Semisance
@semisance.bsky.social
I post daily research highlights from arXiv.com, and I gather curated AI and tech news on https://semisance.substack.com/
Reach at semisance@gmail.com
Reach at semisance@gmail.com
Dynamic Point Maps: A Versatile Representation for Dynamic 3D Reconstruction
arxiv.org/abs/2503.16318
arxiv.org/abs/2503.16318
March 21, 2025 at 6:54 AM
Dynamic Point Maps: A Versatile Representation for Dynamic 3D Reconstruction
arxiv.org/abs/2503.16318
arxiv.org/abs/2503.16318
Structured-Noise Masked Modeling for Video, Audio and Beyond
arxiv.org/abs/2503.16311
arxiv.org/abs/2503.16311
March 21, 2025 at 6:42 AM
Structured-Noise Masked Modeling for Video, Audio and Beyond
arxiv.org/abs/2503.16311
arxiv.org/abs/2503.16311
Jasmine: Harnessing Diffusion Prior for Self-supervised Depth Estimation
arxiv.org/abs/2503.15905
arxiv.org/abs/2503.15905
March 21, 2025 at 6:41 AM
Jasmine: Harnessing Diffusion Prior for Self-supervised Depth Estimation
arxiv.org/abs/2503.15905
arxiv.org/abs/2503.15905
SynCity: Training-Free Generation of 3D Worlds
arxiv.org/abs/2503.16420
Project page: research.paulengstler.com/syncity/
arxiv.org/abs/2503.16420
Project page: research.paulengstler.com/syncity/
March 21, 2025 at 6:40 AM
SynCity: Training-Free Generation of 3D Worlds
arxiv.org/abs/2503.16420
Project page: research.paulengstler.com/syncity/
arxiv.org/abs/2503.16420
Project page: research.paulengstler.com/syncity/
SV4D 2.0: Enhancing Spatio-Temporal Consistency in Multi-View Video Diffusion for High-Quality 4D Generation
arxiv.org/abs/2503.16396
arxiv.org/abs/2503.16396
March 21, 2025 at 6:35 AM
SV4D 2.0: Enhancing Spatio-Temporal Consistency in Multi-View Video Diffusion for High-Quality 4D Generation
arxiv.org/abs/2503.16396
arxiv.org/abs/2503.16396
Bridging Continuous and Discrete Tokens for Autoregressive Visual Generation
arxiv.org/abs/2503.16430
Project page: yuqingwang1029.github.io/TokenBridge/
arxiv.org/abs/2503.16430
Project page: yuqingwang1029.github.io/TokenBridge/
March 21, 2025 at 6:28 AM
Bridging Continuous and Discrete Tokens for Autoregressive Visual Generation
arxiv.org/abs/2503.16430
Project page: yuqingwang1029.github.io/TokenBridge/
arxiv.org/abs/2503.16430
Project page: yuqingwang1029.github.io/TokenBridge/
M3: 3D-Spatial MultiModal Memory
arxiv.org/abs/2503.16413
Project page: m3-spatial-memory.github.io
#ICLR2025 🎉
arxiv.org/abs/2503.16413
Project page: m3-spatial-memory.github.io
#ICLR2025 🎉
March 21, 2025 at 6:21 AM
M3: 3D-Spatial MultiModal Memory
arxiv.org/abs/2503.16413
Project page: m3-spatial-memory.github.io
#ICLR2025 🎉
arxiv.org/abs/2503.16413
Project page: m3-spatial-memory.github.io
#ICLR2025 🎉
Decompositional Neural Scene Reconstruction with Generative Diffusion Prior
arxiv.org/abs/2503.14830
Project page: dp-recon.github.io
#CVPR2025 🎉
arxiv.org/abs/2503.14830
Project page: dp-recon.github.io
#CVPR2025 🎉
March 20, 2025 at 8:11 AM
Decompositional Neural Scene Reconstruction with Generative Diffusion Prior
arxiv.org/abs/2503.14830
Project page: dp-recon.github.io
