Jing Wu 🍄

Ex-Intern @MSFTResearch, DPhil student @AVLOxford @UniOfOxford @St_Catz | CUA Agents, 3D Vision, Generative AI, Music and Arts

[Jing Wu 🍄 @jingwu23]

📣 2 New Papers!!

I am happy to share my 2 recent works. 🥳

1️⃣ [ArXiv Preprint]: ⏱️OS-Marathon: Benchmarking Computer-Use Agents on Long-Horizon Repetitive Tasks
- 🌐Project: https://t.co/NORAd1ptuL
- 📑 Paper: https://t.co/UxERGlevQb

2️⃣ [3DV] Reflect3r: Single-View 3D Stereo Reconstruction Aided by Mirror Reflections
- 🌐Project: https://t.co/9X66b0dIrH
- 🚀Code: https://t.co/Jv3JxE2aER
- 🤗HF: https://t.co/VEji2srAru

[harpreet @DataScienceHarp]

great work on reflect3r from @jingwu23 and co from @3DVconf. the dataset has 16 synthetic blender interior scenes, each with a mirror, rendered from both a real camera and a geometrically derived virtual mirror camera, along with ground-truth point clouds

[Jing Wu 🍄 @jingwu23]

Excited to share that our synthetic evaluation benchmark is now integrated into @Voxel51.

Huge thanks to Harpreet Sahota and the @Voxel51 team for making this happen!

Check it out 👉: https://t.co/NY4zzckZTt

[Jing Wu 🍄 @jingwu23]

📣📣 Introducing Reflect3r @3DVconf
✅ Single-view to 3D reconstruction by using mirror reflections as an auxiliary view
✅ A synthetic evaluation dataset containing 16 fully customizable Blender scenes.
This is a joint work with @ziruiwang_, Iro Laina, and @viprad

🌐 Project Page: https://t.co/9X66b0dIrH
📄 Paper: https://t.co/nk5NWyKOUv
👩‍💻 Code: https://t.co/Jv3JxE2aER
🤗 Huggingface: https://t.co/VEji2srAru

[Qwen @Alibaba_Qwen]

🚀 Introducing the Qwen 3.5 Small Model Series
Qwen3.5-0.8B · Qwen3.5-2B · Qwen3.5-4B · Qwen3.5-9B

✨ More intelligence, less compute.
These small models are built on the same Qwen3.5 foundation — native multimodal, improved architecture, scaled RL:
• 0.8B / 2B → tiny, fast, great for edge device
• 4B → a surprisingly strong multimodal base for lightweight agents
• 9B → compact, but already closing the gap with much larger models
And yes — we’re also releasing the Base models as well.
We hope this better supports research, experimentation, and real-world industrial innovation.
Hugging Face: https://t.co/wFMdX5pDjU
ModelScope: https://t.co/9NGXcIdCWI

[Alexandre Morgand @Almorgand]

@jingwu23 @ziruiwang_ @IroLaina Victor Adrian Prisacariu

@UniofOxford

Project page: https://t.co/tlJlNk4cMD
Paper: https://t.co/RIvcHG9niA
Source code: https://t.co/xo3vFMvHxA

[Jing Wu 🍄 @jingwu23]

📣📣 Introducing OS-Marathon⏱️

I am proud to share this interesting project I did during my internship @Microsoft @MSFTResearch. 🥳

This work is about benchmarking computer-use agents' ability on a type of long-horizon, repetitive tasks.

✅ We focus on desktop workflows that are long-horizon and also repetitive, e.g. filling the expense system given a set of various travelling receipts.
✅ We create data, build tasks and environments and categorise them into multiple difficulty levels to enable fine-grained evaluation.

