DEV Community

#visionmultimodal

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
DreamTac: 703 Franka Trajectories With Gel Fingertip Video for Robot Learning

DreamTac: 703 Franka Trajectories With Gel Fingertip Video for Robot Learning

Comments
5 min read
2026-Humanoid-IKEA-Assembly-Challenge: 35 Motors, Seven Cameras, in FiftyOne

2026-Humanoid-IKEA-Assembly-Challenge: 35 Motors, Seven Cameras, in FiftyOne

Comments
4 min read
Why Squeaky-Clean Datasets Break Production Vision Models

Why Squeaky-Clean Datasets Break Production Vision Models

Comments
4 min read
HapTile: 1,699 UR5e Episodes With Tactile Video and Haptic Levels, in FiftyOne

HapTile: 1,699 UR5e Episodes With Tactile Video and Haptic Levels, in FiftyOne

Comments
5 min read
Human Preference Tuning for Small VLMs: SmolVLM2 + DPO in Transformers 5.12.1

Human Preference Tuning for Small VLMs: SmolVLM2 + DPO in Transformers 5.12.1

Comments
10 min read
Train a Modern VLM on One GPU: Qwen3-VL with Unsloth and Transformers 5.12.1

Train a Modern VLM on One GPU: Qwen3-VL with Unsloth and Transformers 5.12.1

1
Comments
10 min read
Detect What You Can Name: PaliGemma 2 Object Detection with Transformers

Detect What You Can Name: PaliGemma 2 Object Detection with Transformers

1
Comments
8 min read
đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.