VLMs

Feeds to Scour
SubscribedAll
Scoured 261 posts in 6.1 ms

Decoding Pedestrian Crossing Intention from Egocentric Vision via Vision Language Models

 🎭Multimodal AI  Content type: Academic
arxiv.org·

NVlabs/Eagle: Eagle: Frontier Vision-Language Models with Data-Centric Strategies

 🎭Multimodal AI  Content type: Code
github.com·
Less-relevant results

Disquiet Junto Project 0754: The Blip

 🎭Multimodal AI
llllllll.co·

A generalist biomedical vision-language model via multi-CLIP knowledge distillation

 🎭Multimodal AI  Content type: Academic
nature.com·

OpenCV 5 Debuts with Improved ONNX Support and Native AI Upgrades

 🧠LLMs  Content type: News
hackster.io·

OpenCV 5.0 Released With Rewritten DNN Engine, Built-In LLM & VLM Support

 🎭Multimodal AI
phoronix.com··Hacker News

Sale Sharks: Blip or decline after season of strife for Prem club?

 🎭Multimodal AI  Content type: News
bbc.com·

openpilot 0.11.1

 🎭Multimodal AI  Content type: Blog
blog.comma.ai·

MSUE: Multi-Modal Soccer Understanding Expert

 🎭Multimodal AI  Content type: Academic
arxiv.org·

dimitrisdimitrov5-blip/Phantomix: The open-source AI browser agent. Free alternative to OpenAI Operator.

 🔓Open-source Models  Content type: Code
github.com··Hacker News

Scott Bessent says America's in a 'manufacturing renaissance' and Wall Street largely agrees. So where are the jobs?

 🎭Multimodal AI
fortune.com
·

Pinterest inks $4 billion AI deal with AWS, the largest infrastructure commitment in its history

 🎭Multimodal AI
aboutamazon.com·

Modeling Complex Behaviors: Multi-Personality Composition and Dynamic Switching in Vision-Language Models

 🎭Multimodal AI  Content type: Academic
arxiv.org·

A Blip on a Telescope in a Colorado Parking Lot Bolstered a Space Mission That Has Found Thousands of Planets … and Counting

 🎭Multimodal AI
smithsonianmag.com·

A primordial black hole nicknamed ‘Phoebe’ may help solve the mystery of dark matter

 🎭Multimodal AI

VL-DINO: Leveraging CLIP Vision-Language Knowledge for Open-Vocabulary Object Detectio

 🎭Multimodal AI  Content type: Academic
arxiv.org·

Geometric Coastline Localization using Vision-Language Models

 🎭Multimodal AI  Content type: Academic
arxiv.org·

OpenMedReason: Scientific Reasoning Supervision for Medical Vision-Language Models

 💡AI Reasoning  Content type: Academic
arxiv.org·

Pinterest Deepens AWS Partnership with US$4bn Cloud Deal

 🎭Multimodal AI  Content type: News
aimagazine.com·

Reroute, Don't Remove: Recoverable Visual Token Routing for Vision-Language Models

 🎭Multimodal AI  Content type: Academic
arxiv.org·

Keyboard Shortcuts

Navigation

Next / previous item
j/k
Open post
oorEnter
Preview post
v

Post Actions

Love post
a
Like post
l
Dislike post
d
Undo reaction
u
Save / unsave
s

Recommendations

Add interest / feed
Enter
Not interested
x

Go to

Home
gh
Interests
gi
Feeds
gf
Likes
gl
History
gy
Changelog
gc
Settings
gs
Browse
gb
Search
/

General

Show this help
?
Submit feedback
!
Close modal / unfocus
Esc

Press ? anytime to show this help