Wang

ShihaoW's activity

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

upvoted a paper 3 days ago

VFlash: Fast, Accurate Visual Planning via Flash Primitive Decoding

Paper • 2611.08449 • Published 4 days ago • 109

New activity in nvidia/LocateAnything-3B 4 months ago

Using LocateAnything-3B for real-time grounding in robotic inspection (Isaac Sim + UR5e)

1

#26 opened 4 months ago by

taha-M

New activity in nvidia/LocateAnything-3B 5 months ago

Fine-tuning with Lora

3

#23 opened 5 months ago by

hanshupe

solid model

1

#24 opened 5 months ago by

dpe1

NotImplementedError: self._attn_implementation='flash_attention_2'

3

#18 opened 5 months ago by

phamvantoan

New activity in nvidia/LocateAnything 5 months ago

Model hallucinating on easy tasks

1

#3 opened 5 months ago by

johnlockejrr

updated a model 5 months ago

nvidia/LocateAnything-3B

Image-Text-to-Text • 4B • Updated Jun 12 • 157k • 3.18k

New activity in nvidia/LocateAnything-3B 5 months ago

This is the greatest release since GPT 3.5, 'Self Automating Machines'

7

#9 opened 5 months ago by

darkmatter2222

[fastest inference] locateanything-batch — batched + KV-cached LocateAnything-3B, ~2.7× faster

👀🚀 6

1

#10 opened 5 months ago by

Liuwang971

Inference support for vLLM and SGLang OpenAI endpoints

➕ 14

10

#3 opened 5 months ago by

Vishva007

Batch query

2

#5 opened 5 months ago by

SRai22

ComfyUI Node

1

#7 opened 5 months ago by

Alissonerdx

Installation Video and Testing - Step by Step

1

#6 opened 5 months ago by

fahdmirzac

upvoted a paper 5 months ago

GGT-100K: Generative Ground Truth for Generalizable Real-World Image Restoration

Paper • 2605.31039 • Published May 29 • 44

New activity in nvidia/LocateAnything-3B 5 months ago

Great model!

3

#1 opened 5 months ago by

JeanJan90

liked a Space 5 months ago

Running on Zero

Agents

8

LocateAnything

💬

8

Detect and annotate objects in images or videos

New activity in nvidia/LocateAnything 5 months ago

gradio server

1

#1 opened 5 months ago by

akhaliq

upvoted a paper 6 months ago

LLaVA-OneVision-2: Towards Next-Generation Perceptual Intelligence

Paper • 2605.25979 • Published May 25 • 24

authored a paper 6 months ago

LocateAnything: Fast and High-Quality Vision-Language Grounding with Parallel Box Decoding

Paper • 2605.27365 • Published May 26 • 141

updated a collection 6 months ago

Eagle

Collection

Eagle is a family of frontier vision-language models with data-centric strategies. The model supports both HD image and long-context video input. • 17 items • Updated 20 days ago • 51