Score-CAM: Score-Weighted Visual Explanations for Convolutional Neural Networks
Paper
ā¢
1910.01279
ā¢
Published
Haofan Wang
wanghaofan
AI & ML interests
Co-Founder&Researcher@InstantX
Recent Activity
authored
a paper
3 days ago
Score-CAM: Score-Weighted Visual Explanations for Convolutional Neural
Networks
authored
a paper
3 days ago
One-shot Implicit Animatable Avatars with Model-based Priors
authored
a paper
3 days ago
Image Watermarks are Removable Using Controllable Regeneration from
Clean Noise
Organizations
wanghaofan's activity
authored
4
papers
3 days ago
One-shot Implicit Animatable Avatars with Model-based Priors
Paper
ā¢
2212.02469
ā¢
Published
Image Watermarks are Removable Using Controllable Regeneration from Clean Noise
Paper
ā¢
2410.05470
ā¢
Published
EasyControl: Adding Efficient and Flexible Control for Diffusion Transformer
Paper
ā¢
2503.07027
ā¢
Published
ā¢
21
upvoted
a
paper
3 days ago
reacted to
AdinaY's
post with š„
17 days ago
Post
2467
Two AI startups, DeepSeek & Moonshot AI , keep moving in perfect sync š
āØ Last December: DeepSeek & Moonshot AI released their reasoning models on the SAME DAY.
DeepSeek: deepseek-ai/DeepSeek-R1
MoonShot: https://github.com/MoonshotAI/Kimi-k1.5
āØ Last week: Both teams published papers on modifying attention mechanisms on the SAME DAY AGAIN.
DeepSeek: Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention (2502.11089)
Moonshot: MoBA: Mixture of Block Attention for Long-Context LLMs (2502.13189)
āØ TODAY:
DeepSeek unveiled Flash MLA: a efficient MLA decoding kernel for NVIDIA Hopper GPUs, optimized for variable-length sequences.
https://github.com/deepseek-ai/FlashMLA
Moonshot AI introduces Moonlight: a 3B/16B MoE trained on 5.7T tokens using Muon, pushing the Pareto frontier with fewer FLOPs.
moonshotai/Moonlight-16B-A3B
What's next? š
āØ Last December: DeepSeek & Moonshot AI released their reasoning models on the SAME DAY.
DeepSeek: deepseek-ai/DeepSeek-R1
MoonShot: https://github.com/MoonshotAI/Kimi-k1.5
āØ Last week: Both teams published papers on modifying attention mechanisms on the SAME DAY AGAIN.
DeepSeek: Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention (2502.11089)
Moonshot: MoBA: Mixture of Block Attention for Long-Context LLMs (2502.13189)
āØ TODAY:
DeepSeek unveiled Flash MLA: a efficient MLA decoding kernel for NVIDIA Hopper GPUs, optimized for variable-length sequences.
https://github.com/deepseek-ai/FlashMLA
Moonshot AI introduces Moonlight: a 3B/16B MoE trained on 5.7T tokens using Muon, pushing the Pareto frontier with fewer FLOPs.
moonshotai/Moonlight-16B-A3B
What's next? š
upvoted
a
collection
19 days ago
updated
a
dataset
22 days ago
Update README.md
#3 opened 22 days ago
by
wanghaofan
liked
a
model
25 days ago
published
a
model
25 days ago
updated
a
model
26 days ago
updated
2
Spaces
26 days ago
liked
a
dataset
28 days ago
liked
a
Space
29 days ago
liked
a
model
about 1 month ago
updated
a
model
about 1 month ago
published
a
model
about 1 month ago
liked
a
model
about 1 month ago
