VisRAG: Vision-based Retrieval-augmented Generation on Multi-modality Documents
Paper
•
2410.10594
•
Published
•
27
•
3
Cuiunbo PRO
Cuiunbo
AI & ML interests
Anything
Recent Activity
new activity
about 1 month ago
lerobot/pi0fast_base:Hi!
liked
a model
about 1 month ago
lerobot/pi0fast_base
Organizations
Cuiunbo's activity
Are There Quantitative Metrics, Such as Simo Compared to Other TTS?
1
#7 opened 3 months ago
by
Cuiunbo
`streaming_prefill` can't handle the parameter `omni_input=False`
1
#31 opened 3 months ago
by
yzmyyff
add task to the model for better discoverability
#2 opened 4 months ago
by
reach-vb
Where are the MiniCPM-o 2.6 int4 weights?
1
#9 opened 4 months ago
by
AiCreatornator
int-4 quantized version is missing [link broken]
1
#10 opened 4 months ago
by
pranay-ar
Why are you calling this style-controlled TTS End-to-End?
5
#8 opened 4 months ago
by
JosephusCheung
GUIChat box coordinates are shifted
2
#3 opened 7 months ago
by
HongxinLi
commented
a
paper
7 months ago
Is it possible to merge MiniCPM-Llama3-V-2-5 with a Llama-3-1 based model using MOE
10
#68 opened 9 months ago
by
rameshch
Needs OCR data improvements
3
#14 opened 9 months ago
by
mrasker
index is out of bounds for dimension with size 0
5
7
#23 opened 9 months ago
by
akm78
Does this come in an English speaking version?
3
#7 opened 9 months ago
by
sdalemorrey
OCR Capabilities Not So Good As Stated
1
#8 opened 9 months ago
by
bigbrotherr
Differences between minicpm v2.0 and minicpm-guidance
1
#1 opened 10 months ago
by
anothercoder2
gguf / llama.cpp support
2
#45 opened 11 months ago
by
cmp-nct
The Kernel crashed while executing code in the current cell or a previous cell.
2
#34 opened 11 months ago
by
Entz
关于openai compatible api
1
#41 opened 11 months ago
by
weiminw