📎Project Page: https://t.co/NORAd1ptuL
📄Paper: https://t.co/UxERGlevQb

Joint work with Daphne Barretto, Yiye Chen, Nicholas Gydé, Yanan Jian, Yuhang He @HenryOxplore, Vibhav Vineet @VibhavVineet

[Jing Wu 🍄 @jingwu23]

📣📣 Introducing Reflect3r @3DVconf
✅ Single-view to 3D reconstruction by using mirror reflections as an auxiliary view
✅ A synthetic evaluation dataset containing 16 fully customizable Blender scenes.
This is a joint work with @ziruiwang_, Iro Laina, and @viprad

🌐 Project Page: https://t.co/9X66b0dIrH
📄 Paper: https://t.co/nk5NWyKOUv
👩‍💻 Code: https://t.co/Jv3JxE2aER
🤗 Huggingface: https://t.co/VEji2srAru

[Zirui Wang @ziruiwang_]

Excited to share that our Oxford Day-and-Night dataset has been accepted to the NeurIPS 2025 Dataset track! See you in San Diego!

📦 Dataset: https://t.co/FGOKTaKv5W
🌐 Project Page: https://t.co/VDbGYgKq5z

[Jing Wu 🍄 @jingwu23]

Happening now!

[Jing Wu 🍄 @jingwu23]

🥳 We are going to present our poster GaussCtrl at #ECCV2024 in Milan! @eccvconf

Feel free to come and say hi to my poster if you're interested!! 😼

🗓️ Thu 3 Oct 4:30 p.m. CEST — 6:30 p.m. CEST, Poster #261

See you there!!😉

🌐 https://t.co/GKGVV4CFYa

[Jing Wu 🍄 @jingwu23]

🥳 We are going to present our poster GaussCtrl at #ECCV2024 in Milan! @eccvconf

Feel free to come and say hi to my poster if you're interested!! 😼

🗓️ Thu 3 Oct 4:30 p.m. CEST — 6:30 p.m. CEST, Poster #261

See you there!!😉

🌐 https://t.co/GKGVV4CFYa

[MrNeRF @janusch_patas]

Oh wow! I just tested Splatt3R with my own data on my computer, which creates 3D Gaussian Splats at 4 FPS on uncalibrated 512x512 2D images!

It's by far the fastest 3D reconstruction method, powered by MASt3R.

Check out the video!

[Nick St. Pierre @nickfloats]

images: @midjourney
style: --p rixmhgc
music: @suno_ai_
video: @Kling_ai
upscale: @topazlabs
soundfx: @elevenlabs

[Jing Wu 🍄 @jingwu23]

‼️📢Code is released: https://t.co/fJ0XsfxpAP

[Jing Wu 🍄 @jingwu23]

📢📢 📢 Introducing GaussCtrl!!
✅Easy control your Gaussian Splatting model with a text prompt! 🤩
✅Remarkable multi-view consistency quality!
w/ Jia-Wang Bian, @li_xinghui @wanggrun, Ian Reid, Philip Torr, and @viprad
🌐https://t.co/OexUS2NiSP
📰https://t.co/B2jbgL7DV0

[Jing Wu 🍄 @jingwu23]

We got into ECCV!!!!!

[Jing Wu 🍄 @jingwu23]

📢📢 📢 Introducing GaussCtrl!!
✅Easy control your Gaussian Splatting model with a text prompt! 🤩
✅Remarkable multi-view consistency quality!
w/ Jia-Wang Bian, @li_xinghui @wanggrun, Ian Reid, Philip Torr, and @viprad
🌐https://t.co/OexUS2NiSP
📰https://t.co/B2jbgL7DV0

[Stanley H. Chan @stanley_h_chan]

Diffusion models for imaging and vision

Just made this set of slides for an upcoming talk. Feedback is welcome!

Slides: https://t.co/lmFfMHMXAJ

Tutorial (March version): https://t.co/fWv111nG5M
(Thx for messaging me the typos. Still working on them.)

[Framer 🇱🇹 @Framer_X]

"The Construction of a Neon City" 🌆

Supercharging a static Midjourney picture with Photoshop's Generative Fill, WORKFLOW

Time spent: 3 hours 10 minutes. Complexity 6/10

Sound On 🔊

[Framer 🇱🇹 @Framer_X]

I put myself into a Midjourney picture 🤯

I still can't believe how easy it was!

Here’s what I did:

[Framer 🇱🇹 @Framer_X]

Create a looping Lofi animation IN 30 MINUTES with CAPCUT.

I still can't believe how ridiculously easy it is.

Here's what you need to do 👇