Yossi Gandelsman

yossig's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted a collection 3 days ago

DINOv3

Collection

DINOv3: foundation models producing excellent dense features, outperforming SotA w/o fine-tuning - https://arxiv.org/abs/2508.10104 • 13 items • Updated Aug 21, 2025 • 473

authored a paper about 2 months ago

In-Context Representation Hijacking

Paper • 2512.03771 • Published Dec 3, 2025 • 4

authored a paper about 1 year ago

An Empirical Study of Autoregressive Pre-training from Videos

Paper • 2501.05453 • Published Jan 9, 2025 • 41

commented 2 papers over 1 year ago

Learning Video Representations without Natural Videos

Paper • 2410.24213 • Published Oct 31, 2024 • 16 •

2

Interpreting and Editing Vision-Language Representations to Mitigate Hallucinations

Paper • 2410.02762 • Published Oct 3, 2024 • 9 •

2

upvoted a paper over 1 year ago

Interpreting and Editing Vision-Language Representations to Mitigate Hallucinations

Paper • 2410.02762 • Published Oct 3, 2024 • 9

authored a paper over 1 year ago

Interpreting the Weight Space of Customized Diffusion Models

Paper • 2406.09413 • Published Jun 13, 2024 • 20

upvoted 2 papers over 1 year ago

Interpreting the Weight Space of Customized Diffusion Models

Paper • 2406.09413 • Published Jun 13, 2024 • 20

Interpreting the Second-Order Effects of Neurons in CLIP

Paper • 2406.04341 • Published Jun 6, 2024 • 2

authored a paper over 1 year ago

Interpreting CLIP's Image Representation via Text-Based Decomposition

Paper • 2310.05916 • Published Oct 9, 2023 • 2

authored 2 papers about 2 years ago

Synthesizing Moving People with 3D Control

Paper • 2401.10889 • Published Jan 19, 2024 • 12

Idempotent Generative Network

Paper • 2311.01462 • Published Nov 2, 2023 • 25

authored a paper over 2 years ago

Test-Time Training on Video Streams

Paper • 2307.05014 • Published Jul 11, 2023 • 7