首页

投稿

Dual Diffusion Implicit Bridges for Image-to-Image Translation

739

0

2026-03-09 17:33:14

https://www.youtube.com/watch?v=zgE8nUYU-ng @inproceedings{suDualDiffusionImplicit2023a, title = {Dual {{Diffusion Implicit Bridges}} for {{Image-to-Image Translation}}}, booktitle = {The {{Eleventh International Conference}} on {{Learning Representations}}}, author = {Su, Xuan and Song, Jiaming and Meng, Chenlin and Ermon, Stefano}, year = 2023, urldate = {2026-02-08} }

Sa神带你学AI 发消息

Junyang Lin (Alibaba)

32:59

Ariel Data Challenge 2024

Phillip Isola (MIT)

27:03

Bill Freeman (MIT)

36:01

Varun Jampani (Stability AI)

23:06

Arash Vahdat (NVIDIA)

29:14

Ricky T. Q. Chen (FAIR)

27:34

Liang-Chieh Chen (Amazon FAR)

19:43

Jiaming Song (Luma AI)

Jiatao Gu (Apple/UPenn)

Robin Rombach (Black Forest Labs)

Kaiming He (MIT) Towards End-to-End Generative Modeling

Shunyu Yao - The Second Half of AI

38:46

Stefano Ermon - The Next Frontier in Reliable AI

43:27

Stefano Ermon - Machine Learning for Remote Sensing

42:34

Earth Embedding and Geospatial Foundation Models

15:31

Flow Matching for Generative Modeling

The Platonic Representation Hypothesis

01:09:11

Language Models as World Models

01:13:23

Ilya Sutskever's Talk

16:41

Direct Preference Optimization

14:30

Score Entropy Discrete Diffusion models

15:59

Weak-to-Strong Generalizarion

16:09

DoRA: Weight-Decomposed Low-Rank Adaptation

15:20

Foundation Models for Vision, Language and Robotics [CVPR 2024 Workshop]

36:45

Denoising Diffusion Models : A Generative Learning Big Bang [CVPR 2023 Tutorial]

03:04:32

Denoising Diffusion-based Generative Modeling [CVPR 2022 Tutorial]

03:46:15

Ilya Sutskever, U of T honorary degree recipient, June 6, 2025

10:06

NVIDIA - EDM

52:46

Diffusion and Score-Based Generative Models, Yang Song, Stanford University

01:32:01

Ilya Sutskever | Natural language realizes the whole process of conscious AI

28:53

Your Next-Token Prediction and Transformers Are Biased for Long-Context Modeling

01:22:50

GeoChat： a grounded large vision-language model for remote sensing

32:42

VideoGPT+： integrating dual encoding for enhanced video understanding

32:53

【ICLRW'2025】Frontiers in Probabilistic Inference: learning meets Sampling

【ICLRW'2025】Neural Network Weights as a New Data Modality

【ICML 2025 Turorial】Flowing Through Continuous-Time Generative Models

【ICML 2025 Workshop】DataWorld: Unifying data curation frameworks across domains

【ICML'2025 Test of Time Award】Batch Normalization

38:39

【CVPRW 2025】Scalable Generative Models in Computer Vision (Saining Xie)

53:30

【CVPRW 2025】Efficient Repurposing T2I Representation (Bjorn Ommer)

34:26

【CVPRW 2025】Recent Advances in Vision Foundation Models (Zhengyuan Yang)

54:00

【CVPRW 2025】Power-efficient neural networks using low-precision data types

【CVPR Tutorial 2025】See. Think. Act. (Linjie Li)

37:21

【CVPR Tutorial 2025】Towards Multimodal AI Agent (Jianwei Yan)

56:08

【CVPRW 2025】XAI4CV (Junfeng He)

30:07

【双语】Diffusion Schrödinger Bridge (Valentin De Bortoli)

Future Science Prize 2025 - Jun Zhu

26:04

Future Science Prize 2025 - Saining Xie

23:39

Future Science Prize 2025 - Jiajun Wu

26:11

Entropic optimal transport and Gromov-Wasserstein alignment - Kengo Kato

51:41

Optimal Transport for Statistics and Machine Learning - Philippe Rigollet

58:08

【双语】Geoffrey Hinton, Nobel Prize in Physics

31:54

【ICLRW 2025】World Models

【ICMLW 2025】World Models

【Rich Sutton】The Oak Architecture: A Vision of SuperIntelligence from Experience

【Kaiming He】Faster R-CNN (NeurIPS 2025 Test of Time Award)

