fame.

[Angela Yao @angelayao101]

Excited to share that Assembly101 is now hosted on Hugging Face 🤗

https://t.co/nKGRHYTl8U

We've migrated the full dataset and annotations to improve accessibility and ensure long-term availability for the community.

[Qwen @Alibaba_Qwen]

📣 Introducing the Qwen-Robot Suite — Qwen-RobotNav, Qwen-RobotManip, Qwen-RobotWorld, three foundation models, a full stack for embodied intelligence.

🧭 Qwen-RobotNav — the gateway to mobility.
• Unifies 5 navigation tasks in one model: instruction following, point-goal, object-goal, target tracking, autonomous driving
• Controllable observation protocol
• Tool interface for agentic systems

🤖 Qwen-RobotManip — the foundation of interaction.
• Unified state-action space across heterogeneous robots
• Camera-frame delta poses for coherent cross-embodiment training
• Pretrained on a 38,100+ hour open-source corpus

🌍 Qwen-RobotWorld — infinite worlds for physical agents.
• Single world model, 20+ embodiments
• Natural-language action interface
• Predicts physically grounded futures across manipulation, driving, and navigation

Each model is independently useful, and could be composed as physical-world tools.Together, they form the low-level toolkit for general-purpose agentic systems that don't just see the world, but act in it.

📷 Blog:
https://t.co/ytLcbYET26
📖 Report：
Qwen-RobotNav: https://t.co/uPmSwDYGxg
Qwen-RobotManip: https://t.co/GeyIzJSpU8
Qwen-RobotWorld： https://t.co/SXPH1qzDFy

[Space and Technology @spaceandtech_]

Researchers at RAI Institute developed the Koala gripper to help robots handle tools and objects more naturally.

The system includes a handheld version for humans and a motorized version for robots, both using the same design and sensors.

By learning from human demonstrations recorded with cameras and force sensors, robots can repeat the same tasks using the Koala gripper.

[Apratim Bhattacharyya @apratimbh]

🚨Have work in progress or an accepted @CVPR 2026 paper? Submit to the 2nd VAR Workshop!

🎯Topics include:
• Streaming VLMs
• Real-time activity understanding
• VLM grounding
• Egocentric video understanding
• Language & robot learning

👉https://t.co/jve18jCqUc

[Apratim Bhattacharyya @apratimbh]

🚨🚨🚨Extending the deadline to March 7th 2026, taking into account the ECCV deadline❗️

👉Details: https://t.co/5n8tfJb9W4

@CVPR

[Apratim Bhattacharyya @apratimbh]

Submit to the 2nd VAR Workshop @CVPR :
* Streaming/online vision-language models
* Real-time activity understanding
* Grounding of vision-language models
* Ego-centric video understanding
* Language and robot learning

Details : https://t.co/5n8tfJaC6w

[fame. @famesener]

A rainy day strolling through #Morcote, #Switzerland …

[#ICCV2025 @ICCVConference]

#ICCV2025 decisions have been released!

They are going out in batches to manage server load, so please be patient :)

A huge thank you to our entire community—authors, reviewers, and area chairs—for your hard work.

Congratulations to everyone whose paper was accepted!

[Sammy Joe Christen @sammy_j_c]

If you are at #RSS2025, check out our workshop on Generative AI for Human-Robot Interaction. We have a stacked lineup of speakers and panelists!

[Snehal Jauhri @SnehalJauhri]

We are glad to host an exciting array of speakers! @xiaolonw, Kristen Grauman, @anfurnari @angelayao101 @mangahomanga @simar_kareer

Also look out for a special demonstration and talk by our sponsor, Meta @AIatMeta @RealityLabs on the new Aria Gen2 device @meta_aria!

[fame. @famesener]

One great thing about attending @CVPR from #Europe is the chance to stop over in #Iceland
Roaming this stunning island under the midnight sun, almost completely alone, is amazing ☺️

[Paul Streli @paulstreli]

EgoPressure at @CVPR 2025 (Highlight)!

w/ @_yimzhao_ , @taeinkwon1 , @mapo1 , @cholz

🌍 Project page: https://t.co/Ndm0Mo8Bvx
📰 Paper: https://t.co/w8C669rnny

📍Come visit us during our poster session in ExHall D Poster 149, 15 Jun, 16:00 CDT — 18:00 CDT!

[Apratim Bhattacharyya @apratimbh]

Come by our poster #135 between 16:00 - 18:00 tomorrow at @CVPR on distilling LLMs for safe and efficient autonomous driving policies.

@deeptibhegde @RajeevYasarla @Matewhs

👉Paper: https://t.co/313sXjq4kb

[Angela Yao @angelayao101]

Come by to find out about Minjoon’s work on the temporal consistency of video LLMs! Saturday morning poster 293!

[Glory Chen @glory_chen]

🚀 Please visit & check out our @angelayao101 @cvml_nus #CVPR2025 paper for condensing datasets of video temporal action segmentation!
🗓️ Today, 17:00 - 19:00
📍 Poster #184
🌐 https://t.co/a2MEd5VA0d
#CVPR2025

[Visual Geometry Group (VGG) @Oxford_VGG]

Congratulations to @taeinkwon1 and the Team for presenting their work "A Dataset for Hand Pressure and Pose Estimation in Egocentric Vision" as a @CVPR
Highlight #CVPR25 🙌 🎉. https://t.co/HsuGLEljx1

[fame. @famesener]

PSC @ cvpr25 🙈 @ncihancamgoz @tekinbugra

[fame. @famesener]

Zhanzhong Pang is presenting soon #CVPR2025
📍 ExHall D, Poster #318

Context-Enhanced Memory-Refined Transformer for Online Action Detection

https://t.co/OOYiVrLrX3

[Angela Yao @angelayao101]

🚀 Check out our #CVPR2025 paper for efficient streaming action detection!

Today @4pm Poster #318.

https://t.co/J7Gee5frQc

✅ SOTA DinoV2 features
✅ Temporal detection metrics
✅ New benchmark w/ diverse domains

[Angela Yao @angelayao101]

🚀 Check out our #CVPR2025 paper for efficient streaming action detection!

Today @4pm Poster #318.

https://t.co/J7Gee5frQc

✅ SOTA DinoV2 features
✅ Temporal detection metrics
✅ New benchmark w/ diverse domains

[Angela Yao @angelayao101]

Uni Bonn reunion at #CVPR2025 ❤️