VLA

Feeds to Scour
SubscribedAll
Scoured 85 posts in 4.8 ms

The Battle of Socorro, New Mexico and the Uprising Against AI Data Centers

 🤖AI, Robotics, Embodied AI
counterpunch.org·

GEAR-VLA: Learning Geometry-Aware Action Representations for Generalizable Robotic Manipulation

 🤖AI, Robotics, Embodied AI  Content type: Academic
arxiv.org·

Slow Token, Fast ActionLearning in Robotics

 🤖AI, Robotics, Embodied AI  Content type: Blog

The DeepMind and Boston Dynamics team building the brain for every robot raises $400M — TFN

 🤖AI, Robotics, Embodied AI
techfundingnews.com·

TBD-VLA: Temporal Block Diffusion Vision Language Action Model

 🤖AI, Robotics, Embodied AI  Content type: Academic
arxiv.org·

LAST: Bridging Vision-Language and Action Manifolds via Gromov-Wasserstein Alignment

 🤖AI, Robotics, Embodied AI  Content type: Academic
arxiv.org·

Cockpit-Driving Fusion, Qualcomm Unveils Another Major Move

 🤖AI, Robotics, Embodied AI
autonews.gasgoo.com·

MotionVLA: Injecting Geometric Motion into Vision-Language-Action Model

 🤖AI, Robotics, Embodied AI  Content type: Academic
arxiv.org·

A Chinese startup just dethroned Nvidia on the benchmark Nvidia helped build

 🤖AI, Robotics, Embodied AI  Content type: News
thenextweb.com·

FiberTune: Preserving Action-Fiber Visual Residuals in Vision-Language-Action Fine-Tuning

 🤖AI, Robotics, Embodied AI  Content type: Academic
arxiv.org·

Back to the Familiar Future: Failure Recovery for VLA Policies via Pre-Imagined Milestone Selection

 🤖AI, Robotics, Embodied AI  Content type: Academic
arxiv.org·

Xpeng loses robotics product head as 2026 mass production target looms

 🤖AI, Robotics, Embodied AI
cnevpost.com·

Benchmarking Vision-Language-Action Models on SO-101: Failure and Recovery Analysis

 🤖AI, Robotics, Embodied AI  Content type: Academic
arxiv.org·

TORL-VLA: Tactile Guided Online Reinforcement Learning for Contact-Rich Manipulation

 🤖AI, Robotics, Embodied AI  Content type: Academic
arxiv.org·

VeriSpace: Spatially Grounded Action Verification for Vision-Language-Action Models

 🤖AI, Robotics, Embodied AI  Content type: Academic
arxiv.org·

NVIDIA/cosmos: NVIDIA Cosmos is an open platform of world models, datasets, and tools that enables developers to build Physical AI for robots, autonomous vehicles, smart infrastructure, and more.

 🤖LLM  Content type: Code
github.com·

vla.cpp: A Unified Inference Runtime for Vision-Language-Action Models

 🤖AI, Robotics, Embodied AI  Content type: Academic
arxiv.org·

Two Bridges, One Pathway: From VLMs to Generalizable VLAs with Embodied Trajectory-Coupled Data

 🤖AI, Robotics, Embodied AI  Content type: Academic
arxiv.org·

Sparse Autoencoders Reveal Interpretable and Steerable Features in VLA Models

 🤖AI, Robotics, Embodied AI  Content type: Academic
arxiv.org·

LIBERO-Occ: Evaluating and Improving Vision-Language-Action Models under Scene-Induced Occlusion via Viewpoint Imagination

 🤖AI, Robotics, Embodied 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