issues
search
shikiw
/
OPERA
[CVPR 2024 Highlight] OPERA: Alleviating Hallucination in Multi-Modal Large Language Models via Over-Trust Penalty and Retrospection-Allocation
MIT License
215
stars
17
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
关于复现POPE的结果问题
#33
1906200111
opened
2 weeks ago
4
关于可视化
#32
yubo97
opened
2 weeks ago
1
关于是否是幻觉句子的问题
#31
clclclaiggg
closed
2 weeks ago
2
CHAIR hallucination evaluation
#30
running-alpaca
opened
1 month ago
2
Shikra Version
#29
summoneryhl
closed
1 month ago
0
Could you provide the 'model.generate_output' function?
#28
huofushuo
closed
1 month ago
2
Truncation of generated results
#27
lalulxm
closed
1 month ago
3
Does the method to find `knowledge aggregation pattern` have any relevant papers to reference in NLP domain?
#26
shanpoyang654
closed
1 month ago
1
stopping criteria
#25
yeonju7kim
closed
2 months ago
1
Questions about function prepare_inputs_labels_for_multimodal
#24
KlaineWei
opened
2 months ago
1
运行vis.ipynb报错
#23
Ivesfu
closed
2 months ago
1
reproducing shikra problem
#22
KlaineWei
closed
2 months ago
0
GPU information
#21
KlaineWei
closed
2 months ago
4
CHAIR Reproduction Bugs
#20
xing0047
closed
2 months ago
6
reproducing the result
#19
JEONG8652
closed
2 months ago
2
Questions about Figure 3 in paper
#18
minhoooo1
closed
2 months ago
1
Over-Trust Logit Penalty
#17
hubujy
closed
2 months ago
1
是否能支持4.37.2 的transformers
#16
awzhgw
opened
3 months ago
2
AssertionError: OPERA does not support beam=1 in the current version. It will be added in the future.
#15
FanshuoZeng
closed
2 months ago
1
Could you provide the script to plot the attention map?
#14
Rainlt
closed
3 months ago
9
Support for interleaved image-text comprehension(multi-image)
#13
laserwave
closed
3 months ago
1
Random 500 samples in MSCOCO?
#12
zhaoshitian
closed
3 months ago
2
Acknowledge LAVIS
#11
dxli94
closed
3 months ago
1
Attention map plotting
#10
franciscoliu
closed
3 months ago
1
can you add support for other models like QWEN-VL in the future?
#9
chuangzhidan
closed
3 months ago
10
Reproducing MiniGPT-4's POPE result
#8
Ocean-627
closed
4 months ago
4
What should key_position be on mPLUG-Owl2?
#7
BillChan226
closed
3 months ago
1
opera_greedy_search implemented ?
#6
BillChan226
closed
5 months ago
1
AttributeError: 'MiniGPT4' object has no attribute 'embed_tokens'
#5
BillChan226
closed
6 months ago
2
'MiniGPT4' object has no attribute 'embed_tokens'
#4
isruihu
closed
7 months ago
0
Model inference speed is slow
#3
hlz0606
closed
5 months ago
2
Questions about the IM_START and IM_END tokens
#2
Haotian-Zhang
opened
7 months ago
1
Does it work well on videos?
#1
YajieW99
closed
3 months ago
1