【NeurIPS'25 Tutorial】Autoregressive Models Beyond Language

02:42:37

【NeurIPS'25 Workshop】What Makes a Good Video

37:03

【NeurIPS'25 Workshop】What Makes a Good Video (Ming-Yu Liu)

39:55

【NeurIPS'25 Workshop】What Makes a Good Video (Dima Damen)

35:41

【NeurIPS'25 Workshop】What Makes a Good Video (Junjia Wu)

34:08

【NeurIPS'25】Why Diffusion Models Don't Memorize

24:51

【NeurIPS'25】Gated Attention for Large Language Models

21:38

【NeurIPS'25】Superposition Yields Robust Neural Scaling

19:24

【NeurIPS'25】Envisioning Beyond the Pixels

15:01

【NeurIPS'25】Memory Mosaics at scale

20:25

【NeurIPS'25】Generalized Gradient Norm Clipping & Non-Euclidean Smoothness

15:32

【NeurIPS'25】Exploring Diffusion Transformer Designs via Grafting

19:34

【NeurIPS'25】ImageNet-trained CNNs are not biased towards texture

21:31

【NeurIPS'25】Adjoint Schrödinger Bridge Sampler

19:23

【NeurIPS'25 Workshop】World Models

【CVPRW 2025】Scalable Generative Models in Computer Vision (Arash Vahdat)

【CVPRW 2025】Uncertainty Quantification for Computer Vision (Arash Vahdat)

42:30

【NeurIPS'25】Oral 1C Theory 1

57:10

【ICLR'25】LLM-SR: Scientific Equation Discovery via Programming with LLLMs

16:29

【ICLR'25】Block Diffusion: Interpolating Between Autoregressive and Diffusion LLM

13:06

【ICLR'25】Tranfusion

14:57

【ICLR'25】Scaling Laws for Precision

11:04

【ICLR'25】Simplifying, Stabilizing and Scaling Continuous-time Consistency Models

14:02

【ICLR'25】SAM 2: Segment Anything in Images and Videos

15:39

【NeurIPS'25 Workshop】What Makes a Good Video (Hao Zhang)

38:45

【NeurIPS'25】Perception Encoder

13:50

【NeurIPS】Oral 2E Theory 2

59:12

【NeurIPS'25】Oral 3E Theory 3

58:27

【NeurIPS'25】Oral Theory 4

59:04

【TMLR'25】 Is There a Better Source Distribution than Gaussian?

10:19

【ICCV'25】FlowEdit (best student paper)

14:21

【ICCV'25】Scaling Laws for Native Multimodal Models

14:17

【ICCV'25】Diffusion Image Prior

15:41

【ICCV'25】CorrCLIP

13:15

【CVPRW'25】From Multimodal Generative Models to Dynamic World Modeling (Ziwei Liu

23:46

【CVPRW'25】Accelerating Inference in Diffusion Models (Stefano Ermon)

25:50

【CVPRW'25】Scale Efficient Video Generation and Tokenization (Ishan Misra)

21:25

【CVPRW'25】Distilling Diffusion Models into Conditional GANs (Jun-Yan Zhu)

20:22

【CVPRW'25】Cost-Effective Training of Video Generation Foundation Model (Lu Jiang

21:10

【双语】Generative Modeling via Drifting | MingYang Deng

59:22

Dual Diffusion Implicit Bridges for Image-to-Image Translation

20:16

Likelihood Training of Schrödinger Bridge Using Forward-Backward SDEs Theory

01:07:36

How to build a consistency model: Learning flow maps via self-distillation

01:15:47

Stochastic Interpolants: A Unifying Framework for Flows and Diffusions

01:39:59

Meta Flow Maps enable scalable reward alignment | Peter Potaptchik

01:03:29

【ICLR'26】From Physics to AI to Materials; A Journey from Foundations to Impact

58:07

【ICLR'26】RealUID

10:30

【ICLR'26】LLMs Get Lost In Multi-Turn Conversation

11:06

【ICLR'26】Energy-Based Transformers are Scalable Learners and Thinkers

09:25

【ICLR'26】AnyUp: Universal Feature Upsampling

09:40

【ICLR'26】Latent Speech-Text Transformer

09:33

顶部