Li

Xiangtai's activity

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

upvoted 3 papers 3 days ago

Scaling Law for Quantization-Aware Training

Paper • 2505.14302 • Published 9 days ago • 67

Web-Shepherd: Advancing PRMs for Reinforcing Web Agents

Paper • 2505.15277 • Published 8 days ago • 96

MMaDA: Multimodal Large Diffusion Language Models

Paper • 2505.15809 • Published 8 days ago • 83

upvoted a paper 20 days ago

On Path to Multimodal Generalist: General-Level and General-Bench

Paper • 2505.04620 • Published 22 days ago • 78

upvoted a paper about 1 month ago

Pixel-SAIL: Single Transformer For Pixel-Grounded Understanding

Paper • 2504.10465 • Published Apr 14 • 28

liked a dataset about 2 months ago

Enxin/Football

Viewer • Updated Mar 22, 2024 • 44.6M • 2.33k • 4

upvoted a paper about 2 months ago

An Empirical Study of GPT-4o Image Generation Capabilities

Paper • 2504.05979 • Published Apr 8 • 63

updated 4 models 2 months ago

ByteDance/Sa2VA-1B

Image-Text-to-Text • Updated Mar 19 • 1.78k • 24

ByteDance/Sa2VA-4B

Image-Text-to-Text • Updated Mar 19 • 1.24k • 73

ByteDance/Sa2VA-8B

Image-Text-to-Text • Updated Mar 19 • 1.18k • 56

ByteDance/Sa2VA-26B

Image-Text-to-Text • Updated Mar 19 • 275 • 25

New activity in ByteDance/Sa2VA-4B 3 months ago

Issue when running inference with the 4B model

3

#3 opened 5 months ago by

armandal

New activity in google/siglip2-giant-opt-patch16-384 3 months ago

AutoModel.from_pretrained error in loading state_dict

4

#3 opened 3 months ago by

Srymaker

upvoted a collection 4 months ago

Sa2VA Model Zoo

Collection

Huggingace Model Zoo For Sa2VA: Marrying SAM2 with LLaVA for Dense Grounded Understanding of Images and Videos By Bytedance Seed CV Research • 4 items • Updated Feb 9 • 35

liked a model 4 months ago

ByteDance/Sa2VA-26B

Image-Text-to-Text • Updated Mar 19 • 275 • 25

updated a collection 4 months ago

Sa2VA Model Zoo

Collection

Huggingace Model Zoo For Sa2VA: Marrying SAM2 with LLaVA for Dense Grounded Understanding of Images and Videos By Bytedance Seed CV Research • 4 items • Updated Feb 9 • 35

New activity in ByteDance/Sa2VA-4B 5 months ago

Fix for 'got multiple values for keyword argument 'return_dict'

👍 1

2

#1 opened 5 months ago by

Blackroot

Update README.md

#5 opened 5 months ago by

LXT

upvoted a paper 5 months ago

Sa2VA: Marrying SAM2 with LLaVA for Dense Grounded Understanding of Images and Videos

Paper • 2501.04001 • Published Jan 7 • 46