality
      • Settings
      • Debug information
      • Server sl-yoda-v2-stream-001-alpha.b-cdn.net
      • Subtitles size Medium
      • Bookmarks
      • Server
      • sl-yoda-v2-stream-001-alpha.b-cdn.net
      • sl-yoda-v2-stream-001-beta.b-cdn.net
      • 1824830694.rsc.cdn77.org
      • 1979322955.rsc.cdn77.org
      • Subtitles
      • Off
      • English
      • Playback rate
      • Quality
      • Subtitles size
      • Large
      • Medium
      • Small
      • Mode
      • Video Slideshow
      • Audio Slideshow
      • Slideshow
      • Video
      My playlists
        Bookmarks
          00:00:00
            Cones: Concept Neurons in Diffusion Models for Customized Generation
            • Settings
            • Sync diff
            • Quality
            • Settings
            • Server
            • Quality
            • Server

            Cones: Concept Neurons in Diffusion Models for Customized Generation

            Jul 24, 2023

            Speakers

            ZL

            Zhiheng Liu

            Speaker · 0 followers

            RF

            Ruili Feng

            Speaker · 0 followers

            KZ

            Kai Zhu

            Speaker · 0 followers

            About

            Human brains respond to semantic features of presented stimuli with different neurons. It is then curious whether modern deep neural networks admit a similar behavior pattern. Specifically, this paper finds a small cluster of neurons in a diffusion model corresponding to a particular subject. We call those neurons the concept neurons. They can be identified by statistics of network gradients to a stimulation connected with the given subject. The concept neurons demonstrate magnetic properties in…

            Organizer

            I2
            I2

            ICML 2023

            Account · 655 followers

            Like the format? Trust SlidesLive to capture your next event!

            Professional recording and live streaming, delivered globally.

            Sharing

            Recommended Videos

            Presentations on similar topic, category or speaker

            Preference Proxies: Evaluating LLMs in capturing Human Preferences in Human-AI Tasks
            12:10

            Preference Proxies: Evaluating LLMs in capturing Human Preferences in Human-AI Tasks

            Mudit Verma, …

            I2
            I2
            ICML 2023 2 years ago

            Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%

            Quantifying the Variability Collapse of Neural Networks
            04:24

            Quantifying the Variability Collapse of Neural Networks

            Jing Xu, …

            I2
            I2
            ICML 2023 2 years ago

            Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%

            Organizers: Concluding Remarks
            01:40

            Organizers: Concluding Remarks

            Andreea Bobu

            I2
            I2
            ICML 2023 2 years ago

            Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%

            Interpreting Robustness Proofs of Deep Neural Networks
            14:31

            Interpreting Robustness Proofs of Deep Neural Networks

            Debangshu Banerjee, …

            I2
            I2
            ICML 2023 2 years ago

            Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%

            What do CNNs Learn in the First Layer and Why? A Linear Systems Perspective
            05:17

            What do CNNs Learn in the First Layer and Why? A Linear Systems Perspective

            Rhea Chowers, …

            I2
            I2
            ICML 2023 2 years ago

            Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%

            Federated Conformal Predictors for Distributed Uncertainty Quantification
            03:25

            Federated Conformal Predictors for Distributed Uncertainty Quantification

            Charles Lu, …

            I2
            I2
            ICML 2023 2 years ago

            Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%

            Interested in talks like this? Follow ICML 2023