#CVPR2025 🎉
arxiv.org/abs/2503.14830
Project page: dp-recon.github.io
#CVPR2025 🎉
March 20, 2025 at 8:03 AM
1000 Layer Networks for Self-Supervised RL: Scaling Depth Can Enable New Goal-Reaching Capabilities
arxiv.org/abs/2503.14858
Project page: wang-kevin3290.github.io/scaling-crl/
arxiv.org/abs/2503.14858
Project page: wang-kevin3290.github.io/scaling-crl/
March 20, 2025 at 7:59 AM
1000 Layer Networks for Self-Supervised RL: Scaling Depth Can Enable New Goal-Reaching Capabilities
arxiv.org/abs/2503.14858
Project page: wang-kevin3290.github.io/scaling-crl/
arxiv.org/abs/2503.14858
Project page: wang-kevin3290.github.io/scaling-crl/
Temporal Regularization Makes Your Video Generator Stronger
arxiv.org/abs/2503.15417
Project page: haroldchen19.github.io/FluxFlow/
arxiv.org/abs/2503.15417
Project page: haroldchen19.github.io/FluxFlow/
March 20, 2025 at 7:57 AM
Temporal Regularization Makes Your Video Generator Stronger
arxiv.org/abs/2503.15417
Project page: haroldchen19.github.io/FluxFlow/
arxiv.org/abs/2503.15417
Project page: haroldchen19.github.io/FluxFlow/
Visual Persona: Foundation Model for Full-Body Human Customization
arxiv.org/abs/2503.15406
Project page: cvlab-kaist.github.io/Visual-Perso...
#CVPR2025 🎉
arxiv.org/abs/2503.15406
Project page: cvlab-kaist.github.io/Visual-Perso...
#CVPR2025 🎉
March 20, 2025 at 7:55 AM
Visual Persona: Foundation Model for Full-Body Human Customization
arxiv.org/abs/2503.15406
Project page: cvlab-kaist.github.io/Visual-Perso...
#CVPR2025 🎉
arxiv.org/abs/2503.15406
Project page: cvlab-kaist.github.io/Visual-Perso...
#CVPR2025 🎉
Object-Centric Pretraining via Target Encoder Bootstrapping
arxiv.org/abs/2503.15141
#ICLR2025 🎉
Code repository: github.com/djukicn/ocebo (coming soon)
arxiv.org/abs/2503.15141
#ICLR2025 🎉
Code repository: github.com/djukicn/ocebo (coming soon)
March 20, 2025 at 7:54 AM
Object-Centric Pretraining via Target Encoder Bootstrapping
arxiv.org/abs/2503.15141
#ICLR2025 🎉
Code repository: github.com/djukicn/ocebo (coming soon)
arxiv.org/abs/2503.15141
#ICLR2025 🎉
Code repository: github.com/djukicn/ocebo (coming soon)
TULIP: Towards Unified Language-Image Pretraining
arxiv.org/abs/2503.15485
Project page: tulip-berkeley.github.io
arxiv.org/abs/2503.15485
Project page: tulip-berkeley.github.io
March 20, 2025 at 7:53 AM
TULIP: Towards Unified Language-Image Pretraining
arxiv.org/abs/2503.15485
Project page: tulip-berkeley.github.io
arxiv.org/abs/2503.15485
Project page: tulip-berkeley.github.io
When the Future Becomes the Past: Taming Temporal Correspondence for Self-supervised Video Representation Learning
arxiv.org/abs/2503.15096
Project page: github.com/yafeng19/T-C...
#CVPR2025 🎉
arxiv.org/abs/2503.15096
Project page: github.com/yafeng19/T-C...
#CVPR2025 🎉
March 20, 2025 at 7:51 AM
When the Future Becomes the Past: Taming Temporal Correspondence for Self-supervised Video Representation Learning
arxiv.org/abs/2503.15096
Project page: github.com/yafeng19/T-C...
#CVPR2025 🎉
arxiv.org/abs/2503.15096
Project page: github.com/yafeng19/T-C...
