Subhansh Malviya's picture

Subhansh Malviya

Subh775

·

AI & ML interests

Applied Computer Vision Researcher | Vision + Perception + Interpretation | Perception Encoder 🗿

Recent Activity

liked a model about 5 hours ago

iisc-aim/UVH-26

liked a Space about 6 hours ago

merve/EdgeTAM

liked a dataset 10 days ago

iisc-aim/UVH-26

View all activity

Organizations

upvoted a paper 20 days ago

Simple Open-Vocabulary Object Detection with Vision Transformers

Paper • 2205.06230 • Published May 12, 2022 • 3

upvoted a collection 21 days ago

timm Backbones

Pre-trained feature extraction backbones available in timm. • 18 items • Updated Sep 19 • 10

upvoted a collection 23 days ago

DINOv3

DINOv3: foundation models producing excellent dense features, outperforming SotA w/o fine-tuning - https://arxiv.org/abs/2508.10104 • 13 items • Updated Aug 21 • 379

upvoted a paper about 1 month ago

RF-DETR Object Detection vs YOLOv12 : A Study of Transformer-based and CNN-based Architectures for Single-Class and Multi-Class Greenfruit Detection in Complex Orchard Environments Under Label Ambiguity

Paper • 2504.13099 • Published Apr 17 • 8

upvoted 2 papers 3 months ago

Has GPT-5 Achieved Spatial Intelligence? An Empirical Study

Paper • 2508.13142 • Published Aug 18 • 34

MedSAM2: Segment Anything in 3D Medical Images and Videos

Paper • 2504.03600 • Published Apr 4 • 9

upvoted 2 papers 4 months ago

WebSailor: Navigating Super-human Reasoning for Web Agent

Paper • 2507.02592 • Published Jul 3 • 121

Depth Anything at Any Condition

Paper • 2507.01634 • Published Jul 2 • 52

upvoted an article 5 months ago

Article

(LoRA) Fine-Tuning FLUX.1-dev on Consumer Hardware

Jun 19

•

92

upvoted a collection 7 months ago

FLUX.1 ONNX

ONNX exports of our FLUX.1 models. • 5 items • Updated Jun 26 • 40

upvoted a collection about 1 year ago

Themes

5 items • Updated Sep 10, 2024 • 2