#CVPR2025 🎉
March 19, 2025 at 7:42 AM
Stable Virtual Camera: Generative View Synthesis with Diffusion Models
arxiv.org/abs/2503.14489
Project page stable-virtual-camera.github.io
arxiv.org/abs/2503.14489
Project page stable-virtual-camera.github.io
March 19, 2025 at 7:38 AM
Stable Virtual Camera: Generative View Synthesis with Diffusion Models
arxiv.org/abs/2503.14489
Project page stable-virtual-camera.github.io
arxiv.org/abs/2503.14489
Project page stable-virtual-camera.github.io
March 19, 2025 at 7:37 AM
Bolt3D: Generating 3D Scenes in Seconds
arxiv.org/abs/2503.14445
Project page: szymanowiczs.github.io/bolt3d
arxiv.org/abs/2503.14445
Project page: szymanowiczs.github.io/bolt3d
March 19, 2025 at 7:35 AM
Bolt3D: Generating 3D Scenes in Seconds
arxiv.org/abs/2503.14445
Project page: szymanowiczs.github.io/bolt3d
arxiv.org/abs/2503.14445
Project page: szymanowiczs.github.io/bolt3d
MusicInfuser: Making Video Diffusion Listen and Dance
arxiv.org/abs/2503.14505
Project page: susunghong.github.io/MusicInfuser/
arxiv.org/abs/2503.14505
Project page: susunghong.github.io/MusicInfuser/
March 19, 2025 at 7:34 AM
MusicInfuser: Making Video Diffusion Listen and Dance
arxiv.org/abs/2503.14505
Project page: susunghong.github.io/MusicInfuser/
arxiv.org/abs/2503.14505
Project page: susunghong.github.io/MusicInfuser/
Deeply Supervised Flow-Based Generative Models
arxiv.org/abs/2503.14494
Project page: deepflow-project.github.io
arxiv.org/abs/2503.14494
Project page: deepflow-project.github.io
March 19, 2025 at 7:33 AM
Deeply Supervised Flow-Based Generative Models
arxiv.org/abs/2503.14494
Project page: deepflow-project.github.io
arxiv.org/abs/2503.14494
Project page: deepflow-project.github.io
DiffMoE: Dynamic Token Selection for Scalable Diffusion Transformers
arxiv.org/abs/2503.14487
Project page: shiml20.github.io/DiffMoE/
arxiv.org/abs/2503.14487
Project page: shiml20.github.io/DiffMoE/
March 19, 2025 at 7:32 AM
DiffMoE: Dynamic Token Selection for Scalable Diffusion Transformers
arxiv.org/abs/2503.14487
Project page: shiml20.github.io/DiffMoE/
arxiv.org/abs/2503.14487
Project page: shiml20.github.io/DiffMoE/
Seeing the Future, Perceiving the Future: A Unified Driving World Model for Future Generation and Perception
arxiv.org/abs/2503.13587
Project page: github.com/dk-liang/Uni...
arxiv.org/abs/2503.13587
Project page: github.com/dk-liang/Uni...
March 19, 2025 at 7:30 AM
Seeing the Future, Perceiving the Future: A Unified Driving World Model for Future Generation and Perception
arxiv.org/abs/2503.13587
Project page: github.com/dk-liang/Uni...
arxiv.org/abs/2503.13587
Project page: github.com/dk-liang/Uni...
DUNE: Distilling a Universal Encoder from Heterogeneous 2D and 3D Teachers
arxiv.org/abs/2503.14405
Project page: europe.naverlabs.com/research/pub...
#CVPR2025 🎉
arxiv.org/abs/2503.14405
Project page: europe.naverlabs.com/research/pub...
#CVPR2025 🎉
March 19, 2025 at 7:29 AM
DUNE: Distilling a Universal Encoder from Heterogeneous 2D and 3D Teachers
arxiv.org/abs/2503.14405
Project page: europe.naverlabs.com/research/pub...
#CVPR2025 🎉
arxiv.org/abs/2503.14405
Project page: europe.naverlabs.com/research/pub...
#CVPR2025 🎉
LeanVAE: An Ultra-Efficient Reconstruction VAE for Video Diffusion Models
arxiv.org/abs/2503.14325
Project page: github.com/westlake-rep...
arxiv.org/abs/2503.14325
Project page: github.com/westlake-rep...
March 19, 2025 at 7:28 AM
LeanVAE: An Ultra-Efficient Reconstruction VAE for Video Diffusion Models
arxiv.org/abs/2503.14325
Project page: github.com/westlake-rep...
arxiv.org/abs/2503.14325
Project page: github.com/westlake-rep...